agentscope-ai/agentscope

39.0

Adjusted Score

39.0

Raw Score

100%

Time Factor

2026-08-28

Last Push

29.9K

Stars

Python

Language

246.3K

Lines of Code

970

Files

5.1K

Pattern Hits

2026-08-29

Scan Date

0.49

HC Hit Rate

What These Metrics Mean

Adjusted Score: Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score: The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor: The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits: Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate: High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files: Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

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.

Severity Breakdown

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.

CRITICAL 2HIGH 477MEDIUM 1206LOW 3420

Directory Score Breakdown

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.

Pattern Findings

The scanner identified 5105 distinct pattern matches across 21 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.

Decorative Section Separators1132 hits · 3632 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tests/mem0_middleware_test.py	199	# ----------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/mem0_middleware_test.py	201	# ----------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/mem0_middleware_test.py	276	# ----------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/mem0_middleware_test.py	278	# ----------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/mem0_middleware_test.py	844	# ----------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/mem0_middleware_test.py	846	# ----------------------------------------------------------------------	COMMENT
MEDIUM	tests/mem0_middleware_test.py	38	# ----------------------------------------------------------------------	COMMENT
MEDIUM	tests/mem0_middleware_test.py	40	# ----------------------------------------------------------------------	COMMENT
MEDIUM	tests/mem0_middleware_test.py	128	# ----------------------------------------------------------------------	COMMENT
MEDIUM	tests/mem0_middleware_test.py	130	# ----------------------------------------------------------------------	COMMENT
MEDIUM	tests/mem0_middleware_test.py	533	# ----------------------------------------------------------------------	COMMENT
MEDIUM	tests/mem0_middleware_test.py	535	# ----------------------------------------------------------------------	COMMENT
MEDIUM	tests/model_ollama_test.py	23	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/model_ollama_test.py	25	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/model_ollama_test.py	112	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/model_ollama_test.py	114	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/model_ollama_test.py	202	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/model_ollama_test.py	204	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/model_ollama_test.py	347	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/model_ollama_test.py	349	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/storage_sql_test.py	188	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/storage_sql_test.py	190	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/storage_sql_test.py	242	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/storage_sql_test.py	244	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/storage_sql_test.py	312	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/storage_sql_test.py	314	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/storage_sql_test.py	393	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/storage_sql_test.py	395	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/storage_sql_test.py	487	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/storage_sql_test.py	489	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/storage_sql_test.py	580	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/storage_sql_test.py	582	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/storage_sql_test.py	803	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/storage_sql_test.py	805	# ------------------------------------------------------------------	COMMENT
MEDIUM	tests/storage_sql_test.py	830	# ------------------------------------------------------------------	COMMENT
MEDIUM	tests/storage_sql_test.py	832	# ------------------------------------------------------------------	COMMENT
MEDIUM	tests/storage_sql_test.py	924	# ------------------------------------------------------------------	COMMENT
MEDIUM	tests/storage_sql_test.py	926	# ------------------------------------------------------------------	COMMENT
MEDIUM	tests/formatter_openai_chat_test.py	46	# ---------------------------------------------------------------	COMMENT
MEDIUM	tests/formatter_openai_chat_test.py	49	# ---------------------------------------------------------------	COMMENT
MEDIUM	tests/formatter_openai_chat_test.py	110	# ---------------------------------------------------------------	COMMENT
MEDIUM	tests/formatter_openai_chat_test.py	115	# ---------------------------------------------------------------	COMMENT
MEDIUM	tests/formatter_openai_chat_test.py	205	# ---------------------------------------------------------------	COMMENT
MEDIUM	tests/formatter_openai_chat_test.py	211	# ---------------------------------------------------------------	COMMENT
MEDIUM	tests/formatter_openai_chat_test.py	283	# -------------------------------------------------------------------	COMMENT
MEDIUM	tests/formatter_openai_chat_test.py	285	# -------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/formatter_openai_chat_test.py	587	# -------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/formatter_openai_chat_test.py	589	# -------------------------------------------------------------------	COMMENT
MEDIUM	tests/permission_engine_test.py	687	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/permission_engine_test.py	689	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/backend_opensandbox_test.py	30	# ── OpenSandbox availability check ─────────────────────────────────	COMMENT
MEDIUM	tests/backend_opensandbox_test.py	60	# ── exec ───────────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/backend_opensandbox_test.py	91	# ── file I/O ───────────────────────────────────────────────────	COMMENT
MEDIUM⚡	tests/backend_opensandbox_test.py	111	# ── derived filesystem helpers (shell-based) ───────────────────	COMMENT
MEDIUM	tests/hub_router_test.py	266	# ── browse ────────────────────────────────────────────────────	COMMENT
MEDIUM	tests/hub_router_test.py	332	# ── install: MCP ──────────────────────────────────────────────	COMMENT
MEDIUM	tests/hub_router_test.py	576	# ── workspace <-> library ─────────────────────────────────────	COMMENT
MEDIUM	tests/hub_router_test.py	700	# ── install: skill ────────────────────────────────────────────	COMMENT
MEDIUM	tests/formatter_ollama_test.py	170	# ------------------------------------------------------------------	COMMENT
MEDIUM	tests/formatter_ollama_test.py	172	# ------------------------------------------------------------------	COMMENT
1072 more matches not shown…

Hyper-Verbose Identifiers1923 hits · 1773 pts

Severity	File	Line	Snippet	Context
LOW	tests/embedding_openai_test.py	154	async def test_retry_on_transient_error(	CODE
LOW⚡	tests/mem0_middleware_test.py	207	def test_missing_user_id_raises(self) -> None:	CODE
LOW⚡	tests/mem0_middleware_test.py	260	def test_client_alone_does_not_warn(self) -> None:	CODE
LOW⚡	tests/mem0_middleware_test.py	266	def test_only_one_of_chat_or_embedding_without_config_raises(	CODE
LOW⚡	tests/mem0_middleware_test.py	852	async def test_memory_msg_and_tool_hint_both_present(self) -> None:	CODE
LOW	tests/mem0_middleware_test.py	146	def test_list_of_user_msgs_joined(self) -> None:	CODE
LOW	tests/mem0_middleware_test.py	151	def test_resumption_events_return_none(self) -> None:	CODE
LOW	tests/mem0_middleware_test.py	186	def test_plain_list_of_strings(self) -> None:	CODE
LOW	tests/mem0_middleware_test.py	223	def test_neither_client_nor_models_nor_config_raises(self) -> None:	CODE
LOW	tests/mem0_middleware_test.py	231	def test_client_wins_over_other_backend_kwargs_with_warning(	CODE
LOW	tests/mem0_middleware_test.py	304	async def test_retrieve_inject_write(self) -> None:	CODE
LOW	tests/mem0_middleware_test.py	380	async def test_memory_message_lands_after_user_message(self) -> None:	CODE
LOW	tests/mem0_middleware_test.py	415	async def test_no_memories_no_injection(self) -> None:	CODE
LOW	tests/mem0_middleware_test.py	434	async def test_search_failure_does_not_break_reply(self) -> None:	CODE
LOW	tests/mem0_middleware_test.py	451	async def test_scope_search_by_agent_false_drops_agent_id(	CODE
LOW	tests/mem0_middleware_test.py	470	async def test_sync_client_rejected(self) -> None:	CODE
LOW	tests/mem0_middleware_test.py	490	async def test_async_method_wrapped_by_sync_decorator_accepted(	CODE
LOW	tests/mem0_middleware_test.py	567	async def test_tools_listed_and_hint_in_prompt(self) -> None:	CODE
LOW	tests/mem0_middleware_test.py	607	async def test_middleware_does_not_mutate_toolkit(self) -> None:	CODE
LOW	tests/mem0_middleware_test.py	675	async def test_async_search_accepts_per_call_top_k(self) -> None:	CODE
LOW	tests/mem0_middleware_test.py	695	async def test_tools_auto_allow_permission(self) -> None:	CODE
LOW	tests/mem0_middleware_test.py	714	async def test_search_memory_dedupes_across_keywords(self) -> None:	CODE
LOW	tests/mem0_middleware_test.py	736	async def test_search_memory_failure_returns_error_chunk(self) -> None:	CODE
LOW	tests/mem0_middleware_test.py	757	async def test_add_memory_two_tier_fallback(self) -> None:	CODE
LOW	tests/mem0_middleware_test.py	811	async def test_add_memory_does_not_persist_thinking(self) -> None:	CODE
LOW	tests/compress_context_test.py	143	async def _call_api_with_structured_output(	CODE
LOW	tests/compress_context_test.py	176	def _make_failing_compression_agent(	CODE
LOW	tests/compress_context_test.py	861	async def test_split_multi_tool_pairs_reaches_stable_boundary(	CODE
LOW	tests/compress_context_test.py	1183	async def test_context_compression_clears_evicted_read_cache(self) -> None:	CODE
LOW	tests/compress_context_test.py	1255	async def test_context_compression_keeps_reserved_read_cache(	CODE
LOW	tests/compress_context_test.py	1334	async def test_context_compression_clears_unreferenced_read_cache(	CODE
LOW	tests/compress_context_test.py	1392	async def test_context_compression_injects_instructions_as_hint(	CODE
LOW	tests/compress_context_test.py	1457	async def test_context_compression_overflow_retry_keeps_instructions(	CODE
LOW	tests/compress_context_test.py	1523	async def test_max_image_num_without_offloader(self) -> None:	CODE
LOW	tests/compress_context_test.py	1727	async def test_max_image_num_with_offloader(self) -> None:	CODE
LOW	tests/compress_context_test.py	1944	async def test_max_image_num_default(self) -> None:	CODE
LOW	tests/compress_context_test.py	2140	async def test_summary_failure_truncates_context(self) -> None:	CODE
LOW	tests/compress_context_test.py	2154	async def test_offload_reminder_is_not_duplicated(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	73	async def test_raw_json_stream_is_converted(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	88	async def test_sse_data_frame_is_converted(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	108	async def test_sse_heartbeat_is_passed_through(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	115	async def test_sse_data_frame_with_crlf_is_converted(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	135	async def test_fastapi_sse_response_is_converted(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	164	async def test_fastapi_json_response_is_not_converted(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	198	async def test_reply_start_to_run_started(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	212	async def test_reply_end_to_run_finished(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	225	async def test_exceed_max_iters_to_run_error(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	237	async def test_deprecated_exceed_max_iters_to_custom(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	259	async def test_model_call_start_to_step_started(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	270	async def test_model_call_end_to_step_finished(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	346	async def test_thinking_block_start(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	358	async def test_thinking_block_delta(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	442	async def test_tool_result_end_with_buffered_content(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	472	async def test_tool_result_end_fallback_to_state(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	485	async def test_tool_result_start_to_custom(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	498	async def test_tool_result_text_delta_to_custom(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	511	async def test_tool_result_data_delta_to_custom(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	585	async def test_require_user_confirm(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	603	async def test_require_external_execution(self) -> None:	CODE
LOW	tests/agui_protocol_test.py	640	async def test_external_execution_result(self) -> None:	CODE
1863 more matches not shown…

