confident-ai/deepeval

Pattern Findings

The scanner identified 6046 distinct pattern matches across 22 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.

Hyper-Verbose Identifiers3074 hits · 3077 pts

Severity	File	Line	Snippet	Context
LOW	c.py	155	def _transcribe_what_has_arrived(self) -> None:	CODE
LOW	typescript/test/test-integrations/utils.ts	54	export function assertJsonObjectStructure(	CODE
LOW	typescript/src/env-flags.ts	42	export function shouldSkipOnMissingParams(): boolean {	CODE
LOW	typescript/src/metrics/utils.ts	201	export function checkAtLeastOneMetricHasThreshold(	CODE
LOW	typescript/src/metrics/utils.ts	401	export function warnScoreDirectionFlipped(metricName: string): void {	CODE
LOW	typescript/src/metrics/retrieval-context-display.ts	26	export function contextualRecallVerdictVars(	CODE
LOW	typescript/src/metrics/retrieval-context-display.ts	44	export function contextualRecallReasonContentType(multimodal: boolean): string {	CODE
LOW	typescript/src/metrics/retrieval-context-display.ts	49	export function contextualRelevancyVerdictVars(	CODE
LOW	typescript/src/metrics/conversational-utils.ts	11	export function checkConversationalTestCaseParams(	CODE
LOW	typescript/src/metrics/g-eval/utils.ts	66	export function constructGEvalParamsString(params: SingleTurnParams[]): string {	CODE
LOW	typescript/src/metrics/g-eval/utils.ts	108	export function validateAndSortRubrics(	CODE
LOW	typescript/src/metrics/g-eval/utils.ts	138	export function calculateWeightedSummedScore(	CODE
LOW	typescript/src/metrics/g-eval/utils.ts	214	export function validateCriteriaAndEvaluationSteps(	CODE
LOW	typescript/src/metrics/dag/serialization.ts	463	export function constructDagUploadPayload(	CODE
LOW	typescript/src/metrics/faithfulness/faithfulness.ts	42	function truthsMultimodalInstruction(multimodal: boolean): string {	CODE
LOW	typescript/src/metrics/faithfulness/faithfulness.ts	46	function claimsMultimodalInstruction(multimodal: boolean): string {	CODE
LOW	…c/metrics/contextual-relevancy/contextual-relevancy.ts	36	function systemOneRelevancyVerdict(	CODE
LOW	typescript/src/metrics/conversational-g-eval/utils.ts	18	export function constructConversationalGEvalTurnParamsString(	CODE
LOW	typescript/src/metrics/conversational-g-eval/utils.ts	61	export function constructNonTurnsTestCaseString(	CODE
LOW	typescript/src/test-case/mllm-image.ts	186	export function extractImageIdsFromString(	CODE
LOW	typescript/src/config/settings.ts	50	function applyTelemetryOptOutAlias(settings: Settings): Settings {	CODE
LOW	typescript/src/dataset/utils.ts	23	export function convertTestCasesToGoldens(testCases: LLMTestCase[]): Golden[] {	CODE
LOW	typescript/src/dataset/utils.ts	47	export function convertGoldensToTestCases(	CODE
LOW	typescript/src/dataset/utils.ts	75	export function convertConvoTestCasesToConvoGoldens(	CODE
LOW	typescript/src/dataset/utils.ts	100	export function convertConvoGoldensToConvoTestCases(	CODE
LOW	typescript/src/dataset/utils.ts	147	function createConversationalTestCase(params: {	CODE
LOW	typescript/src/dataset/utils.ts	187	export function stripLocalExpectationFields(	CODE
LOW	typescript/src/dataset/utils.ts	236	export function serializeRetrievalContext(	CODE
LOW	typescript/src/dataset/utils.ts	291	export function reconstructRetrievalContext(	CODE
LOW	typescript/src/cli/commands/auth.ts	131	async function promptDynamicQuestionnaire(	CODE
LOW	typescript/src/integrations/openinference/index.ts	136	export function createOpenInferenceProcessors(	CODE
LOW	typescript/src/integrations/langchain/utils.ts	114	export function prepareToolCallInputParameters(	CODE
LOW	typescript/src/integrations/openai-agents/extractors.ts	29	export function updateTracePropertiesFromSpanData(	CODE
LOW	typescript/src/integrations/openai-agents/extractors.ts	138	function updateSpanPropertiesFromResponseSpanData(	CODE
LOW	typescript/src/integrations/openai-agents/extractors.ts	212	function updateSpanPropertiesFromGenerationSpanData(	CODE
LOW	typescript/src/integrations/openai-agents/extractors.ts	250	function updateSpanPropertiesFromFunctionSpanData(	CODE
LOW	typescript/src/integrations/openai-agents/extractors.ts	271	function updateSpanPropertiesFromAgentSpanData(	CODE
LOW	typescript/src/integrations/openai-agents/extractors.ts	299	function updateSpanPropertiesFromMcpListToolsSpanData(	CODE
LOW	typescript/src/integrations/openai-agents/extractors.ts	313	function updateSpanPropertiesFromHandoffSpanData(	CODE
LOW	typescript/src/integrations/openai-agents/extractors.ts	327	function updateSpanPropertiesFromCustomSpanData(	CODE
LOW	typescript/src/integrations/openai-agents/extractors.ts	338	function updateSpanPropertiesFromGuardrailSpanData(	CODE
LOW	typescript/src/integrations/openai-agents/extractors.ts	456	function parseFunctionToolCallParam(toolCall: any): any {	CODE
LOW	typescript/src/evaluate/expectations.ts	294	export function validateExpectationCoverage(	CODE
LOW	typescript/src/evaluate/console-report.ts	412	export function printHyperparametersWarning(	CODE
LOW	typescript/src/prompt/utils.ts	22	export function interpolateMustacheWithSpace(	CODE
LOW	typescript/src/prompt/utils.ts	44	export function interpolateDollarBrackets(	CODE
LOW	typescript/src/telemetry/api.ts	210	export function captureConversationSimulatorRun(	CODE
LOW	typescript/src/telemetry/api.ts	275	export function captureLoginPromptShownOnce(surface: LoginPromptSurface): void {	CODE
LOW	typescript/src/openai/utils.ts	28	export function stringifyMultimodalContent(content: any): string {	CODE
LOW	typescript/src/openai/extractor.ts	13	export function safeExtractInputParameters(	CODE
LOW	typescript/src/openai/extractor.ts	26	export function extractInputParametersFromCompletionAPI(	CODE
LOW	typescript/src/openai/extractor.ts	63	export function extractInputParametersFromResponseAPI(	CODE
LOW	typescript/src/openai/extractor.ts	99	export function safeExtractOutputParameters(	CODE
LOW	typescript/src/openai/extractor.ts	119	export function extractOutputParametersFromCompletionAPI(	CODE
LOW	typescript/src/openai/extractor.ts	165	export function extractOutputParametersFromResponseAPI(	CODE
LOW	typescript/src/openai/patch.ts	93	function patchAsyncOpenAIClientMethod(	CODE
LOW	typescript/src/openai/patch.ts	184	function updateInputAndOutputOfCurrentTrace(	CODE
LOW⚡	tests/test_agent_loop_detection.py	86	def test_repeated_tool_calls_detected():	CODE
LOW⚡	tests/test_agent_loop_detection.py	119	def test_no_trace_returns_zero():	CODE
LOW⚡	tests/test_agent_loop_detection.py	135	def test_reasoning_stagnation_detected():	CODE
3014 more matches not shown…

Decorative Section Separators410 hits · 1545 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tests/test_agent_loop_detection.py	81	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_agent_loop_detection.py	83	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_agent_loop_detection.py	114	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_agent_loop_detection.py	116	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_agent_loop_detection.py	130	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_agent_loop_detection.py	132	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_agent_loop_detection.py	164	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_agent_loop_detection.py	166	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_agent_loop_detection.py	193	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_agent_loop_detection.py	195	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_agent_loop_detection.py	211	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_agent_loop_detection.py	213	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_agent_loop_detection.py	253	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_agent_loop_detection.py	255	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_agent_loop_detection.py	285	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_agent_loop_detection.py	287	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_agent_loop_detection.py	330	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_agent_loop_detection.py	332	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_agent_loop_detection.py	12	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_agent_loop_detection.py	14	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_agent_loop_detection.py	58	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_agent_loop_detection.py	60	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_metrics/test_dag_serialization.py	31	# ----------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_metrics/test_dag_serialization.py	33	# ----------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_metrics/test_dag_serialization.py	224	# ----------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_metrics/test_dag_serialization.py	226	# ----------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_metrics/test_dag_serialization.py	396	# ----------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_metrics/test_dag_serialization.py	398	# ----------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_metrics/test_dag_serialization.py	287	# ----------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_metrics/test_dag_serialization.py	289	# ----------------------------------------------------------------------------	COMMENT
MEDIUM⚡	…t_integrations/test_googleadk/test_span_interceptor.py	173	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	…t_integrations/test_googleadk/test_span_interceptor.py	175	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	…t_integrations/test_googleadk/test_span_interceptor.py	282	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	…t_integrations/test_googleadk/test_span_interceptor.py	284	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	…t_integrations/test_googleadk/test_span_interceptor.py	466	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	…t_integrations/test_googleadk/test_span_interceptor.py	469	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	…t_integrations/test_googleadk/test_span_interceptor.py	529	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	…t_integrations/test_googleadk/test_span_interceptor.py	531	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	…t_integrations/test_googleadk/test_span_interceptor.py	1030	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	…t_integrations/test_googleadk/test_span_interceptor.py	1032	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	…t_integrations/test_googleadk/test_span_interceptor.py	363	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	…t_integrations/test_googleadk/test_span_interceptor.py	365	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	…t_integrations/test_googleadk/test_span_interceptor.py	730	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	…t_integrations/test_googleadk/test_span_interceptor.py	733	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	…t_integrations/test_googleadk/test_span_interceptor.py	984	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	…t_integrations/test_googleadk/test_span_interceptor.py	986	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_integrations/test_llamaindex/test_sync.py	42	# =============================================================================	COMMENT
MEDIUM	tests/test_integrations/test_llamaindex/test_sync.py	44	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_integrations/test_llamaindex/test_sync.py	66	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_integrations/test_llamaindex/test_sync.py	68	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_integrations/test_llamaindex/test_sync.py	105	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_integrations/test_llamaindex/test_sync.py	107	# =============================================================================	COMMENT
MEDIUM	tests/test_integrations/test_llamaindex/test_async.py	58	# =============================================================================	COMMENT
MEDIUM	tests/test_integrations/test_llamaindex/test_async.py	60	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_integrations/test_llamaindex/test_async.py	83	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_integrations/test_llamaindex/test_async.py	85	# =============================================================================	COMMENT
MEDIUM	tests/test_integrations/test_llamaindex/test_async.py	108	# =============================================================================	COMMENT
MEDIUM	tests/test_integrations/test_llamaindex/test_async.py	110	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_integrations/test_llamaindex/test_async.py	150	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_integrations/test_llamaindex/test_async.py	152	# =============================================================================	COMMENT
350 more matches not shown…