Cross-File Repetition301 hits · 1505 pts

Severity	File	Line	Snippet	Context
HIGH	tests/service_cancel_dispatcher_test.py	0	yield the event loop a few times so spawned tasks make progress.	STRING
HIGH	tests/service_index_task_consumer_test.py	0	yield the event loop a few times so spawned tasks make progress.	STRING
HIGH	tests/service_wakeup_dispatcher_test.py	0	yield the event loop a few times so spawned tasks make progress.	STRING
HIGH	tests/model_ollama_test.py	0	non-stream text response returns a single chatresponse.	STRING
HIGH	tests/model_anthropic_test.py	0	non-stream text response returns a single chatresponse.	STRING
HIGH	tests/model_gemini_test.py	0	non-stream text response returns a single chatresponse.	STRING
HIGH	tests/model_dashscope_test.py	0	non-stream text response returns a single chatresponse.	STRING
HIGH	tests/model_deepseek_test.py	0	non-stream text response returns a single chatresponse.	STRING
HIGH	tests/model_openai_response_test.py	0	non-stream text response returns a single chatresponse.	STRING
HIGH	tests/model_moonshot_test.py	0	non-stream text response returns a single chatresponse.	STRING
HIGH	tests/model_openai_chat_test.py	0	non-stream text response returns a single chatresponse.	STRING
HIGH	tests/model_xai_test.py	0	non-stream text response returns a single chatresponse.	STRING
HIGH	tests/formatter_openai_chat_test.py	0	set up shared message fixtures and expected ground-truth dicts.	STRING
HIGH	tests/formatter_anthropic_test.py	0	set up shared message fixtures and expected ground-truth dicts.	STRING
HIGH	tests/formatter_gemini_test.py	0	set up shared message fixtures and expected ground-truth dicts.	STRING
HIGH	tests/formatter_dashscope_test.py	0	set up shared message fixtures and expected ground-truth dicts.	STRING
HIGH	tests/formatter_moonshot_test.py	0	set up shared message fixtures and expected ground-truth dicts.	STRING
HIGH	tests/formatter_openai_response_test.py	0	set up shared message fixtures and expected ground-truth dicts.	STRING
HIGH	tests/formatter_openai_chat_test.py	0	chat formatter produces exact output for various subsets.	STRING
HIGH	tests/formatter_ollama_test.py	0	chat formatter produces exact output for various subsets.	STRING
HIGH	tests/formatter_deepseek_test.py	0	chat formatter produces exact output for various subsets.	STRING
HIGH	tests/formatter_anthropic_test.py	0	chat formatter produces exact output for various subsets.	STRING
HIGH	tests/formatter_gemini_test.py	0	chat formatter produces exact output for various subsets.	STRING
HIGH	tests/formatter_dashscope_test.py	0	chat formatter produces exact output for various subsets.	STRING
HIGH	tests/formatter_moonshot_test.py	0	chat formatter produces exact output for various subsets.	STRING
HIGH	tests/formatter_openai_response_test.py	0	chat formatter produces exact output for various subsets.	STRING
HIGH	tests/formatter_openai_chat_test.py	0	multiagent formatter produces exact output for various subsets.	STRING
HIGH	tests/formatter_ollama_test.py	0	multiagent formatter produces exact output for various subsets.	STRING
HIGH	tests/formatter_deepseek_test.py	0	multiagent formatter produces exact output for various subsets.	STRING
HIGH	tests/formatter_anthropic_test.py	0	multiagent formatter produces exact output for various subsets.	STRING
HIGH	tests/formatter_gemini_test.py	0	multiagent formatter produces exact output for various subsets.	STRING
HIGH	tests/formatter_dashscope_test.py	0	multiagent formatter produces exact output for various subsets.	STRING
HIGH	tests/formatter_moonshot_test.py	0	multiagent formatter produces exact output for various subsets.	STRING
HIGH	tests/formatter_openai_response_test.py	0	multiagent formatter produces exact output for various subsets.	STRING
HIGH	tests/formatter_openai_chat_test.py	0	complex multi-step sequence with interleaved thinking, text, tool calls, and tool results.	STRING
HIGH	tests/formatter_ollama_test.py	0	complex multi-step sequence with interleaved thinking, text, tool calls, and tool results.	STRING
HIGH	tests/formatter_xai_test.py	0	complex multi-step sequence with interleaved thinking, text, tool calls, and tool results.	STRING
HIGH	tests/formatter_deepseek_test.py	0	complex multi-step sequence with interleaved thinking, text, tool calls, and tool results.	STRING
HIGH	tests/formatter_anthropic_test.py	0	complex multi-step sequence with interleaved thinking, text, tool calls, and tool results.	STRING
HIGH	tests/formatter_gemini_test.py	0	complex multi-step sequence with interleaved thinking, text, tool calls, and tool results.	STRING
HIGH	tests/formatter_moonshot_test.py	0	complex multi-step sequence with interleaved thinking, text, tool calls, and tool results.	STRING
HIGH	tests/formatter_openai_response_test.py	0	complex multi-step sequence with interleaved thinking, text, tool calls, and tool results.	STRING
HIGH	tests/formatter_openai_chat_test.py	0	hintblock flushes preceding content and becomes a user message.	STRING
HIGH	tests/formatter_ollama_test.py	0	hintblock flushes preceding content and becomes a user message.	STRING
HIGH	tests/formatter_xai_test.py	0	hintblock flushes preceding content and becomes a user message.	STRING
HIGH	tests/formatter_deepseek_test.py	0	hintblock flushes preceding content and becomes a user message.	STRING
HIGH	tests/formatter_anthropic_test.py	0	hintblock flushes preceding content and becomes a user message.	STRING
HIGH	tests/formatter_gemini_test.py	0	hintblock flushes preceding content and becomes a user message.	STRING
HIGH	tests/formatter_dashscope_test.py	0	hintblock flushes preceding content and becomes a user message.	STRING
HIGH	tests/formatter_moonshot_test.py	0	hintblock flushes preceding content and becomes a user message.	STRING
HIGH	tests/formatter_openai_response_test.py	0	hintblock flushes preceding content and becomes a user message.	STRING
HIGH	tests/formatter_openai_chat_test.py	0	multimodal hintblock becomes a single user message with text + image.	STRING
HIGH	tests/formatter_anthropic_test.py	0	multimodal hintblock becomes a single user message with text + image.	STRING
HIGH	tests/formatter_gemini_test.py	0	multimodal hintblock becomes a single user message with text + image.	STRING
HIGH	tests/formatter_dashscope_test.py	0	multimodal hintblock becomes a single user message with text + image.	STRING
HIGH	tests/formatter_moonshot_test.py	0	multimodal hintblock becomes a single user message with text + image.	STRING
HIGH	tests/formatter_openai_response_test.py	0	multimodal hintblock becomes a single user message with text + image.	STRING
HIGH	tests/backend_opensandbox_test.py	0	a program's stdout/exit code are captured into ``execresult``.	STRING
HIGH	tests/backend_e2b_test.py	0	a program's stdout/exit code are captured into ``execresult``.	STRING
HIGH	tests/backend_daytona_test.py	0	a program's stdout/exit code are captured into ``execresult``.	STRING
241 more matches not shown…

Unused Imports805 hits · 740 pts

Severity	File	Line	Context
LOW	tests/tool_lazy_annotations_test.py	9	CODE
LOW	tests/rag_vdb_elasticsearch_test.py	4	CODE
LOW	tests/workspace_bubblewrap_test.py	5	CODE
LOW	tests/tts_gemini_test.py	79	CODE
LOW	tests/service_workspace_files_test.py	9	CODE
LOW	tests/rag_vdb_mongodb_test.py	4	CODE
LOW	src/agentscope/__init__.py	5	CODE
LOW	src/agentscope/__init__.py	5	CODE
LOW	src/agentscope/__init__.py	9	CODE
LOW	src/agentscope/__init__.py	9	CODE
LOW	src/agentscope/__init__.py	10	CODE
LOW	src/agentscope/middleware/_base.py	8	CODE
LOW	src/agentscope/middleware/_base.py	9	CODE
LOW	src/agentscope/middleware/_base.py	10	CODE
LOW	src/agentscope/middleware/_tts_middleware.py	18	CODE
LOW	src/agentscope/middleware/__init__.py	4	CODE
LOW	src/agentscope/middleware/__init__.py	5	CODE
LOW	src/agentscope/middleware/__init__.py	6	CODE
LOW	src/agentscope/middleware/__init__.py	7	CODE
LOW	src/agentscope/middleware/__init__.py	7	CODE
LOW	src/agentscope/middleware/__init__.py	7	CODE
LOW	src/agentscope/middleware/__init__.py	12	CODE
LOW	src/agentscope/middleware/__init__.py	13	CODE
LOW	src/agentscope/middleware/_rag.py	61	CODE
LOW	src/agentscope/middleware/_rag.py	62	CODE
LOW	src/agentscope/middleware/_rag.py	62	CODE
LOW	src/agentscope/middleware/_budget.py	11	CODE
LOW	src/agentscope/middleware/_longterm_memory/__init__.py	4	CODE
LOW	src/agentscope/middleware/_longterm_memory/__init__.py	5	CODE
LOW	src/agentscope/middleware/_longterm_memory/__init__.py	6	CODE
LOW	…iddleware/_longterm_memory/_agentic_memory/__init__.py	4	CODE
LOW	…leware/_longterm_memory/_agentic_memory/_middleware.py	8	CODE
LOW	…leware/_longterm_memory/_agentic_memory/_middleware.py	25	CODE
LOW	…ddleware/_longterm_memory/_mem0/_agentscope_adapter.py	32	CODE
LOW	…ddleware/_longterm_memory/_mem0/_agentscope_adapter.py	55	CODE
LOW	…agentscope/middleware/_longterm_memory/_mem0/_tools.py	19	CODE
LOW	…agentscope/middleware/_longterm_memory/_mem0/_tools.py	29	CODE
LOW	…entscope/middleware/_longterm_memory/_mem0/__init__.py	4	CODE
LOW	…scope/middleware/_longterm_memory/_mem0/_middleware.py	13	CODE
LOW	…scope/middleware/_longterm_memory/_mem0/_middleware.py	40	CODE
LOW	…scope/middleware/_longterm_memory/_mem0/_middleware.py	41	CODE
LOW	…scope/middleware/_longterm_memory/_mem0/_middleware.py	42	CODE
LOW	…scope/middleware/_longterm_memory/_mem0/_middleware.py	43	CODE
LOW	…agentscope/middleware/_longterm_memory/_mem0/_utils.py	8	CODE
LOW	…agentscope/middleware/_longterm_memory/_reme/_tools.py	16	CODE
LOW	…agentscope/middleware/_longterm_memory/_reme/_tools.py	25	CODE
LOW	…entscope/middleware/_longterm_memory/_reme/__init__.py	12	CODE
LOW	…scope/middleware/_longterm_memory/_reme/_middleware.py	33	CODE
LOW	…scope/middleware/_longterm_memory/_reme/_middleware.py	56	CODE
LOW	…scope/middleware/_longterm_memory/_reme/_middleware.py	57	CODE
LOW	…gentscope/middleware/_longterm_memory/_reme/_config.py	15	CODE
LOW	…agentscope/middleware/_longterm_memory/_reme/_utils.py	8	CODE
LOW	src/agentscope/middleware/_tracing/_extractor.py	15	CODE
LOW	src/agentscope/middleware/_tracing/_extractor.py	22	CODE
LOW	src/agentscope/middleware/_tracing/_extractor.py	23	CODE
LOW	src/agentscope/middleware/_tracing/_extractor.py	23	CODE
LOW	src/agentscope/middleware/_tracing/__init__.py	4	CODE
LOW	src/agentscope/middleware/_tracing/_trace.py	47	CODE
LOW	src/agentscope/middleware/_tracing/_trace.py	48	CODE
LOW	src/agentscope/middleware/_tracing/_trace.py	49	CODE
745 more matches not shown…