Unused Imports1042 hits · 942 pts

Severity	File	Line	Context
LOW	test_pydantic_agent.py	19	CODE
LOW	tests/test_agent_loop_detection.py	6	CODE
LOW	tests/test_metrics/test_mcp_use_metric.py	4	CODE
LOW	tests/test_metrics/test_exact_match_metric.py	4	CODE
LOW	tests/test_metrics/test_dag_serialization.py	4	CODE
LOW	tests/test_metrics/test_dag_serialization.py	21	CODE
LOW	…sts/test_metrics/test_turn_contextual_recall_metric.py	4	CODE
LOW	…trics/test_conversation_completeness_include_reason.py	13	CODE
LOW	…ts/test_metrics/test_topic_adherence_include_reason.py	18	CODE
LOW	tests/test_metrics/turn_contextual_relevancy_metric.py	4	CODE
LOW	…t_metrics/test_answer_relevancy_metric_empty_output.py	18	CODE
LOW	tests/test_integrations/utils.py	1	CODE
LOW	…t_integrations/test_googleadk/test_span_interceptor.py	46	CODE
LOW	…tegrations/test_googleadk/apps/googleadk_simple_app.py	8	CODE
LOW	…ns/test_googleadk/apps/googleadk_multiple_tools_app.py	9	CODE
LOW	…integrations/test_googleadk/apps/googleadk_tool_app.py	8	CODE
LOW	…integrations/test_googleadk/apps/googleadk_eval_app.py	18	CODE
LOW	tests/test_integrations/test_anthropic/conftest.py	6	CODE
LOW	tests/test_integrations/test_crewai/test_stress.py	48	CODE
LOW	…t_integrations/test_crewai/test_knowledge_retriever.py	7	CODE
LOW	…t_integrations/test_crewai/test_knowledge_retriever.py	8	CODE
LOW	…test_integrations/test_crewai/test_crewai_component.py	2	CODE
LOW	…test_integrations/test_crewai/test_crewai_component.py	3	CODE
LOW	…test_integrations/test_crewai/test_crewai_component.py	4	CODE
LOW	…test_integrations/test_crewai/test_crewai_component.py	5	CODE
LOW	tests/test_integrations/test_crewai/test_crewai.py	2	CODE
LOW	tests/test_integrations/test_crewai/test_crewai.py	3	CODE
LOW	tests/test_integrations/test_crewai/test_crewai.py	4	CODE
LOW	tests/test_integrations/test_crewai/test_crewai.py	5	CODE
LOW	tests/test_integrations/test_crewai/test_crewai.py	7	CODE
LOW	tests/test_integrations/test_crewai/test_crewai.py	19	CODE
LOW	tests/test_integrations/test_crewai/apps/simple_app.py	7	CODE
LOW	tests/test_integrations/test_crewai/apps/simple_app.py	9	CODE
LOW	tests/test_integrations/test_crewai/apps/async_app.py	7	CODE
LOW	…rations/test_langgraph/apps/langgraph_next_span_app.py	18	CODE
LOW	tests/test_integrations/test_strands/conftest.py	2	CODE
LOW	…est_integrations/test_strands/test_span_interceptor.py	28	CODE
LOW	…tegrations/test_openai/test_tool_call_flow_response.py	6	CODE
LOW	tests/test_integrations/test_openai/test_sync_openai.py	4	CODE
LOW	…grations/test_openai/test_tool_call_flow_completion.py	6	CODE
LOW	…sts/test_integrations/test_openai/test_async_openai.py	1	CODE
LOW	…sts/test_integrations/test_openai/test_async_openai.py	7	CODE
LOW	tests/test_integrations/test_openai_agents/test_sync.py	9	CODE
LOW	…grations/test_openai_agents/test_scenerios/test_run.py	6	CODE
LOW	…test_openai_agents/test_scenerios/test_multi_agents.py	2	CODE
LOW	…test_openai_agents/test_scenerios/test_multi_agents.py	3	CODE
LOW	…test_openai_agents/test_scenerios/test_multi_agents.py	6	CODE
LOW	…test_openai_agents/test_scenerios/test_multi_agents.py	7	CODE
LOW	…i_agents/test_scenerios/test_with_trace_and_wrapped.py	3	CODE
LOW	…s/test_openai_agents/test_scenerios/test_with_trace.py	5	CODE
LOW	…ons/test_openai_agents/test_scenerios/test_run_sync.py	2	CODE
LOW	…ons/test_openai_agents/test_scenerios/test_run_sync.py	3	CODE
LOW	…ai_agents/test_scenerios/test_weather_agent_patched.py	2	CODE
LOW	…test_openai_agents/test_scenerios/test_run_streamed.py	4	CODE
LOW	…sts/test_integrations/test_langchain/test_next_span.py	18	CODE
LOW	tests/test_integrations/test_pydanticai/conftest.py	2	CODE
LOW	tests/test_integrations/test_agentcore/conftest.py	2	CODE
LOW	…t_integrations/test_agentcore/test_span_interceptor.py	28	CODE
LOW	tests/test_confident/test_prompt.py	8	CODE
LOW	tests/test_confident/test_prompt.py	8	CODE
982 more matches not shown…

Empty Error Handlers158 hits · 790 pts

Severity	File	Line	Snippet	Context
HIGH	c.py	276	except (asyncio.CancelledError, Exception):	CODE
HIGH	tests/test_integrations/test_langgraph/conftest.py	502	except ImportError:	CODE
HIGH	tests/test_integrations/test_langgraph/conftest.py	509	except ImportError:	CODE
HIGH	tests/test_integrations/test_langgraph/conftest.py	518	except ImportError:	CODE
HIGH	tests/test_integrations/test_langgraph/conftest.py	242	except Exception:	CODE
HIGH	tests/test_integrations/test_langgraph/conftest.py	268	except Exception:	CODE
HIGH	tests/test_integrations/test_openai_agents/conftest.py	17	except Exception:	CODE
HIGH	tests/test_integrations/test_langchain/conftest.py	311	except ImportError:	CODE
HIGH	tests/test_integrations/test_langchain/conftest.py	199	except Exception:	CODE
HIGH	tests/test_integrations/test_langchain/conftest.py	224	except Exception:	CODE
HIGH	tests/test_core/conftest.py	7	except Exception:	CODE
HIGH	tests/test_core/conftest.py	194	except Exception:	CODE
HIGH	…racing/test_integration/test_current_golden_context.py	76	except Exception:	CODE
HIGH	…racing/test_integration/test_current_golden_context.py	104	except Exception:	CODE
HIGH	…re/test_evaluation/test_execute/test_error_boundary.py	555	except asyncio.CancelledError:	CODE
HIGH	…re/test_evaluation/test_execute/test_error_boundary.py	329	except StopIteration:	CODE
HIGH	…re/test_evaluation/test_execute/test_error_boundary.py	414	except StopIteration:	CODE
HIGH	…re/test_evaluation/test_execute/test_error_boundary.py	499	except StopIteration:	CODE
HIGH	…re/test_evaluation/test_execute/test_error_boundary.py	613	except StopIteration:	CODE
HIGH	…re/test_evaluation/test_execute/test_error_boundary.py	712	except StopIteration:	CODE
HIGH	…re/test_evaluation/test_execute/test_error_boundary.py	770	except StopIteration:	CODE
HIGH	…re/test_evaluation/test_execute/test_error_boundary.py	481	except Exception:	CODE
HIGH	tests/test_core/test_voice/test_duplex.py	512	except (asyncio.CancelledError, Exception):	CODE
HIGH	.scripts/release.py	399	except subprocess.CalledProcessError:	CODE
HIGH	.scripts/release.py	385	except subprocess.CalledProcessError:	CODE
HIGH	.scripts/changelog/generate.py	890	except ValueError:	CODE
HIGH	deepeval/__init__.py	138	except ModuleNotFoundError:	CODE
HIGH	deepeval/__init__.py	129	except (	CODE
HIGH	deepeval/utils.py	785	except KeyError:	CODE
HIGH	deepeval/key_handler.py	322	except FileNotFoundError:	CODE
HIGH	…l/metrics/agent_loop_detection/agent_loop_detection.py	306	except Exception:	CODE
HIGH	deepeval/metrics/utils/decision.py	196	except Exception: # SDK optional	CODE
HIGH	deepeval/metrics/utils/decision.py	228	except Exception: # SDK optional	CODE
HIGH	deepeval/metrics/role_adherence/role_adherence.py	239	except Exception:	CODE
HIGH	deepeval/metrics/role_adherence/role_adherence.py	274	except Exception:	CODE
HIGH	deepeval/tracing/tracing.py	334	except Exception:	CODE
HIGH	deepeval/tracing/tracing.py	410	except ValueError:	CODE
HIGH	deepeval/tracing/patchers.py	69	except Exception:	CODE
HIGH	deepeval/tracing/patchers.py	95	except Exception:	CODE
HIGH	deepeval/tracing/patchers.py	183	except Exception:	CODE
HIGH	deepeval/tracing/patchers.py	206	except Exception:	CODE
HIGH	deepeval/tracing/otel/context_aware_processor.py	136	except Exception:	CODE
HIGH	deepeval/tracing/otel/exporter.py	360	except Exception:	CODE
HIGH	deepeval/tracing/otel/exporter.py	288	except Exception:	CODE
HIGH	deepeval/tracing/otel/exporter.py	296	except Exception:	CODE
HIGH	deepeval/tracing/otel/exporter.py	813	except ValidationError:	CODE
HIGH	deepeval/tracing/otel/exporter.py	821	except Exception:	CODE
HIGH	deepeval/tracing/otel/exporter.py	648	except Exception:	CODE
HIGH	deepeval/tracing/otel/exporter.py	654	except Exception:	CODE
HIGH	deepeval/tracing/otel/exporter.py	672	except Exception:	CODE
HIGH	deepeval/tracing/otel/exporter.py	718	except Exception:	CODE
HIGH	deepeval/tracing/otel/exporter.py	725	except Exception:	CODE
HIGH	deepeval/tracing/otel/exporter.py	834	except ValidationError:	CODE
HIGH	deepeval/tracing/otel/utils.py	84	except Exception:	CODE
HIGH	deepeval/tracing/otel/utils.py	345	except Exception:	CODE
HIGH	deepeval/tracing/otel/utils.py	350	except Exception:	CODE
HIGH	deepeval/tracing/otel/utils.py	444	except Exception:	CODE
HIGH	deepeval/tracing/otel/utils.py	459	except Exception:	CODE
HIGH	deepeval/tracing/otel/utils.py	478	except Exception:	CODE
HIGH	deepeval/tracing/otel/utils.py	489	except Exception:	CODE
98 more matches not shown…

Cross-File Repetition154 hits · 770 pts

Severity	File	Line	Snippet	Context
HIGH	…trics/test_conversation_completeness_include_reason.py	0	minimal deepevalbasellm that never calls out to a provider.	STRING
HIGH	…ts/test_metrics/test_topic_adherence_include_reason.py	0	minimal deepevalbasellm that never calls out to a provider.	STRING
HIGH	…etrics/test_turn_faithfulness_metric_empty_verdicts.py	0	minimal deepevalbasellm that never calls out to a provider.	STRING
HIGH	tests/test_integrations/test_googleadk/test_sync.py	0	tool-level metric_collection now flows through ``with next_tool_span(metric_collection=...)`` at the call site instead o	STRING
HIGH	tests/test_integrations/test_strands/test_sync.py	0	tool-level metric_collection now flows through ``with next_tool_span(metric_collection=...)`` at the call site instead o	STRING
HIGH	tests/test_integrations/test_agentcore/test_sync.py	0	tool-level metric_collection now flows through ``with next_tool_span(metric_collection=...)`` at the call site instead o	STRING
HIGH	tests/test_integrations/test_googleadk/test_async.py	0	async equivalent of ``testdeepevalfeatures``: span-level kwargs migrate from ``init_evals_agentcore(...)`` to per-call `	STRING
HIGH	tests/test_integrations/test_strands/test_async.py	0	async equivalent of ``testdeepevalfeatures``: span-level kwargs migrate from ``init_evals_agentcore(...)`` to per-call `	STRING
HIGH	tests/test_integrations/test_agentcore/test_async.py	0	async equivalent of ``testdeepevalfeatures``: span-level kwargs migrate from ``init_evals_agentcore(...)`` to per-call `	STRING
HIGH	…t_integrations/test_googleadk/test_span_interceptor.py	0	falls back to settings when current_trace_context is none.	STRING
HIGH	…est_integrations/test_strands/test_span_interceptor.py	0	falls back to settings when current_trace_context is none.	STRING
HIGH	…_integrations/test_pydanticai/test_span_interceptor.py	0	falls back to settings when current_trace_context is none.	STRING
HIGH	…t_integrations/test_agentcore/test_span_interceptor.py	0	falls back to settings when current_trace_context is none.	STRING
HIGH	…t_integrations/test_googleadk/test_span_interceptor.py	0	trace attrs are snapshotted fresh at on_end, not on_start. regression guard for the at-on_start asymmetry: if a downstre	STRING
HIGH	…est_integrations/test_strands/test_span_interceptor.py	0	trace attrs are snapshotted fresh at on_end, not on_start. regression guard for the at-on_start asymmetry: if a downstre	STRING
HIGH	…t_integrations/test_agentcore/test_span_interceptor.py	0	trace attrs are snapshotted fresh at on_end, not on_start. regression guard for the at-on_start asymmetry: if a downstre	STRING
HIGH	…t_integrations/test_googleadk/test_span_interceptor.py	0	symmetric to ``testspancontextpushpop`` but at the trace level. the interceptor pushes an implicit ``trace`` placeholder	STRING
HIGH	…est_integrations/test_strands/test_span_interceptor.py	0	symmetric to ``testspancontextpushpop`` but at the trace level. the interceptor pushes an implicit ``trace`` placeholder	STRING
HIGH	…t_integrations/test_agentcore/test_span_interceptor.py	0	symmetric to ``testspancontextpushpop`` but at the trace level. the interceptor pushes an implicit ``trace`` placeholder	STRING
HIGH	…t_integrations/test_googleadk/test_span_interceptor.py	0	when a real deepeval span is on ``current_span_context`` and the otel span is a root (no native parent), the interceptor	STRING
HIGH	…est_integrations/test_strands/test_span_interceptor.py	0	when a real deepeval span is on ``current_span_context`` and the otel span is a root (no native parent), the interceptor	STRING
HIGH	…t_integrations/test_agentcore/test_span_interceptor.py	0	when a real deepeval span is on ``current_span_context`` and the otel span is a root (no native parent), the interceptor	STRING
HIGH	…t_integrations/test_googleadk/test_span_interceptor.py	0	otel children already have a real parent_id pointing into the same otel trace — no need to bridge.	STRING
HIGH	…est_integrations/test_strands/test_span_interceptor.py	0	otel children already have a real parent_id pointing into the same otel trace — no need to bridge.	STRING
HIGH	…t_integrations/test_agentcore/test_span_interceptor.py	0	otel children already have a real parent_id pointing into the same otel trace — no need to bridge.	STRING
HIGH	…t_integrations/test_googleadk/test_span_interceptor.py	0	one-shot semantics through the interceptor: a second agent span inside the same ``with`` block does not inherit.	STRING
HIGH	…est_integrations/test_strands/test_span_interceptor.py	0	one-shot semantics through the interceptor: a second agent span inside the same ``with`` block does not inherit.	STRING
HIGH	…_integrations/test_pydanticai/test_span_interceptor.py	0	one-shot semantics through the interceptor: a second agent span inside the same ``with`` block does not inherit.	STRING
HIGH	…t_integrations/test_agentcore/test_span_interceptor.py	0	one-shot semantics through the interceptor: a second agent span inside the same ``with`` block does not inherit.	STRING
HIGH	…t_integrations/test_googleadk/test_span_interceptor.py	0	typed slot is not consumed by spans of a different type. an llm span fired inside ``with next_agent_span(...)`` should p	STRING
HIGH	…est_integrations/test_strands/test_span_interceptor.py	0	typed slot is not consumed by spans of a different type. an llm span fired inside ``with next_agent_span(...)`` should p	STRING
HIGH	…t_integrations/test_agentcore/test_span_interceptor.py	0	typed slot is not consumed by spans of a different type. an llm span fired inside ``with next_agent_span(...)`` should p	STRING
HIGH	…t_integrations/test_googleadk/test_span_interceptor.py	0	mirrors the ``test_tool_metric_collection`` flow in test_sync.py — ``with next_tool_span(metric_collection=...)`` sets t	STRING
HIGH	…est_integrations/test_strands/test_span_interceptor.py	0	mirrors the ``test_tool_metric_collection`` flow in test_sync.py — ``with next_tool_span(metric_collection=...)`` sets t	STRING
HIGH	…t_integrations/test_agentcore/test_span_interceptor.py	0	mirrors the ``test_tool_metric_collection`` flow in test_sync.py — ``with next_tool_span(metric_collection=...)`` sets t	STRING
HIGH	…t_integrations/test_googleadk/test_span_interceptor.py	0	``with next_llm_span(prompt=...)`` flattens the ``prompt`` into the ``confident.span.prompt_*`` attrs the exporter reads	STRING
HIGH	…_integrations/test_pydanticai/test_span_interceptor.py	0	``with next_llm_span(prompt=...)`` flattens the ``prompt`` into the ``confident.span.prompt_*`` attrs the exporter reads	STRING
HIGH	…t_integrations/test_agentcore/test_span_interceptor.py	0	``with next_llm_span(prompt=...)`` flattens the ``prompt`` into the ``confident.span.prompt_*`` attrs the exporter reads	STRING
HIGH	…t_integrations/test_googleadk/test_span_interceptor.py	0	last-write-wins: ``next_agent_span`` sets the floor at on_start; later ``update_current_span(...)`` (e.g. from inside a	STRING
HIGH	…est_integrations/test_strands/test_span_interceptor.py	0	last-write-wins: ``next_agent_span`` sets the floor at on_start; later ``update_current_span(...)`` (e.g. from inside a	STRING
HIGH	…t_integrations/test_agentcore/test_span_interceptor.py	0	last-write-wins: ``next_agent_span`` sets the floor at on_start; later ``update_current_span(...)`` (e.g. from inside a	STRING
HIGH	…t_integrations/test_googleadk/test_span_interceptor.py	0	``with next_agent_span(metrics=[...])`` populates the placeholder; at on_end the interceptor calls ``stash_pending_metri	STRING
HIGH	…est_integrations/test_strands/test_span_interceptor.py	0	``with next_agent_span(metrics=[...])`` populates the placeholder; at on_end the interceptor calls ``stash_pending_metri	STRING
HIGH	…t_integrations/test_agentcore/test_span_interceptor.py	0	``with next_agent_span(metrics=[...])`` populates the placeholder; at on_end the interceptor calls ``stash_pending_metri	STRING
HIGH	…t_integrations/test_googleadk/test_span_interceptor.py	0	in production paths (``is_evaluating=false``) the metrics overlay would leak — gate prevents the stash.	STRING
HIGH	…est_integrations/test_strands/test_span_interceptor.py	0	in production paths (``is_evaluating=false``) the metrics overlay would leak — gate prevents the stash.	STRING
HIGH	…t_integrations/test_agentcore/test_span_interceptor.py	0	in production paths (``is_evaluating=false``) the metrics overlay would leak — gate prevents the stash.	STRING
HIGH	…t_integrations/test_googleadk/test_span_interceptor.py	0	span-level kwargs were removed in the otel poc migration. each must raise ``typeerror`` on construction so callers see e	STRING
HIGH	…est_integrations/test_strands/test_span_interceptor.py	0	span-level kwargs were removed in the otel poc migration. each must raise ``typeerror`` on construction so callers see e	STRING
HIGH	…t_integrations/test_agentcore/test_span_interceptor.py	0	span-level kwargs were removed in the otel poc migration. each must raise ``typeerror`` on construction so callers see e	STRING
HIGH	…t_integrations/test_googleadk/test_span_interceptor.py	0	constructor must succeed when no api_key is supplied or in env. the otel pipeline still wires up locally — only the outb	STRING
HIGH	…est_integrations/test_strands/test_span_interceptor.py	0	constructor must succeed when no api_key is supplied or in env. the otel pipeline still wires up locally — only the outb	STRING
HIGH	…t_integrations/test_agentcore/test_span_interceptor.py	0	constructor must succeed when no api_key is supplied or in env. the otel pipeline still wires up locally — only the outb	STRING
HIGH	…ns/test_googleadk/apps/googleadk_multiple_tools_app.py	0	trace-level setup for the multiple-tools fixture. per-tool / per-agent metric collections belong on ``with next_*_span(.	STRING
HIGH	…ations/test_strands/apps/strands_multiple_tools_app.py	0	trace-level setup for the multiple-tools fixture. per-tool / per-agent metric collections belong on ``with next_*_span(.	STRING
HIGH	…ns/test_agentcore/apps/agentcore_multiple_tools_app.py	0	trace-level setup for the multiple-tools fixture. per-tool / per-agent metric collections belong on ``with next_*_span(.	STRING
HIGH	…integrations/test_googleadk/apps/googleadk_tool_app.py	0	trace-only setup. tool / agent / llm span-level fields belong at the call site (``with next_*_span(...)`` or ``update_cu	STRING
HIGH	…est_integrations/test_strands/apps/strands_tool_app.py	0	trace-only setup. tool / agent / llm span-level fields belong at the call site (``with next_*_span(...)`` or ``update_cu	STRING
HIGH	…integrations/test_agentcore/apps/agentcore_tool_app.py	0	trace-only setup. tool / agent / llm span-level fields belong at the call site (``with next_*_span(...)`` or ``update_cu	STRING
HIGH	…integrations/test_googleadk/apps/googleadk_eval_app.py	0	agentcore evals fixture — trace-level setup with a strands tool that mutates its own span via ``update_current_span``. a	STRING
94 more matches not shown…