Cross-Language Confusion85 hits · 536 pts

Severity	File	Line	Snippet	Context
HIGH⚡	tests/builtin_bash_test.py	584	"ls && rm -rf /",	CODE
HIGH⚡	tests/builtin_bash_test.py	585	"cd /tmp && rm -rf /usr",	CODE
HIGH	tests/builtin_bash_test.py	245	cmd = "(cd /tmp && ls)"	CODE
HIGH⚡	tests/permission_engine_test.py	564	{"command": "ls -la && rm ~/.bashrc"},	CODE
HIGH⚡	tests/permission_engine_test.py	576	{"command": "ls -la && cat file.txt"},	CODE
HIGH⚡	tests/permission_engine_test.py	587	{"command": "ls -la && git commit -m 'test'"},	CODE
HIGH	tests/mcp_streamable_http_client_test.py	144	"meta": null,	STRING
HIGH	tests/model_gemini_test.py	749	"""additionalProperties removed; anyOf[X, null] inlined to X."""	STRING
HIGH⚡	tests/workspace_local_test.py	1298	'"finished_at":null},'	CODE
HIGH⚡	tests/workspace_local_test.py	1301	'"created_at":"2026-01-01T00:00:00","finished_at":null}'	CODE
HIGH⚡	tests/workspace_local_test.py	1304	'"usage":null,'	CODE
HIGH⚡	tests/workspace_local_test.py	1306	'"finished_reason":null,"structured_output":null,'	CODE
HIGH⚡	tests/workspace_local_test.py	1307	'"error":null}'	CODE
HIGH⚡	tests/workspace_local_test.py	1358	'"usage":null,'	CODE
HIGH⚡	tests/workspace_local_test.py	1359	'"finished_at":null,'	CODE
HIGH⚡	tests/workspace_local_test.py	1360	'"finished_reason":null,"structured_output":null,'	CODE
HIGH⚡	tests/workspace_local_test.py	1361	'"error":null}'	CODE
HIGH⚡	tests/workspace_local_test.py	1367	'"created_at":"2026-01-02T00:00:00","finished_at":null}'	CODE
HIGH⚡	tests/workspace_local_test.py	1370	'"usage":null,'	CODE
HIGH⚡	tests/workspace_local_test.py	1372	'"finished_reason":null,"structured_output":null,'	CODE
HIGH⚡	tests/workspace_local_test.py	1373	'"error":null}'	CODE
HIGH	tests/backend_local_test.py	389	["/bin/sh", "-c", "true && echo chained"],	CODE
HIGH⚡	tests/tts_dashscope_test.py	151	resp = await model.push("ignored")	CODE
HIGH⚡	tests/tts_dashscope_test.py	566	await model.push("Hello")	CODE
HIGH⚡	tests/tts_dashscope_test.py	567	await model.push(" world")	CODE
HIGH⚡	tests/tts_dashscope_test.py	593	res = await model.push("Hello")	CODE
HIGH⚡	tests/tts_dashscope_test.py	603	await model.push("Hi")	CODE
HIGH⚡	tests/tts_dashscope_test.py	604	await model.push(" there")	CODE
HIGH⚡	tests/tts_dashscope_test.py	608	await model.push(" friend!")	CODE
HIGH⚡	tests/tts_dashscope_test.py	618	await model.push("Hello")	CODE
HIGH⚡	tests/tts_dashscope_test.py	621	await model.push(" world")	CODE
HIGH⚡	tests/tts_dashscope_test.py	632	await model.push("Hello")	CODE
HIGH⚡	tests/tts_dashscope_test.py	633	await model.push(" world")	CODE
HIGH⚡	tests/tts_dashscope_test.py	677	await model.push("Hello")	CODE
HIGH⚡	tests/tts_dashscope_test.py	708	await model.push("Hi")	CODE
HIGH⚡	tests/tts_dashscope_test.py	709	await model.push(" there")	CODE
HIGH⚡	tests/tts_dashscope_test.py	975	await model.push("Hello")	CODE
HIGH⚡	tests/tts_dashscope_test.py	976	await model.push(" world")	CODE
HIGH⚡	tests/tts_dashscope_test.py	1001	res = await model.push("Hello")	CODE
HIGH⚡	tests/tts_dashscope_test.py	1014	await model.push("Hi")	CODE
HIGH⚡	tests/tts_dashscope_test.py	1015	await model.push(" there")	CODE
HIGH⚡	tests/tts_dashscope_test.py	1019	await model.push(" friend!")	CODE
HIGH⚡	tests/tts_dashscope_test.py	1032	await model.push("Hello")	CODE
HIGH⚡	tests/tts_dashscope_test.py	1037	await model.push(" world")	CODE
HIGH⚡	tests/tts_dashscope_test.py	1053	await model.push("Hello")	CODE
HIGH⚡	tests/tts_dashscope_test.py	1054	await model.push(" world")	CODE
HIGH⚡	tests/tts_dashscope_test.py	1066	res = await model.push("Hello")	CODE
HIGH⚡	tests/tts_dashscope_test.py	1111	await model.push("Hello")	CODE
HIGH⚡	tests/tts_dashscope_test.py	1168	await model.push("Hi")	CODE
HIGH⚡	tests/tts_dashscope_test.py	1169	await model.push(" there")	CODE
HIGH	tests/tts_dashscope_test.py	659	await model.push("Hello")	CODE
HIGH	tests/tts_dashscope_test.py	1092	await model.push("Hello")	CODE
HIGH⚡	tests/backend_applecontainer_test.py	95	["sh", "-c", "echo hello && echo world"],	CODE
HIGH⚡	tests/backend_applecontainer_test.py	98	self.assertEqual(argv[-3:], ["sh", "-c", "echo hello && echo world"])	CODE
HIGH⚡	tests/permission_bash_parser_test.py	86	"npm install && npm run build && npm test",	CODE
HIGH⚡	tests/permission_bash_parser_test.py	100	("npm run build \|\| echo failed", ["npm run"]),	CODE
HIGH⚡	tests/permission_bash_parser_test.py	101	("git commit \|\| git status", ["git commit", "git status"]),	CODE
HIGH⚡	tests/permission_bash_parser_test.py	323	"ls -la && cat file.txt",	CODE
HIGH⚡	tests/permission_bash_parser_test.py	324	"git status && git log",	CODE
HIGH⚡	tests/permission_bash_parser_test.py	325	"pwd && ls",	CODE
25 more matches not shown…

Docstring Block Structure91 hits · 455 pts

Severity	File	Line	Snippet	Context
HIGH	src/agentscope/_utils/_mixin.py	11	Get a dictionary item through attribute-style access. Args: key (`str`): The reques	STRING
HIGH	src/agentscope/app/deps.py	38	Return the caller's user ID from the ``X-User-ID`` request header. Args: x_user_id (`str`): Value of the ``	STRING
HIGH	src/agentscope/app/deps.py	231	Return the application-wide knowledge base service. Args: request (`Request`): The incoming Fas	STRING
HIGH	src/agentscope/app/deps.py	262	Return the application-wide knowledge base manager. Args: request (`Request`): The incoming Fas	STRING
HIGH	src/agentscope/app/deps.py	290	Return the application-wide blob store. Args: request (`Request`): The incoming FastAPI request	STRING
HIGH	src/agentscope/app/deps.py	321	Return the parser registry configured on the app. Args: request (`Request`): The incoming FastA	STRING
HIGH	src/agentscope/app/deps.py	352	Return the chunker classes configured on the app. Args: request (`Request`): The incoming FastA	STRING
HIGH	src/agentscope/app/_app.py	50	Key the hubs by id, rejecting duplicates. Args: hubs (`list \| None`): The hubs passed to :func:	STRING
HIGH	src/agentscope/app/middleware/_protocol/_base.py	201	Deserialize event dictionary to AgentEvent object. Args: event_dict: Dictionary containing event da	STRING
HIGH	src/agentscope/app/_router/_channel.py	87	Load a channel and assert the caller owns it. Args: channel_id (`str`): The channel to load. user_i	STRING
HIGH	src/agentscope/app/_router/_chat.py	61	Trigger a chat run for the specified session. Events produced during the run are published to the message bus and	STRING
HIGH	src/agentscope/app/_router/_session.py	196	Return all sessions for an agent as enriched :class:`SessionView` entries. Each entry bundles what the chat UI	STRING
HIGH	src/agentscope/app/_router/_session.py	295	Create (or resume) a session for a given agent and workspace. At most one session exists per ``(user_id, agent_id,	STRING
HIGH	src/agentscope/app/_router/_session.py	416	Request interruption of an in-progress reply for a session. Thin HTTP wrapper around :meth:`ChatService.interrupt`;	STRING
HIGH	src/agentscope/app/_router/_session.py	459	Update the configuration of an existing session. Rejected while a chat run holds the session: the agent snapshots	STRING
HIGH	src/agentscope/app/_router/_session.py	651	Return the unified :class:`SessionStatus` for a session. Ownership validation, cluster-liveness probing, and parked	STRING
HIGH	src/agentscope/app/_router/_credential.py	120	Replace the payload of an existing credential. Args: credential_id (`str`): The credential to update.	STRING
HIGH	src/agentscope/app/_router/_hub.py	40	Return the hub under ``hub_id`` or raise 404. Args: hubs (`dict[str, HubT]`): The registered hu	STRING
HIGH	src/agentscope/app/_router/_agent.py	176	Create and persist a new agent configuration. Args: body (`CreateAgentRequest`): Agent configur	STRING
HIGH	src/agentscope/app/_router/_agent.py	228	Partially update an existing agent configuration. Only the fields present in the request body are updated; all othe	STRING
HIGH	src/agentscope/app/_router/_schedule.py	74	Create a new schedule and register it with the scheduler. The referenced agent may be either the viewer's own or on	STRING
HIGH	src/agentscope/app/_router/_schedule.py	143	Partially update a schedule. Fields omitted from the request body keep their current values. Changing ``cron_ex	STRING
HIGH	src/agentscope/app/_router/_schedule.py	231	Return all sessions triggered by a given schedule. Args: schedule_id (`str`): ID of the schedule. u	STRING
HIGH	src/agentscope/app/_service/_download_token.py	62	Return the user a token was granted to, for this path. The path is not read out of the token but re-derived from th	STRING
HIGH	src/agentscope/app/_service/_knowledge_base.py	128	Delegate creation to the manager, mapping policy errors. Args: user_id (`str`): The	STRING
HIGH	src/agentscope/app/_service/_knowledge_base.py	370	Persist an uploaded document and enqueue it for indexing. Streams ``stream`` into the blob store (so the bytes	STRING
HIGH	src/agentscope/app/_service/_knowledge_base.py	459	List documents of a knowledge base, filtered and paginated. Service-mode source of truth: reads from storage, N	STRING
HIGH	src/agentscope/app/_service/_knowledge_base.py	530	Batch-fetch documents for status polling. The endpoint backing this method accepts a comma-separated list	STRING
HIGH	src/agentscope/app/_service/_knowledge_base.py	577	Fetch one document record, or 404. Args: user_id (`str`): The viewer user id — owne	STRING
HIGH	src/agentscope/app/_service/_knowledge_base.py	621	List one page of a document's chunks in ``chunk_index`` order. ``page`` / ``page_size`` translate to the dense-	STRING
HIGH	src/agentscope/app/_service/_knowledge_base.py	682	Open the original uploaded file of a document for streaming. The bytes come straight from the blob store — the	STRING
HIGH	src/agentscope/app/_service/_knowledge_base.py	814	Search a knowledge base by text query. Args: user_id (`str`): The viewer user id —	STRING
HIGH	src/agentscope/app/_service/_embedding.py	29	Construct an embedding model from an already-resolved credential. This is the record-in variant used by owner-inter	STRING
HIGH	src/agentscope/app/_service/_embedding.py	100	Resolve a credential through :class:`ResourceAccessService` and build the corresponding embedding model. Args:	STRING
HIGH	src/agentscope/app/_service/_workspace.py	200	Return the workspace backing a session. Args: user_id (`str`): The authenticated user ID.	STRING
HIGH	src/agentscope/app/_service/_workspace.py	226	Report where a session sits and the git state of that place. Args: user_id (`str`): The authenticat	STRING
HIGH	src/agentscope/app/_service/_workspace.py	261	Load a session and open the workspace it is bound to. Args: user_id (`str`): The authenticated user	STRING
HIGH	src/agentscope/app/_service/_workspace.py	325	Return the user a token was granted to, for this path. The path is not read out of the token but re-derived fro	STRING
HIGH	src/agentscope/app/_service/_workspace.py	352	Check a manifest and return the skill's root directory name. Args: manifest (`UploadManifest`): The	STRING
HIGH	src/agentscope/app/_service/_workspace.py	448	Emit a tar of the uploaded files, chunk by chunk. Args: manifest (`UploadManifest`): The validated	STRING
HIGH	src/agentscope/app/_service/_mcp_render.py	108	Turn a card plus the user's answers into a connectable client. Args: card (`MCPCard`): The hub	STRING
HIGH	src/agentscope/app/_service/_model.py	15	Build a chat model instance from a stored credential and config. Credentials are resolved through :class:`ResourceA	STRING
HIGH	src/agentscope/app/_manager/_chat_run_registry.py	43	Create and register an asyncio task that runs ``coro``. The task auto-removes from the registry when it finishe	STRING
HIGH	src/agentscope/app/rag/__init__.py	51	Lazy-load attributes that would cause an import cycle. ``run_worker`` is lazy-imported because :mod:`.index_worker`	STRING
HIGH	src/agentscope/app/rag/index_worker/__main__.py	54	Import ``module:attribute`` and return the attribute. Args: dotted (`str`): A ``module:attribut	STRING
HIGH	src/agentscope/app/rag/knowledge_base_manager/_base.py	133	Create a new knowledge base for the given user. Implementations must: 1. validate ``embedding_model_co	STRING
HIGH	src/agentscope/app/rag/knowledge_base_manager/_base.py	284	Resolve a runtime :class:`KnowledgeBase` handle for one KB. Implementations are responsible for: - loo	STRING
HIGH	…e/app/rag/knowledge_base_manager/_collection_per_kb.py	155	Resolve a :class:`KnowledgeBase` runtime for one knowledge base. Looks the record up in storage (raising	STRING
HIGH	src/agentscope/app/storage/_base.py	117	Create or update an installed-MCP record. The record's ``client.name`` is unique per user — the workspace	STRING
HIGH	src/agentscope/app/storage/_base.py	209	Create or update an installed-skill record. The record's ``name`` is unique per user, for the same reason	STRING
HIGH	src/agentscope/app/storage/_redis_storage.py	429	Create or update an installed-MCP record for the given user. Keeps the name index in step with the write: the n	STRING
HIGH	src/agentscope/app/storage/_redis_storage.py	568	Create or update an installed-skill record for the user. Mirrors :meth:`upsert_mcp` — see it for the name-index	STRING
HIGH	src/agentscope/app/storage/_sql/_storage.py	270	Build a dialect-native atomic upsert statement. A single ``INSERT ... ON CONFLICT DO UPDATE`` (Postgres /	STRING
HIGH	src/agentscope/app/storage/_sql/_storage.py	1340	Persist a channel record and its bot-uniqueness column. Args: record (`ChannelRecord`):	STRING
HIGH	src/agentscope/app/_tool/_team_tool_base.py	111	Return the team this session leads. Args: leader_only (`str`): What only the le	STRING
HIGH	src/agentscope/app/hub/_skill/_base.py	75	Fetch a single card by its hub-local id, with ``SKILL.md``. Args: user_id (`str`):	STRING
HIGH	src/agentscope/app/hub/_skill/_base.py	99	Open the skill archive for streaming. Returns rather than yields so the format is known before the firs	STRING
HIGH	src/agentscope/app/hub/_skill/_claw_hub.py	226	Send a request to the ClawHub API with rate-limit handling. Args: method (`str`): T	STRING
HIGH	src/agentscope/app/hub/_skill/_claw_hub.py	285	Open a skill archive via ``GET /api/v1/download``. The response headers are awaited here — so a missing skill o	STRING
HIGH	src/agentscope/app/hub/_skill/_claw_hub.py	548	Browse or search the ClawHub registry in one request. With ``q`` the search endpoint is used, which ranks by re	STRING
31 more matches not shown…