Excessive Try-Catch Wrapping378 hits · 383 pts

Severity	File	Line	Snippet	Context
LOW	c.py	182	except Exception:	CODE
LOW⚡	tests/test_integrations/test_langgraph/conftest.py	144	except Exception:	CODE
LOW	tests/test_integrations/test_langgraph/conftest.py	242	except Exception:	CODE
LOW	tests/test_integrations/test_langgraph/conftest.py	268	except Exception:	CODE
LOW	tests/test_integrations/test_langgraph/conftest.py	697	except Exception:	CODE
LOW	…ns/test_langgraph/apps/langgraph_multiple_tools_app.py	69	except Exception as e:	CODE
LOW	…ns/test_langgraph/apps/langgraph_parallel_tools_app.py	80	except Exception:	CODE
LOW	tests/test_integrations/test_openai_agents/conftest.py	17	except Exception:	CODE
LOW	…est_integrations/test_openai_agents/apps/tool_agent.py	35	except Exception:	CODE
LOW⚡	tests/test_integrations/test_langchain/conftest.py	120	except Exception:	CODE
LOW	tests/test_integrations/test_langchain/conftest.py	199	except Exception:	CODE
LOW	tests/test_integrations/test_langchain/conftest.py	224	except Exception:	CODE
LOW	tests/test_integrations/test_langchain/conftest.py	459	except Exception:	CODE
LOW	…ntegrations/test_langchain/apps/langchain_agent_app.py	39	except Exception as e:	CODE
LOW	…test_langchain/apps/langchain_metric_collection_app.py	34	except Exception as e:	CODE
LOW	…ns/test_langchain/apps/langchain_parallel_tools_app.py	63	except Exception:	CODE
LOW	…ns/test_langchain/apps/langchain_multiple_tools_app.py	68	except Exception as e:	CODE
LOW	tests/test_core/conftest.py	7	except Exception:	CODE
LOW	tests/test_core/conftest.py	194	except Exception:	CODE
LOW	tests/test_core/test_sqlite_store.py	630	except Exception as e: # pragma: no cover	CODE
LOW	…racing/test_integration/test_current_golden_context.py	76	except Exception:	CODE
LOW	…racing/test_integration/test_current_golden_context.py	104	except Exception:	CODE
LOW	tests/test_core/test_tracing/apps/sync_app.py	39	except Exception as e:	CODE
LOW	tests/test_core/test_tracing/apps/sync_app.py	65	except Exception:	CODE
LOW	tests/test_core/test_tracing/apps/sync_app.py	84	except Exception:	CODE
LOW	tests/test_core/test_tracing/apps/sync_app.py	101	except Exception:	CODE
LOW	tests/test_core/test_tracing/apps/sync_app.py	134	except Exception as e:	CODE
LOW	tests/test_core/test_tracing/apps/sync_app.py	159	except Exception as e:	CODE
LOW	tests/test_core/test_tracing/apps/sync_app.py	222	except Exception as e:	CODE
LOW	tests/test_core/test_tracing/apps/sync_app.py	270	except Exception:	STRING
MEDIUM	…acing/test_generators/test_generator_context_safety.py	187	def consume(g):	CODE
LOW	…acing/test_generators/test_generator_context_safety.py	191	except Exception as e:	CODE
LOW	tests/test_core/test_evaluation/test_local_store.py	150	except Exception as e: # pragma: no cover	CODE
MEDIUM	…re/test_evaluation/test_execute/test_error_boundary.py	121	def parent_catches():	CODE
LOW	…re/test_evaluation/test_execute/test_error_boundary.py	442	except Exception:	CODE
LOW	…re/test_evaluation/test_execute/test_error_boundary.py	481	except Exception:	CODE
LOW	…s/test_core/test_synthesizer/test_context_generator.py	552	except Exception:	CODE
LOW	…ent-skills/deepeval-otel/references/span-attributes.md	46	except Exception as e:	CODE
LOW	…skills/deepeval-otel/templates/confident_otel_setup.py	100	except Exception as exc: # pragma: no cover - example only	CODE
LOW	.scripts/changelog/release_notes.py	327	except Exception as exc:	STRING
LOW	.scripts/changelog/generate.py	584	except Exception as e:	STRING
LOW	.scripts/changelog/generate.py	1002	except Exception as e:	STRING
LOW	.scripts/changelog/generate.py	1149	except Exception as e:	STRING
LOW	.scripts/changelog/generate.py	1178	except Exception:	STRING
LOW	.scripts/changelog/generate.py	1458	except Exception as e:	CODE
LOW	scripts/check_openai_model_capabilities.py	89	except Exception as exc:	CODE
LOW	scripts/check_openai_model_capabilities.py	119	except Exception as exc:	CODE
MEDIUM	deepeval/utils.py	485	print(f"An error occurred: {e}")	CODE
MEDIUM	deepeval/utils.py	209	def get_or_create_event_loop() -> asyncio.AbstractEventLoop:	CODE
LOW	deepeval/utils.py	484	except Exception as e:	CODE
LOW	deepeval/utils.py	831	except Exception:	CODE
LOW	deepeval/utils.py	857	except Exception:	CODE
LOW	deepeval/metrics/indicator.py	156	except Exception as e:	CODE
LOW	deepeval/metrics/indicator.py	357	except Exception as e:	CODE
LOW	deepeval/metrics/indicator.py	430	except Exception as e:	CODE
LOW	…l/metrics/agent_loop_detection/agent_loop_detection.py	306	except Exception:	CODE
LOW	deepeval/metrics/utils/generation.py	45	except Exception as e:	CODE
LOW	deepeval/metrics/utils/system_one.py	241	except Exception as e: # noqa: BLE001 - only the overflow is rewrapped	CODE
LOW	deepeval/metrics/utils/system_one.py	252	except Exception as e: # noqa: BLE001 - only the overflow is rewrapped	CODE
LOW	deepeval/metrics/utils/decision.py	196	except Exception: # SDK optional	CODE
318 more matches not shown…

Cross-Language Confusion59 hits · 258 pts

Severity	File	Line	Snippet	Context
HIGH	tests/test_metrics/test_json_correctness_metric.py	30	actual_output="{'name': null}",	CODE
HIGH	tests/test_metrics/test_json_correctness_metric.py	56	actual_output="{'name': null}",	CODE
HIGH	tests/test_metrics/test_json_correctness_metric.py	150	actual_output="{'name': null}",	CODE
HIGH⚡	tests/test_confident/test_prompt.py	172	prompt.push(text=f"Latest content {UUID}")	CODE
HIGH⚡	tests/test_confident/test_prompt.py	185	prompt.push(text=f"Version 1 {UUID1}")	CODE
HIGH⚡	tests/test_confident/test_prompt.py	189	prompt.push(text=f"Version 2 {UUID2}")	CODE
HIGH⚡	tests/test_confident/test_prompt.py	898	prompt.push(messages=MESSAGES)	CODE
HIGH⚡	tests/test_confident/test_prompt.py	913	prompt.push(messages=MESSAGES1)	CODE
HIGH⚡	tests/test_confident/test_prompt.py	918	prompt.push(messages=MESSAGES2)	CODE
HIGH	tests/test_confident/test_prompt.py	136	prompt.push(text=TEXT)	CODE
HIGH	tests/test_confident/test_prompt.py	153	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	263	prompt_setup.push(text=f"Setup cache content {uuid.uuid4()}")	CODE
HIGH	tests/test_confident/test_prompt.py	314	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	341	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	370	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	409	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	428	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	447	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	466	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	485	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	507	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	537	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	587	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	620	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	632	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	659	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	694	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	736	prompt1.push(	CODE
HIGH	tests/test_confident/test_prompt.py	767	prompt.push(text="Main branch push")	CODE
HIGH	tests/test_confident/test_prompt.py	771	prompt.push(text="Different branch push", branch=self.BRANCH_NAME)	CODE
HIGH	tests/test_confident/test_prompt.py	855	prompt.push(messages=MESSAGES)	CODE
HIGH	tests/test_confident/test_prompt.py	875	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	1054	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	1084	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	1118	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	1168	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	1221	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	1257	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	1269	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	1299	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	1337	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	1380	prompt1.push(	CODE
HIGH	tests/test_confident/test_prompt.py	1411	prompt.push(	CODE
HIGH	tests/test_confident/test_prompt.py	1417	prompt.push(	CODE
HIGH	tests/test_confident/test_dataset.py	125	dataset.push(alias=self.PUSH_ALIAS)	CODE
HIGH	tests/test_confident/test_dataset.py	165	dataset.push(alias=self.PUSH_ALIAS)	CODE
HIGH	tests/test_confident/test_dataset.py	183	new_dataset.push(alias=self.PUSH_ALIAS, version=version)	CODE
HIGH	tests/test_confident/test_dataset.py	214	dataset.push(alias=self.PUSH_ALIAS)	CODE
HIGH	tests/test_core/test_evaluation/test_expectations.py	967	dataset.push("alias")	CODE
HIGH	…ts/test_core/test_voice/test_connectors/test_webrtc.py	257	source.push(b"\x01\x00" * 960)	CODE
HIGH	.scripts/release.py	112	publish_commands=["cd typescript && npm publish"],	CODE
HIGH	deepeval/prompt/prompt.py	856	return self.push(	CODE
HIGH	…epeval/voice/connectors/providers/livekit/connector.py	527	frames = resampler.push(bytearray(pcm))	CODE
HIGH	…epeval/voice/connectors/providers/livekit/connector.py	666	frames = resampler.push(bytearray(pcm))	CODE
HIGH	…epeval/voice/connectors/providers/livekit/connector.py	692	out = resampler.push(bytearray(pcm))	CODE
HIGH	deepeval/voice/connectors/transports/webrtc.py	611	self._source.push(frame)	CODE
HIGH	deepeval/voice/connectors/transports/webrtc.py	625	self._source.push(frame)	CODE
HIGH	deepeval/simulator/simulation_graph/template.py	40	"index": null,	CODE
HIGH	deepeval/test_run/hyperparameters.py	48	value.push(_verbose=verbose)	CODE