Excessive Try-Catch Wrapping243 hits · 248 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_e2e_api.py	51	except Exception:	CODE
LOW	tests/test_e2e_api.py	90	except Exception:	CODE
LOW	tests/_daytona_live_utils.py	46	except Exception:	CODE
LOW	scripts/model_examples/run_tests.py	87	except Exception:	CODE
LOW	src/agentscope/_utils/_common.py	135	except Exception:	CODE
LOW	src/agentscope/_utils/_common.py	243	except Exception as e:	CODE
LOW	src/agentscope/middleware/_rag.py	280	except Exception as e: # pylint: disable=broad-except	CODE
LOW	src/agentscope/middleware/_rag.py	730	except Exception: # pylint: disable=broad-except	CODE
LOW⚡	…leware/_longterm_memory/_agentic_memory/_middleware.py	774	except Exception:	CODE
LOW	…leware/_longterm_memory/_agentic_memory/_middleware.py	908	except Exception:	CODE
LOW	…leware/_longterm_memory/_agentic_memory/_middleware.py	949	except Exception:	CODE
LOW	…agentscope/middleware/_longterm_memory/_mem0/_tools.py	135	except Exception as e: # noqa: BLE001	CODE
LOW	…agentscope/middleware/_longterm_memory/_mem0/_tools.py	230	except Exception as e: # noqa: BLE001	CODE
MEDIUM	…scope/middleware/_longterm_memory/_mem0/_middleware.py	715	def _bg() -> None:	CODE
LOW	…scope/middleware/_longterm_memory/_mem0/_middleware.py	343	except Exception as e: # noqa: BLE001	CODE
LOW	…scope/middleware/_longterm_memory/_mem0/_middleware.py	707	except Exception as e: # noqa: BLE001	CODE
LOW	…scope/middleware/_longterm_memory/_mem0/_middleware.py	734	except Exception as e: # noqa: BLE001	CODE
LOW	…agentscope/middleware/_longterm_memory/_reme/_tools.py	146	except Exception as e: # noqa: BLE001	CODE
LOW⚡	…scope/middleware/_longterm_memory/_reme/_middleware.py	518	except Exception as e: # noqa: BLE001	CODE
LOW	src/agentscope/middleware/_tracing/_extractor.py	164	except Exception:	CODE
LOW	src/agentscope/middleware/_tracing/_extractor.py	307	except Exception:	CODE
LOW	src/agentscope/middleware/_tracing/_extractor.py	431	except Exception:	CODE
LOW	src/agentscope/middleware/_tracing/_extractor.py	452	except Exception:	CODE
LOW	src/agentscope/app/message_bus/_redis_message_bus.py	645	except Exception: # pylint: disable=broad-except	CODE
LOW	…c/agentscope/app/middleware/_team_member_middleware.py	91	except Exception: # pylint: disable=broad-except	CODE
LOW⚡	…/agentscope/app/middleware/_tool_offload_middleware.py	174	except Exception as exc: # pylint: disable=broad-except	CODE
LOW	…/agentscope/app/middleware/_tool_offload_middleware.py	257	except Exception: # pylint: disable=broad-except	CODE
LOW	src/agentscope/app/_router/_workspace.py	87	except Exception as e:	CODE
LOW	src/agentscope/app/_router/_workspace.py	187	except Exception as e:	CODE
LOW	src/agentscope/app/_router/_workspace.py	373	except Exception as e: # pylint: disable=broad-except	CODE
LOW	src/agentscope/app/_service/_knowledge_base.py	432	except Exception:	CODE
LOW	src/agentscope/app/_service/_knowledge_base.py	898	except Exception: # noqa: BLE001 — cleanup only	CODE
LOW	src/agentscope/app/_service/_index_sweeper.py	109	except Exception: # noqa: BLE001 — keep the loop alive	CODE
LOW	src/agentscope/app/_service/_index_sweeper.py	143	except Exception: # noqa: BLE001 — keep iterating	CODE
LOW	src/agentscope/app/_service/_channel.py	170	except Exception: # pylint: disable=broad-except	CODE
LOW	src/agentscope/app/_service/_channel.py	224	except Exception: # pylint: disable=broad-except	CODE
LOW	src/agentscope/app/_service/_chat.py	280	except Exception as e:	CODE
LOW	src/agentscope/app/_service/_chat.py	423	except Exception: # pylint: disable=broad-except	CODE
LOW	src/agentscope/app/_service/_chat.py	504	except Exception:	CODE
LOW	src/agentscope/app/_service/_chat.py	868	except Exception: # pylint: disable=broad-except	CODE
LOW	src/agentscope/app/_service/_chat.py	998	except Exception as e: # pylint: disable=broad-except	CODE
LOW	src/agentscope/app/_service/_chat.py	1185	except Exception as e: # pylint: disable=broad-except	CODE
LOW	src/agentscope/app/_service/_chat.py	1344	except Exception as e: # pylint: disable=broad-except	CODE
LOW	src/agentscope/app/_service/_session.py	412	except Exception as e:	CODE
LOW	src/agentscope/app/_service/_session.py	558	except Exception as e:	CODE
LOW	src/agentscope/app/_service/_session.py	722	except Exception as e: # pylint: disable=broad-except	CODE
LOW	src/agentscope/app/_service/_workspace.py	525	except Exception as exc: # pylint: disable=broad-except	CODE
LOW	src/agentscope/app/_service/_workspace.py	552	except Exception as exc: # pylint: disable=broad-except	CODE
LOW	src/agentscope/app/_service/_index_worker.py	310	except Exception as exc: # noqa: BLE001 — terminal error sink	CODE
LOW⚡	src/agentscope/app/_service/_index_worker.py	599	except Exception: # noqa: BLE001 — last-resort log	CODE
LOW	src/agentscope/app/_service/_index_task_consumer.py	140	except Exception: # pylint: disable=broad-except	CODE
LOW	src/agentscope/app/_service/_index_task_consumer.py	158	except Exception: # pylint: disable=broad-except	CODE
LOW	src/agentscope/app/_service/_model.py	67	except Exception: # pylint: disable=broad-except	CODE
LOW	src/agentscope/app/_manager/_cancel_dispatcher.py	131	except Exception:	CODE
LOW⚡	src/agentscope/app/_manager/_cancel_dispatcher.py	191	except Exception: # pylint: disable=broad-except	CODE
LOW	src/agentscope/app/_manager/_cancel_dispatcher.py	220	except Exception: # pylint: disable=broad-except	CODE
LOW⚡	src/agentscope/app/_manager/_background_task_manager.py	349	except Exception as e: # pylint: disable=broad-except	CODE
LOW	src/agentscope/app/_manager/_wakeup_dispatcher.py	173	except Exception: # pylint: disable=broad-except	CODE
LOW	src/agentscope/app/_manager/_wakeup_dispatcher.py	186	except Exception: # pylint: disable=broad-except	CODE
LOW	src/agentscope/app/_manager/_wakeup_dispatcher.py	265	except Exception: # pylint: disable=broad-except	CODE
183 more matches not shown…

Deep Nesting146 hits · 134 pts

Severity	File	Line	Context
LOW	tests/workspace_bubblewrap_test.py	606	CODE
LOW	tests/compress_tool_result_test.py	325	CODE
LOW	tests/compress_tool_result_test.py	481	CODE
LOW	tests/compress_tool_result_test.py	340	CODE
LOW	tests/compress_tool_result_test.py	496	CODE
LOW	examples/long_term_memory/agentic_memory/main.py	115	CODE
LOW	examples/long_term_memory/mem0/oss_demo.py	93	CODE
LOW	examples/long_term_memory/reme/reme_demo.py	127	CODE
LOW	scripts/model_examples/run_tests.py	293	CODE
LOW	scripts/model_examples/_utils.py	15	CODE
LOW	src/agentscope/_utils/_common.py	269	CODE
LOW	src/agentscope/_utils/_common.py	313	CODE
LOW	src/agentscope/middleware/_tts_middleware.py	51	CODE
LOW	src/agentscope/middleware/_rag.py	196	CODE
LOW	src/agentscope/middleware/_rag.py	682	CODE
LOW	src/agentscope/middleware/_budget.py	98	CODE
LOW	…leware/_longterm_memory/_agentic_memory/_middleware.py	709	CODE
LOW	…ddleware/_longterm_memory/_mem0/_agentscope_adapter.py	172	CODE
LOW	…ddleware/_longterm_memory/_mem0/_agentscope_adapter.py	191	CODE
LOW	…agentscope/middleware/_longterm_memory/_mem0/_utils.py	55	CODE
LOW	…agentscope/middleware/_longterm_memory/_reme/_utils.py	51	CODE
LOW	src/agentscope/middleware/_tracing/_extractor.py	67	CODE
LOW	src/agentscope/middleware/_tracing/_extractor.py	394	CODE
LOW	src/agentscope/middleware/_tracing/_extractor.py	456	CODE
LOW	src/agentscope/middleware/_tracing/_extractor.py	545	CODE
LOW	src/agentscope/middleware/_tracing/_converter.py	63	CODE
LOW	src/agentscope/middleware/_tracing/_trace.py	137	CODE
LOW	src/agentscope/middleware/_tracing/_utils.py	15	CODE
LOW	src/agentscope/pipeline/_goal_pipeline.py	93	CODE
LOW	src/agentscope/app/_router/_session.py	764	CODE
LOW	src/agentscope/app/_router/_session.py	807	CODE
LOW	src/agentscope/app/_service/_chat.py	634	CODE
LOW	src/agentscope/app/_service/_session.py	477	CODE
LOW	src/agentscope/app/_service/_workspace.py	567	CODE
LOW	src/agentscope/app/channel/_base.py	334	CODE
LOW	src/agentscope/app/channel/_stream.py	71	CODE
LOW	src/agentscope/app/channel/_dingtalk/_channel.py	198	CODE
LOW	src/agentscope/app/channel/_dingtalk/_channel.py	291	CODE
LOW	src/agentscope/app/channel/_discord/_channel.py	159	CODE
LOW	src/agentscope/app/channel/_discord/_channel.py	306	CODE
LOW	src/agentscope/app/channel/_feishu/_channel.py	181	CODE
LOW	src/agentscope/app/channel/_feishu/_channel.py	376	CODE
LOW	src/agentscope/app/channel/_feishu/_channel.py	555	CODE
LOW	src/agentscope/app/channel/_feishu/_channel.py	652	CODE
LOW	src/agentscope/app/hub/_skill/_claw_hub.py	277	CODE
LOW	src/agentscope/skill/_local_loader.py	100	CODE
LOW	src/agentscope/workspace/_base.py	1004	CODE
LOW	src/agentscope/workspace/_base.py	1060	CODE
LOW	src/agentscope/workspace/_gateway_client.py	583	CODE
LOW	src/agentscope/workspace/_daytona/_daytona_workspace.py	357	CODE
LOW	…workspace/_applecontainer/_applecontainer_workspace.py	303	CODE
LOW	src/agentscope/workspace/_k8s/_k8s_workspace.py	502	CODE
LOW	src/agentscope/workspace/_k8s/_k8s_backend.py	80	CODE
LOW	src/agentscope/workspace/_k8s/_k8s_backend.py	205	CODE
LOW	src/agentscope/workspace/_k8s/_k8s_backend.py	324	CODE
LOW	src/agentscope/workspace/_k8s/_k8s_backend.py	121	CODE
LOW	…/agentscope/workspace/_mcp_gateway/_mcp_gateway_app.py	190	CODE
LOW	…gentscope/workspace/_bubblewrap/_bubblewrap_backend.py	199	CODE
LOW	src/agentscope/workspace/_docker/_docker_backend.py	136	CODE
LOW	src/agentscope/workspace/_docker/_docker_workspace.py	202	CODE
86 more matches not shown…

Self-Referential Comments38 hits · 117 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/skill_loader_test.py	19	# Create a temporary directory for testing	COMMENT
MEDIUM	tests/skill_loader_test.py	80	# Create a directory without SKILL.md	COMMENT
MEDIUM	tests/rag_vdb_milvus_lite_test.py	79	# Creating an existing collection is a no-op	COMMENT
MEDIUM	tests/builtin_grep_test.py	22	# Create a temporary directory with test files	COMMENT
MEDIUM⚡	tests/builtin_file_cache_test.py	143	# Create a file	COMMENT
MEDIUM⚡	tests/builtin_file_cache_test.py	186	# Create a file	COMMENT
MEDIUM⚡	tests/builtin_file_cache_test.py	306	# Create a file	COMMENT
MEDIUM	tests/builtin_file_cache_test.py	21	# Create a temporary directory	COMMENT
MEDIUM	tests/builtin_file_cache_test.py	34	# Create a file	COMMENT
MEDIUM	tests/builtin_file_cache_test.py	52	# Create a file	COMMENT
MEDIUM	tests/builtin_file_cache_test.py	88	# Create a file	COMMENT
MEDIUM	tests/builtin_file_cache_test.py	116	# Create a file	COMMENT
MEDIUM	tests/builtin_file_cache_test.py	285	# Create a file	COMMENT
MEDIUM	tests/rag_vdb_qdrant_test.py	90	# Creating an existing collection is a no-op	COMMENT
MEDIUM	tests/builtin_edit_test.py	21	# Create a temporary file for testing	COMMENT
MEDIUM	tests/task_tool_test.py	312	# Create a task	COMMENT
MEDIUM	tests/task_tool_test.py	388	# Create a task	COMMENT
MEDIUM	tests/task_tool_test.py	443	# Create a task	COMMENT
MEDIUM	tests/task_tool_test.py	498	# Create a task	COMMENT
MEDIUM	tests/task_tool_test.py	627	# Create a task	COMMENT
MEDIUM	tests/task_tool_test.py	682	# Create a task with initial metadata	COMMENT
MEDIUM⚡	tests/workspace_local_test.py	851	# Create a valid skill	COMMENT
MEDIUM⚡	tests/workspace_local_test.py	857	# Create an invalid skill without SKILL.md	COMMENT
MEDIUM	tests/workspace_local_test.py	276	# Create a test image data (1x1 red pixel PNG)	COMMENT
MEDIUM	tests/workspace_local_test.py	807	# Create a test skill	COMMENT
MEDIUM	tests/workspace_local_test.py	870	# Create an invalid skill with malformed frontmatter	COMMENT
MEDIUM	tests/toolkit_skill_test.py	49	# Create a minimal SKILL.md so LocalSkillLoader can load it	COMMENT
MEDIUM	tests/builtin_read_test.py	26	# Create a temporary file for testing	COMMENT
MEDIUM	tests/rag_vdb_mongodb_test.py	364	# Creating an existing collection is a no-op	COMMENT
MEDIUM	tests/builtin_glob_test.py	22	# Create a temporary directory with test files	COMMENT
MEDIUM	examples/pipeline/goal/goal_pipeline.py	26	# Create the executor agent	COMMENT
MEDIUM	examples/pipeline/goal/goal_pipeline.py	45	# Create the verifier agent	COMMENT
MEDIUM	src/agentscope/app/middleware/_protocol/_base.py	75	# Create a new StreamingResponse with the converted stream	COMMENT
MEDIUM	src/agentscope/workspace/_docker/_docker_workspace.py	319	# Create the backend now that the container is running. All	COMMENT
MEDIUM	src/agentscope/agent/_agent.py	2051	# Create a queue to collect events from all concurrent workers.	COMMENT
MEDIUM	src/agentscope/state/_state.py	287	# Create a new assistant message with the current reply ID	COMMENT
MEDIUM	src/agentscope/formatter/_formatter_base.py	148	# Create an identifier for such multimodal data for	COMMENT
MEDIUM	src/agentscope/tool/_utils.py	111	# Create a dynamic model with the function signature	COMMENT

Modern Structural Boilerplate96 hits · 96 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_e2e_api.py	57	def _setup_module() -> None:	CODE
LOW	tests/service_team_failure_report_test.py	76	async def update_session_state(self, _: object, *__: object) -> None:	CODE
LOW	tests/service_chat_channel_delivery_test.py	125	async def update_session_state(self, _: object, *__: object) -> None:	CODE
LOW	tests/service_chat_run_context_test.py	65	async def update_session_state(self, _: object, *__: object) -> None:	CODE
LOW	tests/backend_applecontainer_test.py	303	async def _setup_container(cls) -> None:	CODE
LOW	src/agentscope/__init__.py	16	__all__ = [	CODE
LOW	src/agentscope/_utils/_common.py	23	def set_id_factory(factory: Callable[[], str]) -> None:	CODE
LOW	src/agentscope/_utils/_common.py	52	def set_timestamp_factory(factory: Callable[[], str]) -> None:	CODE
LOW	src/agentscope/middleware/__init__.py	15	__all__ = [	CODE
LOW	src/agentscope/middleware/_longterm_memory/__init__.py	8	__all__ = [	CODE
LOW	…iddleware/_longterm_memory/_agentic_memory/__init__.py	6	__all__ = ["AgenticMemoryMiddleware"]	CODE
LOW	…entscope/middleware/_longterm_memory/_mem0/__init__.py	6	__all__ = ["Mem0Middleware"]	CODE
LOW	…entscope/middleware/_longterm_memory/_reme/__init__.py	14	__all__ = [	CODE
LOW	src/agentscope/middleware/_tracing/__init__.py	6	__all__ = [	CODE
LOW⚡	src/agentscope/middleware/_tracing/_trace.py	73	def _set_span_success_status(span: "Span") -> None:	CODE
LOW⚡	src/agentscope/middleware/_tracing/_trace.py	79	def _set_span_error_status(span: "Span", e: BaseException) -> None:	CODE
LOW	src/agentscope/pipeline/__init__.py	7	__all__ = [	CODE
LOW	src/agentscope/credential/__init__.py	16	__all__ = [	CODE
LOW	src/agentscope/types/__init__.py	19	__all__ = [	CODE
LOW	src/agentscope/app/__init__.py	9	__all__ = [	CODE
LOW	src/agentscope/app/message_bus/__init__.py	9	__all__ = [	CODE
LOW	src/agentscope/app/middleware/__init__.py	11	__all__ = [	CODE
LOW	src/agentscope/app/middleware/_protocol/__init__.py	7	__all__ = [	CODE
LOW	src/agentscope/app/_router/__init__.py	19	__all__ = [	CODE
LOW	src/agentscope/app/_router/_schema/__init__.py	91	__all__ = [	CODE
LOW	src/agentscope/app/access/__init__.py	24	__all__ = [	CODE
LOW	src/agentscope/app/_service/__init__.py	27	__all__ = [	CODE
LOW	src/agentscope/app/_service/_projectors/__init__.py	11	__all__ = [	CODE
LOW	src/agentscope/app/_manager/__init__.py	11	__all__ = [	CODE
LOW	src/agentscope/app/_manager/_scheduler/__init__.py	6	__all__ = [	CODE
LOW	…/agentscope/app/_manager/_scheduler/_tools/__init__.py	9	__all__ = [	CODE
LOW	src/agentscope/app/rag/__init__.py	79	__all__ = [	CODE
LOW	…/agentscope/app/rag/knowledge_base_manager/__init__.py	25	__all__ = [	CODE
LOW	src/agentscope/app/rag/blob_store/__init__.py	7	__all__ = [	CODE
LOW	src/agentscope/app/storage/__init__.py	68	__all__ = [	CODE
LOW	src/agentscope/app/storage/_redis_storage.py	191	async def _set_with_ttl(self, key: str, value: str) -> None:	CODE
LOW	src/agentscope/app/storage/_sql/__init__.py	12	__all__ = ["AsyncSQLAlchemyStorage"]	CODE
LOW	src/agentscope/app/storage/_model/__init__.py	38	__all__ = [	CODE
LOW	src/agentscope/app/channel/__init__.py	29	__all__ = [	CODE
LOW	src/agentscope/app/channel/_dingtalk/__init__.py	6	__all__ = ["DingTalkChannel"]	CODE
LOW	src/agentscope/app/channel/_dingtalk/_tools/__init__.py	10	__all__ = [	CODE
LOW	src/agentscope/app/channel/_discord/__init__.py	5	__all__ = ["DiscordChannel"]	CODE
LOW	src/agentscope/app/channel/_feishu/__init__.py	5	__all__ = ["FeishuChannel"]	CODE
LOW	src/agentscope/app/channel/_feishu/_tools/__init__.py	15	__all__ = [	CODE
LOW	src/agentscope/app/workspace_manager/__init__.py	18	__all__ = [	CODE
LOW	src/agentscope/app/_tool/__init__.py	40	__all__ = [	CODE
LOW	src/agentscope/app/hub/__init__.py	21	__all__ = [	CODE
LOW	src/agentscope/app/hub/_skill/__init__.py	8	__all__ = [	CODE
LOW	src/agentscope/app/hub/_mcp/__init__.py	8	__all__ = [	CODE
LOW	src/agentscope/skill/__init__.py	7	__all__ = [	CODE
LOW	src/agentscope/workspace/_base.py	1536	async def _setup_skills(self) -> None:	CODE
LOW	src/agentscope/workspace/__init__.py	17	__all__ = [	CODE
LOW	src/agentscope/workspace/_sandboxed_base.py	435	async def _setup_mcp_gateway(self) -> None:	CODE
LOW	src/agentscope/workspace/_e2b/__init__.py	12	__all__ = ["E2BWorkspace", "E2BBackend"]	CODE
LOW	src/agentscope/workspace/_daytona/__init__.py	12	__all__ = [	CODE
LOW	src/agentscope/workspace/_applecontainer/__init__.py	18	__all__ = ["AppleContainerBackend", "AppleContainerWorkspace"]	CODE
LOW	src/agentscope/workspace/_k8s/__init__.py	12	__all__ = ["K8sWorkspace", "K8sBackend"]	CODE
LOW	src/agentscope/workspace/_bubblewrap/__init__.py	7	__all__ = ["BubblewrapBackend", "BubblewrapWorkspace"]	CODE
LOW	…ntscope/workspace/_bubblewrap/_bubblewrap_workspace.py	339	async def _setup_mcp_gateway(self) -> None:	CODE
LOW	src/agentscope/workspace/_opensandbox/__init__.py	12	__all__ = ["OpenSandboxWorkspace", "OpenSandboxBackend"]	CODE
36 more matches not shown…