Deep Nesting256 hits · 232 pts

Severity	File	Line	Context
LOW	tests/test_metrics/system_one_fakes.py	93	CODE
LOW	tests/test_metrics/system_one_fakes.py	104	CODE
LOW	tests/test_integrations/utils.py	28	CODE
LOW	tests/test_integrations/utils.py	87	CODE
LOW	tests/test_integrations/utils.py	43	CODE
LOW	tests/test_integrations/utils.py	156	CODE
LOW	tests/test_integrations/utils.py	270	CODE
LOW	tests/test_integrations/test_langgraph/conftest.py	183	CODE
LOW	tests/test_integrations/test_langgraph/conftest.py	214	CODE
LOW	tests/test_integrations/test_langgraph/conftest.py	348	CODE
LOW	…grations/test_openai/test_tool_call_flow_completion.py	66	CODE
LOW	tests/test_integrations/test_langchain/conftest.py	153	CODE
LOW	tests/test_integrations/test_langchain/conftest.py	176	CODE
LOW	…ntegrations/test_langchain/apps/langchain_agent_app.py	66	CODE
LOW	…ntegrations/test_langchain/apps/langchain_agent_app.py	115	CODE
LOW	…rations/test_langchain/apps/langchain_streaming_app.py	56	CODE
LOW	…rations/test_langchain/apps/langchain_streaming_app.py	101	CODE
LOW	…rations/test_langchain/apps/langchain_streaming_app.py	146	CODE
LOW	…rations/test_langchain/apps/langchain_streaming_app.py	191	CODE
LOW	…ns/test_langchain/apps/langchain_parallel_tools_app.py	86	CODE
LOW	…ns/test_langchain/apps/langchain_parallel_tools_app.py	131	CODE
LOW	…ns/test_langchain/apps/langchain_multiple_tools_app.py	86	CODE
LOW	…ns/test_langchain/apps/langchain_multiple_tools_app.py	131	CODE
LOW	…tions/test_langchain/apps/langchain_conditional_app.py	68	CODE
LOW	…tions/test_langchain/apps/langchain_conditional_app.py	113	CODE
LOW	…tions/test_langchain/apps/langchain_single_tool_app.py	35	CODE
LOW	…tions/test_langchain/apps/langchain_single_tool_app.py	84	CODE
LOW	tests/test_confident/test_dataset.py	72	CODE
LOW	tests/test_core/stubs.py	119	CODE
LOW	tests/test_core/stubs.py	125	CODE
LOW	tests/test_core/test_config/test_settings.py	312	CODE
LOW	…re/test_evaluation/test_execute/test_error_boundary.py	436	CODE
LOW	.scripts/release.py	376	CODE
LOW	.scripts/changelog/release_notes.py	111	CODE
LOW	.scripts/changelog/generate.py	866	CODE
LOW	.scripts/changelog/generate.py	895	CODE
LOW	.scripts/changelog/generate.py	961	CODE
LOW	.scripts/changelog/generate.py	1070	CODE
LOW	.scripts/changelog/generate.py	1246	CODE
LOW	.scripts/changelog/generate.py	1297	CODE
LOW	examples/mcp_evaluation/mcp_eval_multi_turn.py	59	CODE
LOW	scripts/compile_metric_templates.py	73	CODE
LOW	deepeval/progress_context.py	39	CODE
LOW	deepeval/utils.py	139	CODE
LOW	deepeval/utils.py	449	CODE
LOW	deepeval/utils.py	464	CODE
LOW	deepeval/metrics/indicator.py	92	CODE
LOW	deepeval/metrics/indicator.py	174	CODE
LOW	deepeval/metrics/indicator.py	373	CODE
LOW	deepeval/metrics/tool_use/tool_use.py	373	CODE
LOW	deepeval/metrics/summarization/summarization.py	304	CODE
LOW	deepeval/metrics/dag/utils.py	63	CODE
LOW	deepeval/metrics/dag/utils.py	104	CODE
LOW	deepeval/metrics/dag/nodes.py	430	CODE
LOW	deepeval/metrics/conversational_dag/nodes.py	490	CODE
LOW	deepeval/metrics/conversational_dag/nodes.py	45	CODE
LOW	deepeval/metrics/utils/models.py	195	CODE
LOW	deepeval/metrics/utils/models.py	331	CODE
LOW	deepeval/metrics/utils/test_case.py	35	CODE
LOW	deepeval/metrics/utils/test_case.py	121	CODE
196 more matches not shown…

Modern Structural Boilerplate187 hits · 192 pts

Severity	File	Line	Snippet	Context
LOW⚡	tests/test_core/stubs.py	28	def update_metric_data(self, args, *kwargs) -> None: ...	CODE
LOW⚡	tests/test_core/stubs.py	29	def update_status(self, args, *kwargs) -> None: ...	CODE
LOW⚡	tests/test_core/stubs.py	30	def update_run_duration(self, args, *kwargs) -> None: ...	CODE
LOW⚡	tests/test_core/test_stubs_contract.py	144	def update_metric_data(self, args, *kwargs) -> None:	CODE
LOW⚡	tests/test_core/test_stubs_contract.py	147	def update_status(self, args, *kwargs) -> None:	CODE
LOW⚡	tests/test_core/test_stubs_contract.py	150	def update_run_duration(self, args, *kwargs) -> None:	CODE
LOW	deepeval/__init__.py	95	__all__ = [	CODE
LOW	deepeval/key_handler.py	14	logger = logging.getLogger(__name__)	CODE
LOW	deepeval/metrics/indicator.py	26	logger = logging.getLogger(__name__)	CODE
LOW	deepeval/metrics/__init__.py	88	__all__ = [	CODE
LOW	deepeval/metrics/turn_contextual_relevancy/__init__.py	6	__all__ = ["TurnContextualRelevancyMetric", "TurnContextualRelevancyTemplate"]	CODE
LOW	deepeval/metrics/tool_use/__init__.py	3	__all__ = ["ToolUseMetric", "ToolUseTemplate"]	CODE
LOW	deepeval/metrics/conversational_g_eval/__init__.py	6	__all__ = ["ConversationalGEval", "ConversationalGEvalTemplate"]	CODE
LOW	deepeval/metrics/hallucination/__init__.py	3	__all__ = ["HallucinationMetric", "HallucinationTemplate"]	CODE
LOW	deepeval/metrics/step_efficiency/__init__.py	3	__all__ = ["StepEfficiencyMetric", "StepEfficiencyTemplate"]	CODE
LOW	deepeval/metrics/role_violation/__init__.py	3	__all__ = ["RoleViolationMetric", "RoleViolationTemplate"]	CODE
LOW	deepeval/metrics/tool_permission/__init__.py	3	__all__ = ["ToolPermissionMetric"]	CODE
LOW	deepeval/metrics/conversational_jev_eval/__init__.py	3	__all__ = ["ConversationalJevEval"]	CODE
LOW	deepeval/metrics/task_completion/__init__.py	3	__all__ = ["TaskCompletionMetric", "TaskCompletionTemplate"]	CODE
LOW	deepeval/metrics/contextual_precision/__init__.py	6	__all__ = ["ContextualPrecisionMetric", "ContextualPrecisionTemplate"]	CODE
LOW	deepeval/metrics/summarization/__init__.py	3	__all__ = ["SummarizationMetric", "SummarizationTemplate"]	CODE
LOW	deepeval/metrics/misuse/__init__.py	3	__all__ = ["MisuseMetric", "MisuseTemplate"]	CODE
LOW	deepeval/metrics/dag/serialization/__init__.py	9	__all__ = [	CODE
LOW	deepeval/metrics/plan_adherence/__init__.py	3	__all__ = ["PlanAdherenceMetric", "PlanAdherenceTemplate"]	CODE
LOW	deepeval/metrics/knowledge_retention/__init__.py	6	__all__ = ["KnowledgeRetentionMetric", "KnowledgeRetentionTemplate"]	CODE
LOW	deepeval/metrics/pii_leakage/__init__.py	3	__all__ = ["PIILeakageMetric", "PIILeakageTemplate"]	CODE
LOW	deepeval/metrics/transcription_accuracy/__init__.py	6	__all__ = ["TranscriptionAccuracyMetric", "TranscriptionAccuracyTemplate"]	CODE
LOW	deepeval/metrics/jev_eval/__init__.py	4	__all__ = [	CODE
LOW	deepeval/metrics/mcp_use_metric/__init__.py	3	__all__ = ["MCPUseMetric", "MCPUseTemplate"]	CODE
LOW	deepeval/metrics/utils/__init__.py	113	__all__ = [	CODE
LOW	deepeval/metrics/utils/system_one_batch.py	275	def _settle(request: _Request, result: Any, ignore_errors: bool) -> None:	CODE
LOW	deepeval/metrics/mcp/__init__.py	6	__all__ = ["MCPTaskCompletionMetric", "MCPTaskCompletionTemplate"]	CODE
LOW	deepeval/metrics/g_eval/__init__.py	4	__all__ = ["Rubric", "GEval", "GEvalTemplate"]	CODE
LOW	deepeval/metrics/topic_adherence/__init__.py	3	__all__ = ["TopicAdherenceMetric", "TopicAdherenceTemplate"]	CODE
LOW	deepeval/metrics/toxicity/__init__.py	3	__all__ = ["ToxicityMetric", "ToxicityTemplate"]	CODE
LOW	deepeval/metrics/faithfulness/__init__.py	3	__all__ = ["FaithfulnessMetric", "FaithfulnessTemplate"]	CODE
LOW	deepeval/metrics/answer_relevancy/__init__.py	3	__all__ = ["AnswerRelevancyMetric", "AnswerRelevancyTemplate"]	CODE
LOW	deepeval/metrics/turn_faithfulness/__init__.py	3	__all__ = ["TurnFaithfulnessMetric", "TurnFaithfulnessTemplate"]	CODE
LOW	deepeval/metrics/goal_accuracy/__init__.py	3	__all__ = ["GoalAccuracyMetric", "GoalAccuracyTemplate"]	CODE
LOW	…l/metrics/multimodal_metrics/image_editing/__init__.py	3	__all__ = ["ImageEditingMetric", "ImageEditingTemplate"]	CODE
LOW	…l/metrics/multimodal_metrics/text_to_image/__init__.py	3	__all__ = ["TextToImageMetric", "TextToImageTemplate"]	CODE
LOW	…metrics/multimodal_metrics/image_coherence/__init__.py	3	__all__ = ["ImageCoherenceMetric", "ImageCoherenceTemplate"]	CODE
LOW	…metrics/multimodal_metrics/image_reference/__init__.py	3	__all__ = ["ImageReferenceMetric", "ImageReferenceTemplate"]	CODE
LOW	…trics/multimodal_metrics/image_helpfulness/__init__.py	3	__all__ = ["ImageHelpfulnessMetric", "ImageHelpfulnessTemplate"]	CODE
LOW	deepeval/metrics/turn_contextual_recall/__init__.py	6	__all__ = ["TurnContextualRecallMetric", "TurnContextualRecallTemplate"]	CODE
LOW	deepeval/metrics/contextual_recall/__init__.py	3	__all__ = ["ContextualRecallMetric", "ContextualRecallTemplate"]	CODE
LOW	deepeval/metrics/voice/__init__.py	9	__all__ = [	CODE
LOW	deepeval/metrics/tool_correctness/__init__.py	3	__all__ = ["ToolCorrectnessMetric", "ToolCorrectnessTemplate"]	CODE
LOW	deepeval/metrics/json_correctness/__init__.py	3	__all__ = ["JsonCorrectnessMetric", "JsonCorrectnessTemplate"]	CODE
LOW	deepeval/metrics/argument_correctness/__init__.py	6	__all__ = ["ArgumentCorrectnessMetric", "ArgumentCorrectnessTemplate"]	CODE
LOW	deepeval/metrics/arena_g_eval/__init__.py	3	__all__ = ["ArenaGEval", "ArenaGEvalTemplate"]	CODE
LOW	deepeval/metrics/bias/__init__.py	3	__all__ = ["BiasMetric", "BiasTemplate"]	CODE
LOW	deepeval/metrics/plan_quality/__init__.py	3	__all__ = ["PlanQualityMetric", "PlanQualityTemplate"]	CODE
LOW	deepeval/metrics/community/__init__.py	5	__all__ = [	CODE
LOW	…al/metrics/community/citation_faithfulness/__init__.py	3	__all__ = ["CitationFaithfulnessMetric"]	CODE
LOW	deepeval/metrics/turn_contextual_precision/__init__.py	6	__all__ = ["TurnContextualPrecisionMetric", "TurnContextualPrecisionTemplate"]	CODE
LOW	deepeval/metrics/role_adherence/__init__.py	3	__all__ = ["RoleAdherenceMetric", "RoleAdherenceTemplate"]	CODE
LOW	deepeval/metrics/contextual_relevancy/__init__.py	6	__all__ = ["ContextualRelevancyMetric", "ContextualRelevancyTemplate"]	CODE
LOW	deepeval/metrics/non_advice/__init__.py	3	__all__ = ["NonAdviceMetric", "NonAdviceTemplate"]	CODE
LOW	deepeval/metrics/conversation_completeness/__init__.py	6	__all__ = ["ConversationCompletenessMetric", "ConversationCompletenessTemplate"]	CODE
127 more matches not shown…

Self-Referential Comments43 hits · 135 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/test_integrations/test_exporter/readable_spans.py	5	# Create a simple span context	COMMENT
MEDIUM	tests/test_integrations/test_exporter/readable_spans.py	13	# Create the ReadableSpan with one attribute	COMMENT
MEDIUM	tests/test_integrations/test_exporter/readable_spans.py	184	# Create a multi-turn span context	COMMENT
MEDIUM	tests/test_integrations/test_exporter/readable_spans.py	192	# Create the multi-turn readable span	COMMENT
MEDIUM⚡	…t_integrations/test_crewai/test_knowledge_retriever.py	18	# Create a knowledge source	COMMENT
MEDIUM⚡	…t_integrations/test_crewai/test_knowledge_retriever.py	24	# Create an LLM with a temperature of 0 to ensure deterministic outputs	COMMENT
MEDIUM⚡	…t_integrations/test_crewai/test_knowledge_retriever.py	27	# Create an agent with the knowledge store	COMMENT
MEDIUM	tests/test_integrations/test_langgraph/conftest.py	79	# Create a unique identifier for this test run	COMMENT
MEDIUM	…test_langgraph/apps/langgraph_metric_collection_app.py	19	# Create a Prompt object for prompt tracking	COMMENT
MEDIUM	…grations/test_openai_agents/test_scenerios/test_run.py	63	# Create the weather specialist agent	COMMENT
MEDIUM	…i_agents/test_scenerios/test_with_trace_and_wrapped.py	82	# Create the weather specialist agent	COMMENT
MEDIUM	…s/test_openai_agents/test_scenerios/test_with_trace.py	65	# Create the weather specialist agent	COMMENT
MEDIUM	…ons/test_openai_agents/test_scenerios/test_run_sync.py	62	# Create the weather specialist agent	COMMENT
MEDIUM	…ai_agents/test_scenerios/test_weather_agent_patched.py	78	# Create the weather specialist agent	COMMENT
MEDIUM	…test_openai_agents/test_scenerios/test_run_streamed.py	63	# Create the weather specialist agent	COMMENT
MEDIUM	tests/test_integrations/test_langchain/conftest.py	58	# Create a unique identifier for this test run	COMMENT
MEDIUM	…test_langchain/apps/langchain_metric_collection_app.py	16	# Create a Prompt object for prompt tracking	COMMENT
MEDIUM	tests/test_core/stubs.py	189	# Define the mock types	COMMENT
MEDIUM	tests/test_core/test_models/test_openai_model.py	166	# Create a mock parsed response	COMMENT
MEDIUM	tests/test_core/test_models/test_openai_model.py	215	# Create a mock that tracks the call arguments	COMMENT
MEDIUM	tests/test_core/test_models/test_openai_model.py	263	# Create a mock parsed response	COMMENT
MEDIUM	tests/test_core/test_cli/test_cli.py	752	# Create a real JSON file (with whitespace) so we can verify normalization.	COMMENT
MEDIUM⚡	…agent_evals/test_langgraph/test_langgraph_component.py	12	# Define the tool	COMMENT
MEDIUM	…ocs/test_confident/test_integrations/test_langgraph.py	23	# Create a metric	COMMENT
MEDIUM	deepeval/metrics/ragas.py	76	# Create a dataset from the test case	COMMENT
MEDIUM	deepeval/metrics/ragas.py	519	# Create a dataset from the test case	COMMENT
MEDIUM	deepeval/tracing/tracing.py	605	# Create a new event loop	COMMENT
MEDIUM	deepeval/tracing/tracing.py	981	# Create the base API span	COMMENT
MEDIUM	deepeval/synthesizer/synthesizer.py	1876	# Create the pandas DataFrame	COMMENT
MEDIUM	deepeval/benchmarks/math_qa/math_qa.py	144	# Create a DataFrame from task_results_data	COMMENT
MEDIUM	deepeval/benchmarks/bbq/bbq.py	106	# Create a DataFrame from task_results_data	COMMENT
MEDIUM	deepeval/benchmarks/human_eval/human_eval.py	21	# Create a restricted globals dictionary with only safe built-ins	COMMENT
MEDIUM	deepeval/benchmarks/human_eval/human_eval.py	160	# Create a DataFrame from task_results_data	COMMENT
MEDIUM	deepeval/benchmarks/logi_qa/logi_qa.py	146	# Create a DataFrame from task_results_data	COMMENT
MEDIUM	deepeval/benchmarks/drop/drop.py	153	# Create a DataFrame from task_results_data	COMMENT
MEDIUM	deepeval/benchmarks/truthful_qa/truthful_qa.py	155	# Create a DataFrame from task_results_data	COMMENT
MEDIUM	deepeval/benchmarks/big_bench_hard/big_bench_hard.py	178	# Create a DataFrame from task_results_data	COMMENT
MEDIUM	deepeval/benchmarks/squad/squad.py	147	# Create a DataFrame from task_results_data	COMMENT
MEDIUM	deepeval/benchmarks/mmlu/mmlu.py	145	# Create a DataFrame from task_results_data	COMMENT
MEDIUM	deepeval/benchmarks/equity_med_qa/equity_med_qa.py	88	# Create a DataFrame from task_results_data	COMMENT
MEDIUM	deepeval/benchmarks/hellaswag/hellaswag.py	149	# Create a DataFrame from task_results_data	COMMENT
MEDIUM	deepeval/test_run/test_run.py	391	# Create a single TraceMetricScores object instead of a list	COMMENT
MEDIUM	deepeval/test_run/hyperparameters.py	72	# Define the wrapper function that will be the actual decorator	COMMENT