Modern AI Meta-Vocabulary27 hits · 87 pts

Severity	File	Line	Snippet	Context
MEDIUM	pyproject.toml	113	# ------------ RAG ------------	COMMENT
MEDIUM	pyproject.toml	188	# RAG parser tests — used to generate PDF fixtures in-memory	COMMENT
MEDIUM	pyproject.toml	214	# The Alembic scaffolding for the SQL storage backend lives in the	COMMENT
MEDIUM⚡	tests/middleware_rag_test.py	439	# embedding model isn't multimodal — the model only saw text.	COMMENT
MEDIUM	docs/changelog.md	89	## RAG	COMMENT
MEDIUM	examples/rag/README.md	1	# RAG Examples	COMMENT
MEDIUM	examples/rag/integrate_with_agent.py	177	# ---- Mode 2: agentic ----	COMMENT
MEDIUM	examples/long_term_memory/mem0/README.md	45	# chat + embedding model. mem0 defaults for everything else.	COMMENT
MEDIUM	scripts/model_examples/README.md	17	├── openai_chat_multiagent.py # OpenAI Chat Completions – multi-agent conversation	CODE
MEDIUM⚡	scripts/model_examples/deepseek_call.py	30	# Example 1: Simple user message (streaming, with chain-of-thought)	COMMENT
MEDIUM⚡	src/agentscope/middleware/_rag.py	303	# Shared helpers — used by both the tool (agentic mode) and the	COMMENT
MEDIUM	src/agentscope/middleware/_rag.py	472	# Agent-driven search (agentic mode, the default)	STRING
MEDIUM⚡	…leware/_longterm_memory/_agentic_memory/_middleware.py	764	# Cap each file to avoid flooding the context window.	COMMENT
MEDIUM⚡	…leware/_longterm_memory/_agentic_memory/_middleware.py	777	# Truncate large files to avoid flooding the context window.	COMMENT
MEDIUM⚡	src/agentscope/app/_service/_chat.py	839	# (own embedding model + vector store), so the middleware can	COMMENT
MEDIUM	…agentscope/model/_dashscope/_models/qwen3.6-flash.yaml	25	# Max chain-of-thought is independent of max_tokens.	COMMENT
MEDIUM	…agentscope/model/_dashscope/_models/qwen3.7-flash.yaml	25	# Max chain-of-thought is independent of max_tokens.	COMMENT
MEDIUM	…agentscope/model/_dashscope/_models/qwen3.5-flash.yaml	25	# Max chain-of-thought is independent of max_tokens.	COMMENT
MEDIUM	…c/agentscope/model/_dashscope/_models/qwen3.8-max.yaml	25	# Max chain-of-thought is 262144 tokens, independent of max_tokens.	COMMENT
MEDIUM	…agentscope/model/_moonshot/_models/kimi-k2.7-code.yaml	15	# which shares the same context window.	COMMENT
MEDIUM	…/model/_moonshot/_models/kimi-k2.7-code-highspeed.yaml	15	# which shares the same context window.	COMMENT
MEDIUM	…ope/model/_xai/_models/grok-4.20-multi-agent-0309.yaml	14	# the context window, matching the ratio of providers that do publish one.	COMMENT
MEDIUM	…e/model/_xai/_models/grok-4.20-0309-non-reasoning.yaml	13	# the context window, matching the ratio of providers that do publish one.	COMMENT
MEDIUM	…scope/model/_xai/_models/grok-4.20-0309-reasoning.yaml	14	# the context window, matching the ratio of providers that do publish one.	COMMENT
MEDIUM	src/agentscope/model/_xai/_models/grok-build-0.1.yaml	14	# the context window, matching the ratio of providers that do publish one.	COMMENT
MEDIUM	src/agentscope/model/_xai/_models/grok-4.3.yaml	16	# the context window, matching the ratio of providers that do publish one.	COMMENT
MEDIUM	src/agentscope/model/_xai/_models/grok-4.5.yaml	16	# the context window, matching the ratio of providers that do publish one.	COMMENT

Verbosity Indicators49 hits · 59 pts

Severity	File	Line	Snippet	Context
LOW	tests/middleware_budget_test.py	382	# Step 1: model produces a tool call that requires confirmation	COMMENT
LOW⚡	tests/service_agent_interrupt_test.py	207	# Step 1: Publish interrupt (simulating API endpoint)	COMMENT
LOW⚡	tests/service_agent_interrupt_test.py	216	# Step 2: Verify agent was interrupted	COMMENT
LOW⚡	tests/service_agent_interrupt_test.py	223	# Step 3: Verify chat-run task is done	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	974	# Step 1: Checking agent input:	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	981	# Step 2: Handling agent event if applicable	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	1015	# Step 3: Enter the reasoning-acting loop until reaching max_iters	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	1255	# Step 1: Analyze the current context	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	1312	# Step 2: Check Time Injection	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	1370	# Step 3: Check Plan Tasks	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	1383	# Step 4: Context Length	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	2284	# Step 1: Check and parse the tool call input:	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	2326	# Step 2: Check permission by toolkit and permission engine	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	2335	# Step 3: Handle the permission and execute the tool call if allowed	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	2428	# Step 4: Delegate raw execution to _acting (middleware hook point)	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	2444	# Step 5: Truncate the tool result if exceed	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	3256	# Step 1: Check executable and awaiting tool calls	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	3299	# Step 2: Check structured output if no blocked tool calls	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	3402	# Step 3: Exit with the final message, or continue reasoning	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	150	# Step 1: Deny rules — highest priority (all modes)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	157	# Step 2: Ask rules → ASK (with suggestions)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	168	# Step 3: Read-only fast path → ALLOW	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	175	# Step 4: Tool's own check_permissions	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	194	# Step 5: Allow rules → ALLOW	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	201	# Step 6: Mode fallback → ASK the user	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	248	# Step 1: Deny rules — highest priority (all modes)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	255	# Step 2: Ask rules → ASK (with suggestions)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	266	# Step 3: Read-only fast path → ALLOW	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	273	# Step 4: Tool's own check_permissions	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	280	# Step 5: Allow rules	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	286	# Step 6: Mode fallback → DENY (invocation is not read-only)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	330	# Step 1: Deny rules — highest priority (all modes)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	337	# Step 2: Ask rules → ASK (with suggestions)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	348	# Step 3: Read-only fast path → ALLOW	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	355	# Step 4: Tool's own check_permissions (working-directory auto-allow	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	375	# Step 5: Allow rules → ALLOW	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	382	# Step 6: Mode fallback → ASK the user	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	439	# Step 1: Deny rules — highest priority (all modes)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	446	# Step 2: Ask rules → ASK (honor explicit user intent to be prompted)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	457	# Step 3: Read-only fast path → ALLOW	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	464	# Step 4: Tool's own check_permissions — ALLOW / DENY returned;	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	476	# Step 5: Allow rules → ALLOW	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	483	# Step 6: Mode fallback → ALLOW everything else (BYPASS)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	530	# Step 1: Deny rules — highest priority (all modes)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	537	# Step 2: Ask rules → DENY (converted; no user available to answer)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	548	# Step 3: Read-only fast path → ALLOW	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	555	# Step 4: Tool's own check_permissions	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	574	# Step 5: Allow rules → ALLOW	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	581	# Step 6: Mode fallback → DENY (no user available to confirm)	COMMENT

Structural Annotation Overuse49 hits · 59 pts

Severity	File	Line	Snippet	Context
LOW	tests/middleware_budget_test.py	382	# Step 1: model produces a tool call that requires confirmation	COMMENT
LOW⚡	tests/service_agent_interrupt_test.py	207	# Step 1: Publish interrupt (simulating API endpoint)	COMMENT
LOW⚡	tests/service_agent_interrupt_test.py	216	# Step 2: Verify agent was interrupted	COMMENT
LOW⚡	tests/service_agent_interrupt_test.py	223	# Step 3: Verify chat-run task is done	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	974	# Step 1: Checking agent input:	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	981	# Step 2: Handling agent event if applicable	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	1015	# Step 3: Enter the reasoning-acting loop until reaching max_iters	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	1255	# Step 1: Analyze the current context	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	1312	# Step 2: Check Time Injection	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	1370	# Step 3: Check Plan Tasks	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	1383	# Step 4: Context Length	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	2284	# Step 1: Check and parse the tool call input:	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	2326	# Step 2: Check permission by toolkit and permission engine	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	2335	# Step 3: Handle the permission and execute the tool call if allowed	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	2428	# Step 4: Delegate raw execution to _acting (middleware hook point)	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	2444	# Step 5: Truncate the tool result if exceed	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	3256	# Step 1: Check executable and awaiting tool calls	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	3299	# Step 2: Check structured output if no blocked tool calls	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	3402	# Step 3: Exit with the final message, or continue reasoning	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	150	# Step 1: Deny rules — highest priority (all modes)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	157	# Step 2: Ask rules → ASK (with suggestions)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	168	# Step 3: Read-only fast path → ALLOW	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	175	# Step 4: Tool's own check_permissions	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	194	# Step 5: Allow rules → ALLOW	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	201	# Step 6: Mode fallback → ASK the user	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	248	# Step 1: Deny rules — highest priority (all modes)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	255	# Step 2: Ask rules → ASK (with suggestions)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	266	# Step 3: Read-only fast path → ALLOW	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	273	# Step 4: Tool's own check_permissions	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	280	# Step 5: Allow rules	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	286	# Step 6: Mode fallback → DENY (invocation is not read-only)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	330	# Step 1: Deny rules — highest priority (all modes)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	337	# Step 2: Ask rules → ASK (with suggestions)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	348	# Step 3: Read-only fast path → ALLOW	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	355	# Step 4: Tool's own check_permissions (working-directory auto-allow	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	375	# Step 5: Allow rules → ALLOW	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	382	# Step 6: Mode fallback → ASK the user	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	439	# Step 1: Deny rules — highest priority (all modes)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	446	# Step 2: Ask rules → ASK (honor explicit user intent to be prompted)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	457	# Step 3: Read-only fast path → ALLOW	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	464	# Step 4: Tool's own check_permissions — ALLOW / DENY returned;	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	476	# Step 5: Allow rules → ALLOW	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	483	# Step 6: Mode fallback → ALLOW everything else (BYPASS)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	530	# Step 1: Deny rules — highest priority (all modes)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	537	# Step 2: Ask rules → DENY (converted; no user available to answer)	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	548	# Step 3: Read-only fast path → ALLOW	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	555	# Step 4: Tool's own check_permissions	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	574	# Step 5: Allow rules → ALLOW	COMMENT
LOW⚡	src/agentscope/permission/_engine.py	581	# Step 6: Mode fallback → DENY (no user available to confirm)	COMMENT