AI Structural Patterns127 hits · 120 pts

Severity	File	Line	Context
LOW	tests/test_integrations/test_langgraph/apps/main.py	167	CODE
LOW	…ts/test_core/test_tracing/test_masking/test_masking.py	33	CODE
LOW	…re/test_tracing/test_nested_spans/test_nested_spans.py	22	CODE
LOW	…re/test_tracing/test_nested_spans/test_nested_spans.py	77	CODE
LOW	tests/test_core/test_tracing/apps/async_app.py	56	CODE
LOW	…_agent_evals/test_langchain/test_langchain_e2e_sync.py	56	CODE
LOW	…ocs/test_confident/test_integrations/test_anthropic.py	22	CODE
LOW	…ocs/test_confident/test_integrations/test_anthropic.py	42	CODE
LOW	…t_docs/test_confident/test_integrations/test_openai.py	18	CODE
LOW	…t_docs/test_confident/test_integrations/test_openai.py	39	CODE
LOW	…est_confident/test_tracing_features/test_span_types.py	107	CODE
LOW	.scripts/changelog/generate.py	1070	CODE
LOW	…turn_contextual_relevancy/turn_contextual_relevancy.py	85	CODE
LOW	deepeval/metrics/tool_use/tool_use.py	66	CODE
LOW	…metrics/conversational_g_eval/conversational_g_eval.py	47	CODE
LOW	deepeval/metrics/hallucination/hallucination.py	48	CODE
LOW	deepeval/metrics/step_efficiency/step_efficiency.py	48	CODE
LOW	deepeval/metrics/role_violation/role_violation.py	46	CODE
LOW	…ics/conversational_jev_eval/conversational_jev_eval.py	37	CODE
LOW	deepeval/metrics/task_completion/task_completion.py	54	CODE
LOW	…l/metrics/contextual_precision/contextual_precision.py	66	CODE
LOW	…l/metrics/agent_loop_detection/agent_loop_detection.py	119	CODE
LOW	deepeval/metrics/summarization/summarization.py	58	CODE
LOW	deepeval/metrics/misuse/misuse.py	48	CODE
LOW	deepeval/metrics/dag/dag.py	27	CODE
LOW	deepeval/metrics/plan_adherence/plan_adherence.py	56	CODE
LOW	…val/metrics/knowledge_retention/knowledge_retention.py	41	CODE
LOW	deepeval/metrics/pii_leakage/pii_leakage.py	47	CODE
LOW	…trics/transcription_accuracy/transcription_accuracy.py	81	CODE
LOW	…peval/metrics/conversational_dag/conversational_dag.py	26	CODE
LOW	deepeval/metrics/jev_eval/jev_eval.py	48	CODE
LOW	deepeval/metrics/mcp_use_metric/mcp_use_metric.py	61	CODE
LOW	deepeval/metrics/mcp/mcp_task_completion.py	52	CODE
LOW	deepeval/metrics/mcp/multi_turn_mcp_use_metric.py	58	CODE
LOW	deepeval/metrics/g_eval/g_eval.py	54	CODE
LOW	deepeval/metrics/topic_adherence/topic_adherence.py	47	CODE
LOW	deepeval/metrics/toxicity/toxicity.py	49	CODE
LOW	deepeval/metrics/faithfulness/faithfulness.py	73	CODE
LOW	deepeval/metrics/answer_relevancy/answer_relevancy.py	47	CODE
LOW	deepeval/metrics/turn_faithfulness/turn_faithfulness.py	63	CODE
LOW	deepeval/metrics/goal_accuracy/goal_accuracy.py	62	CODE
LOW	…/multimodal_metrics/image_coherence/image_coherence.py	34	CODE
LOW	…/multimodal_metrics/image_reference/image_reference.py	35	CODE
LOW	…timodal_metrics/image_helpfulness/image_helpfulness.py	35	CODE
LOW	…trics/turn_contextual_recall/turn_contextual_recall.py	81	CODE
LOW	deepeval/metrics/contextual_recall/contextual_recall.py	81	CODE
LOW	deepeval/metrics/tool_correctness/tool_correctness.py	51	CODE
LOW	deepeval/metrics/json_correctness/json_correctness.py	36	CODE
LOW	…l/metrics/argument_correctness/argument_correctness.py	47	CODE
LOW	deepeval/metrics/bias/bias.py	48	CODE
LOW	deepeval/metrics/plan_quality/plan_quality.py	56	CODE
LOW	…mmunity/citation_faithfulness/citation_faithfulness.py	62	CODE
LOW	…turn_contextual_precision/turn_contextual_precision.py	72	CODE
LOW	deepeval/metrics/role_adherence/role_adherence.py	43	CODE
LOW	…l/metrics/contextual_relevancy/contextual_relevancy.py	93	CODE
LOW	deepeval/metrics/non_advice/non_advice.py	50	CODE
LOW	…conversation_completeness/conversation_completeness.py	46	CODE
LOW	deepeval/metrics/turn_relevancy/turn_relevancy.py	44	CODE
LOW	deepeval/metrics/prompt_alignment/prompt_alignment.py	49	CODE
LOW	deepeval/tracing/trace_context.py	46	CODE
67 more matches not shown…

Modern AI Meta-Vocabulary29 hits · 96 pts

Severity	File	Line	Snippet	Context
MEDIUM	typescript/src/metrics/README.md	347	### Trace metrics (agentic)	COMMENT
MEDIUM	typescript/src/evaluate/trace-eval.ts	196	// agentic executor passes for both scopes. Published rather than threaded	COMMENT
MEDIUM⚡	tests/test_integrations/test_llamaindex/test_sync.py	67	# RAG APP TESTS	COMMENT
MEDIUM⚡	tests/test_integrations/test_llamaindex/test_async.py	84	# ASYNC RAG APP TESTS	COMMENT
MEDIUM	…test_integrations/test_crewai/apps/hierarchical_app.py	23	agent=writer, # In hierarchical, this is the target, but Manager orchestrates	CODE
MEDIUM	tests/test_integrations/test_langgraph/conftest.py	599	context=context, # None - not a RAG app	CODE
MEDIUM	tests/test_integrations/test_langgraph/conftest.py	600	retrievalContext=retrieval_context, # None - not a RAG app	CODE
MEDIUM⚡	tests/test_integrations/test_langgraph/test_sync.py	554	# RETRIEVER (RAG) TESTS	COMMENT
MEDIUM	…rations/test_langgraph/apps/langgraph_retriever_app.py	111	# Create augmented prompt with system message for RAG	COMMENT
MEDIUM⚡	tests/test_integrations/test_langchain/test_sync.py	428	# RETRIEVER (RAG) TESTS	COMMENT
MEDIUM⚡	tests/test_integrations/test_langchain/test_async.py	436	# ASYNC RETRIEVER (RAG) TESTS	COMMENT
MEDIUM	…rations/test_langchain/apps/langchain_retriever_app.py	97	# Create augmented prompt with system message for RAG	COMMENT
MEDIUM	…rations/test_langchain/apps/langchain_retriever_app.py	142	# Create augmented prompt with system message for RAG	COMMENT
MEDIUM	…rations/test_langchain/apps/langchain_retriever_app.py	206	# Create augmented prompt with system message for RAG	COMMENT
MEDIUM	tests/test_core/test_imports.py	19	# RAG metrics	COMMENT
MEDIUM	tests/test_core/test_synthesizer_bugs.py	506	# The few-shot example must demonstrate the new key.	COMMENT
MEDIUM	tests/test_core/test_synthesizer_bugs.py	541	# The few-shot example must demonstrate the new key.	COMMENT
MEDIUM	…_core/test_evaluation/test_trace_results_extraction.py	68	# Monkeypatch create_api_trace in the agentic submodule where	COMMENT
MEDIUM	…ocs/test_deepeval/test_llm_evals/test_setup_tracing.py	71	# Calls RAG pipeline	COMMENT
MEDIUM	…ocs/test_deepeval/test_llm_evals/test_setup_tracing.py	77	# Generate final response incorporating both RAG and search results	COMMENT
MEDIUM	…est_confident/test_tracing_features/test_span_types.py	98	# Custom span wrapping the RAG pipeline	COMMENT
MEDIUM⚡	…est_confident/test_tracing_features/test_span_types.py	110	# Agent that does RAG + tool calling	COMMENT
MEDIUM⚡	…est_confident/test_tracing_features/test_span_types.py	113	# Call RAG pipeline	COMMENT
MEDIUM⚡	…est_confident/test_tracing_features/test_span_types.py	119	# Generate final response incorporating both RAG and search results	COMMENT
MEDIUM	docs/lib/source.ts	161	// Backwards-compatible alias so scaffold-generated routes that still import	COMMENT
MEDIUM	deepeval/metrics/__init__.py	107	# RAG metrics	COMMENT
MEDIUM	deepeval/test_case/conversational_test_case.py	83	# RAG & tools	COMMENT
MEDIUM	deepeval/evaluate/execute/__init__.py	28	# agentic	COMMENT
MEDIUM	deepeval/evaluate/execute/loop.py	448	# parent. Mirrors the async path in ``agentic.py``.	COMMENT

Over-Commented Block74 hits · 72 pts

Severity	File	Line	Snippet	Context
LOW	typescript/test/test-core/tracing.test.ts	81	return response;	COMMENT
LOW	typescript/test/test-core/tracing.test.ts	101	// toolsCalled: [toolCall],	COMMENT
LOW	typescript/test/test-core/tracing.test.ts	121	// query: "test query",	COMMENT
LOW	typescript/examples/tracing/example-quickstart.ts	1	import OpenAI from "openai";	COMMENT
LOW	typescript/examples/dataset/example-dataset.ts	1	// /**	COMMENT
LOW	typescript/examples/dataset/example-dataset.ts	21	// // Option 2: Import from specific submodules	COMMENT
LOW	typescript/examples/dataset/example-dataset.ts	41	// filePath: csvFilePath,	COMMENT
LOW	typescript/examples/dataset/example-dataset.ts	61	// );	COMMENT
LOW	typescript/examples/dataset/example-dataset.ts	81	// actualOutput: "H2O",	COMMENT
LOW	typescript/examples/dataset/example-dataset.ts	101	// expectedOutput: "H2O",	COMMENT
LOW	typescript/examples/dataset/example-dataset.ts	121	// );	COMMENT
LOW	typescript/examples/dataset/example-dataset.ts	141	// // Create a new dataset for pushing	COMMENT
LOW	typescript/examples/dataset/example-dataset.ts	161	// retrievalContext: [	COMMENT
LOW	typescript/examples/dataset/example-dataset.ts	181	// if (error.message && error.message.includes("deepeval login")) {	COMMENT
LOW	typescript/examples/dataset/example-dataset.ts	201	// autoConvertGoldensToTestCases: false,	COMMENT
LOW	typescript/examples/dataset/example-dataset.ts	221	// }	COMMENT
LOW	typescript/src/metrics/jev-eval/questions.ts	1	// The three decision points a JevEval metric is built from.	COMMENT
LOW	typescript/src/metrics/system-one/decision.ts	1	// System One (Jev) plumbing shared by every metric's decision points.	COMMENT
LOW	typescript/src/metrics/system-one/batch.ts	1	// Batched System One for `evaluate()`: every metric Jev judges on a test case,	COMMENT
LOW	typescript/src/metrics/system-one/runner.ts	1	// The whole-chain System One path for built-in metrics (`system_one` eval	COMMENT
LOW	typescript/src/config/eval-mode.ts	1	// Resolves who decides in an LLM-as-a-judge metric: `DEEPEVAL_EVAL_MODE`.	COMMENT
LOW	typescript/src/integrations/langchain/patch-tool.ts	1	// import { tool as originalTool } from "@langchain/core/tools";	COMMENT
LOW	typescript/src/integrations/langchain/patch-tool.ts	21	// metrics = kwargs.metrics;	COMMENT
LOW	typescript/src/integrations/langchain/patch-tool.ts	41	// }	COMMENT
LOW	typescript/src/integrations/langchain/patch-tool.ts	61	// try {	COMMENT
LOW	typescript/src/sqlite-store/store.ts	1	// SQLite storage for deepeval test runs (opt-in via `DEEPEVAL_LOCAL_STORE=sqlite`).	COMMENT
LOW	…_integrations/test_pydanticai/test_span_interceptor.py	841	from deepeval.integrations.pydantic_ai.instrumentator import (	COMMENT
LOW	tests/test_confident/test_dataset.py	221		COMMENT
LOW	…i_agent_evals/test_pydanticai/test_pydanticai_setup.py	21	# result = await agent.run("What are the LLMs?")	COMMENT
LOW	…_deepeval/test_llm_evals/test_component_level_evals.py	61	# dataset.evaluate(task)	COMMENT
LOW	docs/source.config.ts	141	rehypePlugins: (v) => [rehypeKatex, ...v],	COMMENT
LOW	docs/app/layout.tsx	61	description: siteDescription,	COMMENT
LOW	docs/lib/layout.shared.tsx	81	// `links` intentionally omitted — text items live in `navLinks`	COMMENT
LOW	…ts/MetricTagsDisplayer/MetricTagsDisplayer.module.scss	1	// Metric classification tags shown under each metric's H1. Each variant	COMMENT
LOW	examples/tracing/test_chatbot.py	1	# from deepeval.tracing import trace, TraceType	COMMENT
LOW	examples/tracing/test_chatbot.py	21	# ],	COMMENT
LOW	examples/tracing/test_chatbot.py	41	# def retriever(self, input=input):	COMMENT
LOW	examples/tracing/test_chatbot.py	61		COMMENT
LOW	examples/tracing/test_chatbot.py	81	# "Be at least 35 years old.",	COMMENT
LOW	deepeval/metrics/base_metric.py	21	from deepeval.metrics.utils.system_one import SystemOneEvalSpec	COMMENT
LOW	deepeval/metrics/ragas.py	261	# class RAGASNoiseSensitivityMetric(BaseMetric):	COMMENT
LOW	deepeval/metrics/ragas.py	281	# try:	COMMENT
LOW	deepeval/metrics/ragas.py	301		COMMENT
LOW	deepeval/metrics/utils/qag.py	41	)	COMMENT
LOW	deepeval/metrics/utils/decision.py	41	)	COMMENT
LOW	deepeval/metrics/utils/decision.py	61	###############################################	COMMENT
LOW	deepeval/tracing/types.py	201	turn_id: Optional[str] = Field(None, serialization_alias="turnId")	COMMENT
LOW	deepeval/tracing/context.py	281	# ---------------------------------------------------------------------------	COMMENT
LOW	deepeval/tracing/otel/exporter.py	201	# When inside an active deepeval trace context, the wrapping	COMMENT
LOW	deepeval/config/settings.py	1041	# Async Task Configuration	COMMENT
LOW	deepeval/openai_agents/runner.py	1	# from __future__ import annotations	COMMENT
LOW	deepeval/openai_agents/runner.py	21	# from agents.models.interface import Model	COMMENT
LOW	deepeval/openai_agents/runner.py	41	# # Import observed provider/model helpers from our agent module	COMMENT
LOW	deepeval/openai_agents/runner.py	61		COMMENT
LOW	deepeval/openai_agents/runner.py	81	# patched_get_model.__doc__ = original_get_model.__doc__	COMMENT
LOW	deepeval/openai_agents/runner.py	101	# context: Optional[TContext] = None,	COMMENT
LOW	deepeval/openai_agents/runner.py	121	# span_type="custom",	COMMENT
LOW	deepeval/openai_agents/runner.py	141	# current_span.input = input	COMMENT
LOW	deepeval/openai_agents/runner.py	161	# update_trace_attributes(output=_output)	COMMENT
LOW	deepeval/openai_agents/runner.py	181	# metadata: Optional[dict] = None,	COMMENT
14 more matches not shown…

Docstring Block Structure11 hits · 55 pts

Severity	File	Line	Snippet	Context
HIGH	deepeval/utils.py	915	Ensures that a required parameter is provided. If the parameter is `None`, raises a `DeepEvalError` with a help	STRING
HIGH	deepeval/utils.py	947	Imports an optional dependency module or raises a `DeepEvalError` if the module is not found. The error message	STRING
HIGH	deepeval/dataset/dataset.py	286	Load test cases from a CSV file. This method reads a CSV file, extracting test case data based on spec	STRING
HIGH	deepeval/dataset/dataset.py	431	Load test cases from a JSON file. This method reads a JSON file containing a list of objects, each rep	STRING
HIGH	deepeval/models/utils.py	44	Extract base model name from provider-prefixed format. This function is useful for extracting the actual model name	STRING
HIGH	deepeval/models/utils.py	80	Normalize and validate a provider API key stored as a SecretStr. Args: secret: The SecretS	STRING
HIGH	deepeval/models/retry_policy.py	515	Run a synchronous callable with a soft timeout enforced by a helper thread, with a global cap on concurrent tim	STRING
HIGH	deepeval/scorer/scorer.py	276	Calculate the toxicity score of a given text prediction using the Detoxify model. Args: pr	STRING
HIGH	deepeval/synthesizer/synthesizer.py	1893	Save synthetic goldens to a file. Args: file_type: Type of file to save as ('json' or 'csv').	STRING
HIGH	deepeval/anthropic/utils.py	10	Return a short, human-readable summary string for an Anthropic-style multimodal `content` value. This is used	STRING
HIGH	deepeval/openai/utils.py	42	Return a short, human-readable summary string for an OpenAI-style multimodal `content` value. This is used to	STRING

Redundant / Tautological Comments16 hits · 26 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_integrations/test_langgraph/conftest.py	632	# Print values when present	COMMENT
LOW	…ntegrations/test_langchain/apps/langchain_agent_app.py	82	# Check if we have tool calls	COMMENT
LOW	…ntegrations/test_langchain/apps/langchain_agent_app.py	131	# Check if we have tool calls	COMMENT
LOW	tests/test_core/test_evaluation/test_console_report.py	113	# Check if the aggregate table is built correctly	COMMENT
LOW	tests/test_core/test_evaluation/test_console_report.py	119	# Check if it's a Panel and contains the aggregate metrics table	COMMENT
LOW	…al/test_ai_agent_evals/test_setup_end_to_end_python.py	24	# Loop through dataset	COMMENT
LOW	deepeval/utils.py	418	# Check if obj is iterable (but not a string)	COMMENT
LOW⚡	deepeval/metrics/g_eval/utils.py	193	# Check if both criteria and evaluation_steps are not None at the same time	COMMENT
LOW⚡	deepeval/metrics/g_eval/utils.py	199	# Check if criteria is provided, it cannot be an empty string	COMMENT
LOW⚡	deepeval/metrics/g_eval/utils.py	203	# Check if evaluation_steps is provided, it cannot be an empty list	COMMENT
LOW	deepeval/metrics/g_eval/utils.py	224	# Check if ranges overlap	COMMENT
LOW	deepeval/tracing/tracing.py	590	# Add the trace to the queue	COMMENT
LOW	deepeval/tracing/tracing.py	875	# Add children to the stack for processing	COMMENT
LOW	deepeval/synthesizer/chunking/context_generator.py	341	# Check if chunk_size and max_context_size is valid for document lengths	COMMENT
LOW	deepeval/evaluate/execute/agentic.py	311	# Set it to None to ensure the test_case is added	COMMENT
LOW	deepeval/prompt/prompt.py	520	# Check if we need to bootstrap the cache	COMMENT

Magic Placeholder Names3 hits · 18 pts

Severity	File	Line	Snippet	Context
HIGH	typescript/examples/dataset/example-dataset.ts	188	// console.log("export CONFIDENT_API_KEY='your-api-key-here'");	COMMENT
HIGH	typescript/examples/dataset/example-dataset.ts	233	// console.log("export CONFIDENT_API_KEY='your-api-key-here'");	COMMENT
HIGH	deepeval/models/llms/gemini_model.py	53	api_key="your-api-key"	STRING

AI Slop Vocabulary6 hits · 14 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/test_core/test_tracing/apps/sync_app.py	212	research_prompt = f"""Based on the following retrieved documents, provide a comprehensive research analysis of '	STRING
MEDIUM	docs/src/sections/home/HomeSection.module.scss	100	// Duplicated content length is 200%; shift by half for a seamless loop.	COMMENT
MEDIUM⚡	deepeval/tracing/otel/context_aware_processor.py	138	# Trace-shape testing override: when a test harness has set	COMMENT
LOW	deepeval/dataset/utils.py	328	# already a Task so just return it	COMMENT
LOW	deepeval/dataset/utils.py	332	# If it is a future, it is already scheduled, so just return it	COMMENT
MEDIUM	deepeval/simulator/conversation_simulator.py	700	# up — so the harness's own thinking time is not neutral, it	COMMENT

Fake / Example Data13 hits · 14 pts

Severity	File	Line	Snippet	Context
LOW	typescript/test/test-core/expectations.test.ts	220	process.env.CONFIDENT_API_KEY = "fake-key";	CODE
LOW	typescript/test/test-core/expectations.test.ts	316	process.env.CONFIDENT_API_KEY = "fake-key";	CODE
LOW	typescript/test/test-core/expectations.test.ts	351	process.env.CONFIDENT_API_KEY = "fake-key";	CODE
LOW	…acing/schemas/masking/comprehensive_masked_schema.json	15	"name": "John Doe"	CODE
LOW	…acing/schemas/masking/comprehensive_masked_schema.json	23	"name": "John Doe"	CODE
LOW	…acing/schemas/masking/comprehensive_masked_schema.json	39	"name": "John Doe"	CODE
LOW	…acing/schemas/masking/comprehensive_masked_schema.json	47	"name": "John Doe"	CODE
LOW⚡	…ts/test_core/test_tracing/test_masking/test_masking.py	94	"email": "user@example.com",	CODE
LOW⚡	…ts/test_core/test_tracing/test_masking/test_masking.py	96	"name": "John Doe",	CODE
LOW	…test_tracing/test_configuration/test_masking_config.py	183	return "user@example.com"	CODE
LOW	…test_tracing/test_configuration/test_masking_config.py	186	assert result == "user@example.com" # Function returns original	CODE
LOW⚡	tests/test_core/test_models/test_azure_model.py	603	api_key="fake-key",	CODE
LOW	deepeval/cli/auth/flow.py	36	"email": "user@example.com"}}	STRING

Dead Code3 hits · 6 pts

Severity	File	Line	Context
MEDIUM	deepeval/models/base_model.py	285	CODE
MEDIUM	deepeval/models/base_model.py	359	CODE
MEDIUM	deepeval/voice/connectors/transports/base.py	232	CODE

Cross-Language Confusion (JS/TS)1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	docs/lib/wizard/setup-script.ts	110	elif command -v sha256sum >/dev/null 2>&1; then	CODE

Overly Generic Function Names1 hit · 0 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_integrations/utils.py	441	async def my_function():	STRING

Slop Phrases1 hit · 0 pts

Severity	File	Line	Snippet	Context
LOW⚡	tests/test_core/test_prompts/test_interpolation.py	568	This ensures users don't forget to provide required template variables.	STRING

Maintenance and Governance Review

Risk Review · v3

What These Metrics Mean

Pattern-Signal History

Severity Breakdown

Directory Score Breakdown

Pattern Findings