Redundant / Tautological Comments35 hits · 53 pts

Severity	File	Line	Snippet	Context
LOW⚡	tests/builtin_file_cache_test.py	147	# Read the file to cache it	COMMENT
LOW⚡	tests/builtin_file_cache_test.py	190	# Read the file to cache it	COMMENT
LOW⚡	tests/builtin_file_cache_test.py	310	# Read the file	COMMENT
LOW	tests/builtin_file_cache_test.py	92	# Read the file first	COMMENT
LOW	tests/builtin_file_cache_test.py	120	# Read the file first	COMMENT
LOW	tests/builtin_edit_test.py	86	# Write file with duplicate content	COMMENT
LOW	tests/builtin_edit_test.py	101	# Write file with duplicate content	COMMENT
LOW	src/agentscope/skill/_local_loader.py	45	# Check if SKILL.md exists	COMMENT
LOW	src/agentscope/skill/_local_loader.py	112	# Check if directory exists	COMMENT
LOW	src/agentscope/workspace/_local_workspace.py	349	# Check if SKILL.md exists	COMMENT
LOW	…workspace/_applecontainer/_applecontainer_workspace.py	312	# Check if the image is already available locally.	COMMENT
LOW	…workspace/_applecontainer/_applecontainer_workspace.py	395	# Check if the container is already running.	COMMENT
LOW	src/agentscope/embedding/_dashscope/_model.py	270	# Check if adding this item would exceed any limit.	COMMENT
LOW⚡	src/agentscope/agent/_agent.py	2289	# Check if the tool is available	COMMENT
LOW	src/agentscope/agent/_agent.py	1543	# Check if res is an async generator (streaming response)	COMMENT
LOW	src/agentscope/agent/_agent.py	2759	# Check if the reserved part has tool results that don't have the	COMMENT
LOW	src/agentscope/state/_state.py	59	# Check if cache is still valid	COMMENT
LOW	src/agentscope/formatter/_gemini_formatter.py	49	# Check if media type is supported	COMMENT
LOW	src/agentscope/formatter/_anthropic_formatter.py	295	# Check if media type is supported	COMMENT
LOW	src/agentscope/formatter/_ollama_formatter.py	49	# Check if media type is supported	COMMENT
LOW	src/agentscope/tool/_base.py	437	# Check if filename matches dangerous files (case-insensitive)	COMMENT
LOW	src/agentscope/tool/_base.py	444	# Check if any path segment matches dangerous directories	COMMENT
LOW	src/agentscope/tool/_types.py	131	# Check if the two definitions are from the same BaseModel	COMMENT
LOW	src/agentscope/tool/_response.py	156	# Check if the last block is also a TextBlock	COMMENT
LOW	src/agentscope/tool/_builtin/_read.py	500	# Read file content via backend	COMMENT
LOW	src/agentscope/tool/_builtin/_write.py	252	# Check if file exists, it must be read first if it exists	COMMENT
LOW⚡	src/agentscope/tool/_builtin/_bash_parser.py	233	# Check if base command is in safe commands	COMMENT
LOW⚡	src/agentscope/tool/_builtin/_bash_parser.py	612	# Check if environment variables are safe	COMMENT
LOW⚡	src/agentscope/tool/_builtin/_bash_parser.py	616	# Check if the command is a safe command that doesn't need permission	COMMENT
LOW	src/agentscope/tool/_builtin/_bash_parser.py	179	# Check if it's a compound command	COMMENT
LOW	src/agentscope/tool/_builtin/_bash_parser.py	217	# Check if it starts with a read-only prefix	COMMENT
LOW	src/agentscope/tool/_builtin/_bash_parser.py	332	# Check if this is a file-manipulating command	COMMENT
LOW	src/agentscope/tool/_builtin/_bash_parser.py	910	# Check if this node is a dangerous type	COMMENT
LOW	src/agentscope/tool/_builtin/_bash.py	425	# Check if pattern is a prefix pattern (ends with :*)	STRING
LOW	src/agentscope/tool/_builtin/_bash.py	430	# Check if pattern has unescaped wildcards	STRING

Hallucination Indicators2 hits · 30 pts

Severity	File	Line	Snippet	Context
CRITICAL⚡	tests/tts_gemini_test.py	139	self.mock_client.aio.models.generate_content.assert_not_called()	CODE
CRITICAL⚡	tests/tts_gemini_test.py	149	self.mock_client.aio.models.generate_content.assert_not_called()	CODE

Over-Commented Block26 hits · 24 pts

Severity	File	Line	Snippet	Context
LOW	pyproject.toml	121	"pandas",	COMMENT
LOW	examples/long_term_memory/mem0/oss_demo.py	201	)	COMMENT
LOW	examples/long_term_memory/mem0/oss_demo.py	221	#	COMMENT
LOW	examples/long_term_memory/reme/reme_demo.py	261	# One middleware, shared across both sessions. ReMe is embedded	COMMENT
LOW	examples/web_ui/frontend/src/vite-env.d.ts	1	/// <reference types="vite/client" />	COMMENT
LOW	…ntend/src/components/dialog/WorkingDirectoryDialog.tsx	101	// The answer, and the single source of truth: whatever the input	COMMENT
LOW	examples/web_ui/frontend/src/hooks/useMessages.ts	301	}	COMMENT
LOW	.github/workflows/github-monitor.yml	1	# ─────────────────────────────────────────────────────────────────────────────	COMMENT
LOW	…scope/middleware/_longterm_memory/_mem0/_middleware.py	301		COMMENT
LOW	src/agentscope/app/_bus_ops.py	141	# Three helpers implementing one protocol, whose only job is to make	COMMENT
LOW	src/agentscope/app/_lifespan.py	181	)	COMMENT
LOW	src/agentscope/app/message_bus/_base.py	501	Registry key to delete.	COMMENT
LOW	src/agentscope/app/_router/_chat.py	101	# ------------------------------------------------------------------	COMMENT
LOW	src/agentscope/app/_service/_chat.py	661	# them, and may happen before either is resolved.	COMMENT
LOW	src/agentscope/app/_service/_index_worker.py	421	)	COMMENT
LOW	src/agentscope/app/storage/_sql/_storage.py	401	).scalar_one()	COMMENT
LOW	src/agentscope/app/storage/_sql/_alembic/alembic.ini	1	# Alembic configuration for the AgentScope SQL storage backend.	COMMENT
LOW	src/agentscope/app/_tool/_agent_invite.py	361	# rules are anchored to the leader's workspace, which the	COMMENT
LOW	src/agentscope/app/_tool/_agent_create.py	41	system_prompt_template=_DEFAULT_SYSTEM_PROMPT_TEMPLATE,	COMMENT
LOW	src/agentscope/workspace/_gateway_shim.py	21	"""	COMMENT
LOW	src/agentscope/workspace/_opensandbox/_constants.py	21	#: Per-command timeout for first-time bootstrap shell commands.	COMMENT
LOW	src/agentscope/permission/_engine.py	261	tool_input,	COMMENT
LOW	src/agentscope/tool/_constants.py	61	"fdisk",	COMMENT
LOW	src/agentscope/tool/_constants.py	101	#	COMMENT
LOW	src/agentscope/tool/_builtin/_backend.py	141	Subclasses must implement three abstract primitives — ``exec_shell``,	COMMENT
LOW	src/agentscope/tool/_builtin/_backend.py	161	#: .. important::	COMMENT

Fake / Example Data24 hits · 24 pts

Severity	File	Line	Snippet	Context
LOW	examples/web_ui/frontend/src/i18n/locales/zh.json	174	"placeholder": "我的智能体"	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/zh.json	217	"placeholder": "简要描述此智能体的专长；允许被邀请时必填。"	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/zh.json	237	"placeholder": "会话名称"	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/zh.json	258	"placeholder": "我的知识库"	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/zh.json	262	"placeholder": "描述知识库用途"	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/zh.json	292	"placeholder": "我的知识库"	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/zh.json	296	"placeholder": "描述知识库用途"	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/zh.json	420	"placeholder": "选择模型",	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/zh.json	431	"placeholder": "选择 Embedding 模型",	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/zh.json	440	"placeholder": "选择分块策略",	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/zh.json	460	"placeholder": "选择维度",	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/zh.json	464	"placeholder": "选择权限模式",	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/en.json	174	"placeholder": "My agent"	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/en.json	217	"placeholder": "Briefly describe this agent's expertise; required when invitable is on."	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/en.json	237	"placeholder": "Session name"	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/en.json	258	"placeholder": "My knowledge base"	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/en.json	262	"placeholder": "Describe what this knowledge base is for."	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/en.json	292	"placeholder": "My knowledge base"	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/en.json	296	"placeholder": "Describe what this knowledge base is for."	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/en.json	420	"placeholder": "Select a model",	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/en.json	431	"placeholder": "Select an embedding model",	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/en.json	440	"placeholder": "Select a chunker",	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/en.json	460	"placeholder": "Select a dimension",	CODE
LOW	examples/web_ui/frontend/src/i18n/locales/en.json	464	"placeholder": "Select permission mode",	CODE

AI Structural Patterns24 hits · 23 pts

Severity	File	Line	Context
LOW	…scope/middleware/_longterm_memory/_mem0/_middleware.py	143	CODE
LOW	src/agentscope/app/_app.py	78	CODE
LOW	src/agentscope/app/_router/_knowledge_base.py	312	CODE
LOW	src/agentscope/app/_router/_knowledge_base.py	465	CODE
LOW	…ope/app/_manager/_scheduler/_tools/_schedule_create.py	163	CODE
LOW	…ope/app/workspace_manager/_docker_workspace_manager.py	65	CODE
LOW	…app/workspace_manager/_bubblewrap_workspace_manager.py	40	CODE
LOW	…workspace_manager/_applecontainer_workspace_manager.py	50	CODE
LOW	…pp/workspace_manager/_opensandbox_workspace_manager.py	57	CODE
LOW	…tscope/app/workspace_manager/_k8s_workspace_manager.py	43	CODE
LOW	…pe/app/workspace_manager/_daytona_workspace_manager.py	48	CODE
LOW	…tscope/app/workspace_manager/_e2b_workspace_manager.py	66	CODE
LOW	src/agentscope/app/hub/_skill/_claw_hub.py	86	CODE
LOW	src/agentscope/workspace/_e2b/_e2b_workspace.py	75	CODE
LOW	src/agentscope/workspace/_daytona/_daytona_workspace.py	79	CODE
LOW	…workspace/_applecontainer/_applecontainer_workspace.py	89	CODE
LOW	src/agentscope/workspace/_k8s/_k8s_workspace.py	60	CODE
LOW	…ntscope/workspace/_bubblewrap/_bubblewrap_workspace.py	77	CODE
LOW	…scope/workspace/_opensandbox/_opensandbox_workspace.py	49	CODE
LOW	src/agentscope/workspace/_docker/_docker_workspace.py	52	CODE
LOW	src/agentscope/agent/_agent.py	115	CODE
LOW	src/agentscope/model/_ollama/_model.py	56	CODE
LOW	src/agentscope/model/_openai_chat/_model.py	111	CODE
LOW	src/agentscope/tool/_builtin/_grep.py	320	CODE

Dead Code7 hits · 14 pts

Severity	File	Line	Context
MEDIUM	tests/tool_middleware_test.py	331	CODE
MEDIUM	tests/service_inbox_middleware_test.py	208	CODE
MEDIUM	tests/service_inbox_middleware_test.py	114	CODE
MEDIUM	tests/service_inbox_middleware_test.py	125	CODE
MEDIUM	src/agentscope/middleware/_base.py	99	CODE
MEDIUM	src/agentscope/middleware/_base.py	122	CODE
MEDIUM	src/agentscope/middleware/_base.py	168	CODE

AI Slop Vocabulary1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	…scope/middleware/_longterm_memory/_mem0/_middleware.py	296	# tools — so just pass through.	COMMENT

Overly Generic Function Names1 hit · 0 pts

Severity	File	Line	Snippet	Context
LOW	tests/workspace_local_test.py	605	{"helper.py": "def helper():\n return 42\n"},	STRING

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings