emcie-co/parlant

15.8

Adjusted Score

15.8

Raw Score

100%

Time Factor

2026-07-12

Last Push

18.2K

Stars

Python

Language

186.1K

Lines of Code

449

Files

2.6K

Pattern Hits

2026-07-14

Scan Date

0.18

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 78MEDIUM 124LOW 2428

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 2632 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.

Hyper-Verbose Identifiers1520 hits · 1318 pts

Severity	File	Line	Snippet	Context
LOW	tests/tool_utilities.py	74	def get_available_product_by_type(product_type: ProductType = ProductType.DRINKS) -> ToolResult:	CODE
LOW	tests/tool_utilities.py	138	def available_products_by_category(category: ProductCategory) -> ToolResult:	CODE
LOW	tests/tool_utilities.py	147	def available_products_by_categories(categories: list[ProductCategory]) -> ToolResult:	CODE
LOW	tests/tool_utilities.py	241	def calculate_expected_salary(	CODE
LOW	tests/tool_utilities.py	252	async def get_electronic_products_by_type(	CODE
LOW	tests/tool_utilities.py	297	async def search_electronic_products(	CODE
LOW	tests/tool_utilities.py	553	def _mock_lookup_credit_limit(username: str) -> Optional[float]:	CODE
LOW	tests/test_utilities.py	290	async def set_context_variable_value(	STRING
LOW	tests/test_utilities.py	404	async def get_when_async_done_or_timeout(	STRING
LOW	tests/test_utilities.py	458	def _ensure_cache_file_exists(self) -> None:	STRING
LOW	tests/test_utilities.py	476	def serialize_generation_info(generation: GenerationInfo) -> _GenerationInfoDocument:	STRING
LOW	tests/test_utilities.py	501	def deserialize_generation_info(	STRING
LOW	tests/test_utilities.py	567	async def create_schematic_generation_result_collection(	STRING
LOW	tests/test_utilities.py	608	async def two_required_query_params(	STRING
LOW	tests/test_utilities.py	636	async def one_required_query_param_one_required_body_param(	STRING
LOW	tests/core/test_cancellation_suppression_latch.py	25	async def test_latch_behavior_with_no_cancellation() -> None:	CODE
LOW	tests/core/test_cancellation_suppression_latch.py	46	async def test_latch_behavior_with_cancellation_after_suppression() -> None:	CODE
LOW	tests/core/test_cancellation_suppression_latch.py	78	async def test_latch_behavior_with_cancellation_before_suppression() -> None:	CODE
LOW	tests/core/test_id_generator.py	18	async def test_that_id_generator_generates_different_ids_for_objects_with_similar_small_content() -> (	CODE
LOW	tests/core/test_id_generator.py	34	async def test_that_id_generator_generates_different_ids_for_objects_with_similar_big_content() -> (	CODE
LOW	tests/core/stable/test_capability_vector_store.py	26	async def test_that_updating_a_capability_replaces_its_vector_documents(	CODE
LOW	tests/core/stable/test_capability_vector_store.py	66	async def test_that_deleting_a_capability_removes_its_vector_documents(	CODE
LOW	tests/core/stable/test_journey_guideline_projection.py	10	async def test_that_projection_yields_followup_for_existing_guideline(container: Container) -> None:	CODE
LOW	tests/core/stable/test_relationships.py	55	async def test_that_direct_guideline_relationships_can_be_listed(	CODE
LOW	tests/core/stable/test_relationships.py	93	async def test_that_indirect_guideline_relationships_can_be_listed(	CODE
LOW	tests/core/stable/test_relationships.py	127	async def test_that_db_data_is_loaded_correctly(	CODE
LOW	tests/core/stable/test_relationships.py	165	async def test_that_relationships_are_returned_for_source_without_indirect_relationships(	CODE
LOW	tests/core/stable/test_relationships.py	206	async def test_that_connections_are_returned_for_source_with_indirect_connections(	CODE
LOW	tests/core/stable/test_relationships.py	248	async def test_that_relationships_are_returned_for_target_without_indirect_connections(	CODE
LOW	tests/core/stable/test_relationships.py	289	async def test_that_relationships_are_returned_for_target_with_indirect_connections(	CODE
LOW	tests/core/stable/test_relationships.py	331	async def test_that_all_relationships_can_be_listed(	CODE
LOW	tests/core/stable/test_relationships.py	360	async def test_that_relationships_can_be_listed_by_kind_without_entity_filters(	CODE
LOW	tests/core/stable/test_relationships.py	401	async def test_that_relationships_can_be_listed_by_source_id_without_kind_filter(	CODE
LOW	tests/core/stable/test_relationships.py	427	async def test_that_relationships_can_be_listed_by_target_id_without_kind_filter(	CODE
LOW	tests/core/stable/test_relationships.py	453	async def test_that_relationships_can_be_listed_with_both_source_and_target_filters(	CODE
LOW	tests/core/stable/test_relationships.py	483	async def test_that_creating_a_direct_circular_dependency_raises_an_error(	CODE
LOW	tests/core/stable/test_relationships.py	504	async def test_that_creating_an_indirect_circular_dependency_raises_an_error(	CODE
LOW	tests/core/stable/test_relationships.py	532	async def test_that_creating_a_self_dependency_is_allowed(	CODE
LOW	tests/core/stable/test_relationships.py	545	async def test_that_creating_a_cycle_across_dependency_and_dependency_any_raises_an_error(	CODE
LOW	tests/core/stable/test_application.py	102	async def test_that_a_new_customer_session_can_be_created(	CODE
LOW	tests/core/stable/test_application.py	118	async def test_that_a_new_customer_session_with_a_proactive_agent_contains_a_message(	CODE
LOW	tests/core/stable/test_application.py	140	async def test_that_when_a_client_event_is_posted_then_new_server_events_are_emitted(	CODE
LOW	tests/core/stable/test_application.py	168	async def test_that_a_session_update_is_detected_as_soon_as_a_client_event_is_posted(	CODE
LOW	tests/core/stable/test_application.py	192	async def test_that_when_a_customer_quickly_posts_more_than_one_message_then_only_one_message_is_emitted_as_a_reply_to_t	CODE
LOW	tests/core/stable/test_application.py	226	def hand_off_to_human_operator() -> ToolResult:	CODE
LOW	tests/core/stable/test_application.py	230	async def test_that_a_response_is_not_generated_automatically_after_a_tool_switches_the_session_to_manual_mode(	CODE
LOW	tests/core/stable/test_entity_cq.py	37	async def test_that_list_guidelines_with_mutual_agent_tag_are_returned(	CODE
LOW	tests/core/stable/test_entity_cq.py	76	async def test_that_list_guidelines_global_guideline_is_returned(	CODE
LOW	tests/core/stable/test_entity_cq.py	94	async def test_that_guideline_with_not_hierarchy_tag_is_not_returned(	CODE
LOW	tests/core/stable/test_entity_cq.py	127	async def test_that_guideline_matches_are_not_filtered_by_enabled_journeys(	CODE
LOW	tests/core/stable/test_entity_cq.py	169	async def test_that_guideline_tagged_with_disabled_journey_is_filtered_out_when_matched(	CODE
LOW	tests/core/stable/test_entity_cq.py	209	async def test_that_find_canned_responses_for_agent_returns_global_canned_responses(	CODE
LOW	tests/core/stable/test_entity_cq.py	230	async def test_that_find_canned_responses_for_agent_returns_none_for_non_matching_tag(	CODE
LOW	tests/core/stable/test_entity_cq.py	253	async def test_that_find_canned_responses_for_agent_and_journey_returns_journey_canned_responses(	CODE
LOW	tests/core/stable/test_entity_cq.py	282	async def test_that_find_glossary_terms_for_agent_returns_all_when_no_tags(	CODE
LOW	tests/core/stable/test_entity_cq.py	307	async def test_that_find_glossary_terms_for_agent_returns_none_for_non_matching_tag(	CODE
LOW	tests/core/stable/test_entity_cq.py	329	async def test_that_find_capabilities_for_agent_returns_unique_capabilities(	CODE
LOW	tests/core/stable/test_entity_cq.py	362	async def test_find_relevant_journeys_for_agent_returns_most_relevant(	CODE
LOW	tests/core/stable/test_entity_cq.py	400	async def test_list_guidelines_dependent_directly_on_journey(	CODE
LOW	tests/core/stable/test_entity_cq.py	438	async def test_list_guidelines_dependent_indirectly_on_journey(	CODE
1460 more matches not shown…

Cross-File Repetition65 hits · 325 pts

Severity	File	Line	Snippet	Context
HIGH	src/parlant/core/engines/alpha/message_generator.py	0	- expected result: ```json {json.dumps(shot.expected_result.model_dump(mode="json", exclude_unset=true), indent=2)}	STRING
HIGH	…arlant/core/engines/alpha/canned_response_generator.py	0	- expected result: ```json {json.dumps(shot.expected_result.model_dump(mode="json", exclude_unset=true), indent=2)}	STRING
HIGH	…viously_applied_actionable_customer_dependent_batch.py	0	- expected result: ```json {json.dumps(shot.expected_result.model_dump(mode="json", exclude_unset=true), indent=2)}	STRING
HIGH	…lpha/guideline_matching/generic/observational_batch.py	0	- expected result: ```json {json.dumps(shot.expected_result.model_dump(mode="json", exclude_unset=true), indent=2)}	STRING
HIGH	…pha/guideline_matching/generic/disambiguation_batch.py	0	- expected result: ```json {json.dumps(shot.expected_result.model_dump(mode="json", exclude_unset=true), indent=2)}	STRING
HIGH	…/guideline_matching/generic/response_analysis_batch.py	0	- expected result: ```json {json.dumps(shot.expected_result.model_dump(mode="json", exclude_unset=true), indent=2)}	STRING
HIGH	…ideline_matching/generic/guideline_actionable_batch.py	0	- expected result: ```json {json.dumps(shot.expected_result.model_dump(mode="json", exclude_unset=true), indent=2)}	STRING
HIGH	…neric/guideline_previously_applied_actionable_batch.py	0	- expected result: ```json {json.dumps(shot.expected_result.model_dump(mode="json", exclude_unset=true), indent=2)}	STRING
HIGH	…ne_matching/generic/guideline_low_criticality_batch.py	0	- expected result: ```json {json.dumps(shot.expected_result.model_dump(mode="json", exclude_unset=true), indent=2)}	STRING
HIGH	…atching/generic/journey/journey_next_step_selection.py	0	- expected result: ```json {json.dumps(shot.expected_result.model_dump(mode="json", exclude_unset=true), indent=2)}	STRING
HIGH	…ne_matching/generic/journey/journey_backtrack_check.py	0	- expected result: ```json {json.dumps(shot.expected_result.model_dump(mode="json", exclude_unset=true), indent=2)}	STRING
HIGH	…ng/generic/journey/journey_backtrack_node_selection.py	0	- expected result: ```json {json.dumps(shot.expected_result.model_dump(mode="json", exclude_unset=true), indent=2)}	STRING
HIGH	…ant/core/services/indexing/relative_action_proposer.py	0	- expected result: ```json {json.dumps(shot.expected_result.model_dump(mode="json", exclude_unset=true), indent=2)}	STRING
HIGH	…ervices/indexing/journey_reachable_nodes_evaluation.py	0	- expected result: ```json {json.dumps(shot.expected_result.model_dump(mode="json", exclude_unset=true), indent=2)}	STRING
HIGH	…/engines/alpha/tool_calling/overlapping_tools_batch.py	0	- context: {shot.description} - expected result: ```json {json.dumps(shot.expected_result.model_dump(mode="json"	STRING
HIGH	…t/core/engines/alpha/tool_calling/single_tool_batch.py	0	- context: {shot.description} - expected result: ```json {json.dumps(shot.expected_result.model_dump(mode="json"	STRING
HIGH	…core/services/indexing/tool_running_action_detector.py	0	- context: {shot.description} - expected result: ```json {json.dumps(shot.expected_result.model_dump(mode="json"	STRING
HIGH	…viously_applied_actionable_customer_dependent_batch.py	0	- interaction events: {json.dumps([adapt_event(e) for e in shot.interaction_events], indent=2)}	STRING
HIGH	…lpha/guideline_matching/generic/observational_batch.py	0	- interaction events: {json.dumps([adapt_event(e) for e in shot.interaction_events], indent=2)}	STRING
HIGH	…pha/guideline_matching/generic/disambiguation_batch.py	0	- interaction events: {json.dumps([adapt_event(e) for e in shot.interaction_events], indent=2)}	STRING
HIGH	…/guideline_matching/generic/response_analysis_batch.py	0	- interaction events: {json.dumps([adapt_event(e) for e in shot.interaction_events], indent=2)}	STRING
HIGH	…ideline_matching/generic/guideline_actionable_batch.py	0	- interaction events: {json.dumps([adapt_event(e) for e in shot.interaction_events], indent=2)}	STRING
HIGH	…neric/guideline_previously_applied_actionable_batch.py	0	- interaction events: {json.dumps([adapt_event(e) for e in shot.interaction_events], indent=2)}	STRING
HIGH	…ne_matching/generic/guideline_low_criticality_batch.py	0	- interaction events: {json.dumps([adapt_event(e) for e in shot.interaction_events], indent=2)}	STRING
HIGH	…atching/generic/journey/journey_next_step_selection.py	0	- interaction events: {json.dumps([adapt_event(e) for e in shot.interaction_events], indent=2)}	STRING
HIGH	…ne_matching/generic/journey/journey_backtrack_check.py	0	- interaction events: {json.dumps([adapt_event(e) for e in shot.interaction_events], indent=2)}	STRING
HIGH	…ng/generic/journey/journey_backtrack_node_selection.py	0	- interaction events: {json.dumps([adapt_event(e) for e in shot.interaction_events], indent=2)}	STRING
HIGH	…viously_applied_actionable_customer_dependent_batch.py	0	examples of guideline match evaluations: ------------------- {formatted_shots}	STRING
HIGH	…ideline_matching/generic/guideline_actionable_batch.py	0	examples of guideline match evaluations: ------------------- {formatted_shots}	STRING
HIGH	…neric/guideline_previously_applied_actionable_batch.py	0	examples of guideline match evaluations: ------------------- {formatted_shots}	STRING
HIGH	…ne_matching/generic/guideline_low_criticality_batch.py	0	examples of guideline match evaluations: ------------------- {formatted_shots}	STRING
HIGH	…viously_applied_actionable_customer_dependent_batch.py	0	important: please note there are exactly {guidelines_len} guidelines in the list for you to check. output format -------	STRING
HIGH	…ideline_matching/generic/guideline_actionable_batch.py	0	important: please note there are exactly {guidelines_len} guidelines in the list for you to check. output format -------	STRING
HIGH	…neric/guideline_previously_applied_actionable_batch.py	0	important: please note there are exactly {guidelines_len} guidelines in the list for you to check. output format -------	STRING
HIGH	…ne_matching/generic/guideline_low_criticality_batch.py	0	important: please note there are exactly {guidelines_len} guidelines in the list for you to check. output format -------	STRING
HIGH	…/guideline_matching/generic/response_analysis_batch.py	0	important: please note there are exactly {guidelines_len} guidelines in the list for you to check. output format -------	STRING
HIGH	…atching/generic/journey/journey_next_step_selection.py	0	examples of journey step selections: ------------------- {formatted_shots} ### example section is over. the following is	STRING
HIGH	…ne_matching/generic/journey/journey_backtrack_check.py	0	examples of journey step selections: ------------------- {formatted_shots} ### example section is over. the following is	STRING
HIGH	…ng/generic/journey/journey_backtrack_node_selection.py	0	examples of journey step selections: ------------------- {formatted_shots} ### example section is over. the following is	STRING
HIGH	…ore/services/indexing/guideline_continuous_proposer.py	0	guideline ----------- condition: {condition} action: {action}	STRING
HIGH	…core/services/indexing/tool_running_action_detector.py	0	guideline ----------- condition: {condition} action: {action}	STRING
HIGH	…ervices/indexing/guideline_agent_intention_proposer.py	0	guideline ----------- condition: {condition} action: {action}	STRING
HIGH	…ervices/indexing/customer_dependent_action_detector.py	0	guideline ----------- condition: {condition} action: {action}	STRING
HIGH	src/parlant/adapters/nlp/vertex_service.py	0	returns an error message if the environment is not set up correctly.	STRING
HIGH	src/parlant/adapters/nlp/cerebras_service.py	0	returns an error message if the environment is not set up correctly.	STRING
HIGH	src/parlant/adapters/nlp/qwen_service.py	0	returns an error message if the environment is not set up correctly.	STRING
HIGH	src/parlant/adapters/nlp/mistral_service.py	0	returns an error message if the environment is not set up correctly.	STRING
HIGH	src/parlant/adapters/nlp/azure_service.py	0	returns an error message if the environment is not set up correctly.	STRING
HIGH	src/parlant/adapters/nlp/parlant_cloud_service.py	0	returns an error message if the environment is not set up correctly.	STRING
HIGH	src/parlant/adapters/nlp/litellm_service.py	0	returns an error message if the environment is not set up correctly.	STRING
HIGH	src/parlant/adapters/nlp/openrouter_service.py	0	returns an error message if the environment is not set up correctly.	STRING
HIGH	src/parlant/adapters/nlp/aws_service.py	0	returns an error message if the environment is not set up correctly.	STRING
HIGH	src/parlant/adapters/nlp/modelscope_service.py	0	returns an error message if the environment is not set up correctly.	STRING
HIGH	src/parlant/adapters/nlp/together_service.py	0	returns an error message if the environment is not set up correctly.	STRING
HIGH	src/parlant/adapters/nlp/openai_service.py	0	returns an error message if the environment is not set up correctly.	STRING
HIGH	src/parlant/adapters/nlp/gemini_service.py	0	returns an error message if the environment is not set up correctly.	STRING
HIGH	src/parlant/adapters/nlp/fireworks_service.py	0	returns an error message if the environment is not set up correctly.	STRING
HIGH	src/parlant/adapters/nlp/ollama_service.py	0	returns an error message if the environment is not set up correctly.	STRING
HIGH	src/parlant/adapters/nlp/anthropic_service.py	0	returns an error message if the environment is not set up correctly.	STRING
HIGH	src/parlant/adapters/nlp/deepseek_service.py	0	returns an error message if the environment is not set up correctly.	STRING
5 more matches not shown…

Over-Commented Block267 hits · 253 pts

Severity	File	Line	Snippet	Context
LOW	tests/conftest.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/tool_utilities.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/test_utilities.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/__init__.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/test_cancellation_suppression_latch.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/conftest.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/test_id_generator.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/stable/test_relationships.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/stable/test_application.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/stable/test_entity_cq.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/stable/test_health_reporter.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…core/stable/engines/alpha/test_user_story_scenarios.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…viously_applied_actionable_customer_dependent_batch.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…table/engines/alpha/test_guideline_actionable_batch.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…ines/alpha/test_previously_applied_actionable_batch.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…/core/stable/engines/alpha/test_relational_resolver.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…/stable/engines/alpha/test_context_variable_loading.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…/engines/alpha/test_guideline_low_criticality_batch.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…ts/core/stable/engines/alpha/test_guideline_matcher.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/stable/engines/alpha/test_mcp.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…s/core/stable/engines/alpha/test_baseline_scenarios.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…core/stable/engines/alpha/test_disambiguation_batch.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…stable/engines/alpha/test_generic_response_analysis.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/stable/engines/alpha/test_tool_caller.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/stable/persistence/test_matches_filters.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/stable/nlp/test_embedding.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/stable/nlp/test_generation.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/stable/services/tools/test_openapi.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/stable/services/tools/test_plugin_client.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…ces/indexing/test_journey_reachable_nodes_evaluator.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…ble/services/indexing/test_agent_intention_proposer.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…ervices/indexing/test_continuous_guideline_proposer.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/stable/services/indexing/test_indexer.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…es/indexing/test_customer_dependent_action_detector.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…le/services/indexing/test_guideline_action_proposer.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/common/utils.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/common/engines/alpha/utils.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/common/engines/alpha/steps/terms.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/common/engines/alpha/steps/tags.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/common/engines/alpha/steps/sessions.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…s/core/common/engines/alpha/steps/context_variables.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/common/engines/alpha/steps/engines.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/common/engines/alpha/steps/events.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…ts/core/common/engines/alpha/steps/canned_responses.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/common/engines/alpha/steps/tools.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/common/engines/alpha/steps/journeys.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/common/engines/alpha/steps/agents.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/common/engines/alpha/steps/capabilities.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/common/engines/alpha/steps/customers.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/core/common/engines/alpha/steps/guidelines.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…re/unstable/engines/alpha/test_user_story_scenarios.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…nstable/engines/alpha/test_agent_intention_proposer.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…ines/alpha/test_previously_applied_actionable_batch.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…/core/unstable/engines/alpha/test_guideline_matcher.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…core/unstable/engines/alpha/test_baseline_scenarios.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	…re/unstable/engines/alpha/test_disambiguation_batch.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/adapters/vector_db/test_mongo_vector.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/adapters/vector_db/test_qdrant.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/adapters/nlp/test_zhipu_service.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
LOW	tests/adapters/nlp/test_azure_service.py	1	# Copyright 2026 Emcie Co Ltd.	COMMENT
207 more matches not shown…

Self-Referential Comments60 hits · 181 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	…/core/stable/engines/alpha/test_relational_resolver.py	232	# Create a standalone guideline	COMMENT
MEDIUM⚡	…/core/stable/engines/alpha/test_relational_resolver.py	238	# Create a journey with a condition	COMMENT
MEDIUM	…/core/stable/engines/alpha/test_relational_resolver.py	315	# Create a journey with a condition	COMMENT
MEDIUM	…/core/stable/engines/alpha/test_relational_resolver.py	351	# Create a standalone guideline	COMMENT
MEDIUM	…/core/stable/engines/alpha/test_relational_resolver.py	405	# Create a journey	COMMENT
MEDIUM	tests/core/stable/engines/alpha/test_tool_caller.py	1343	# Create a tool with no parameters and consequential=False (default)	COMMENT
MEDIUM	tests/core/stable/engines/alpha/test_tool_caller.py	1397	# Create a tool with no parameters and consequential=False (default)	COMMENT
MEDIUM	tests/core/stable/engines/alpha/test_tool_caller.py	1408	# Create a staged event representing this tool already being staged	COMMENT
MEDIUM	tests/adapters/vector_db/test_mongo_vector.py	390	# Create a new database instance pointing to the same database	COMMENT
MEDIUM	tests/adapters/db/test_mongodb.py	527	# Create a simple collection	COMMENT
MEDIUM	tests/adapters/db/test_json_file.py	198	# Create a document first	COMMENT
MEDIUM	tests/adapters/db/test_json_file.py	221	# Create a document first	COMMENT
MEDIUM	tests/adapters/db/test_json_file.py	249	# Create a document first	COMMENT
MEDIUM	tests/adapters/db/test_json_file.py	542	# Create an empty file	COMMENT
MEDIUM	tests/sdk/test_journeys.py	1061	# Create the first journey	COMMENT
MEDIUM	tests/sdk/test_journeys.py	1107	# Create a chat state for order confirmation	COMMENT
MEDIUM	tests/sdk/test_journeys.py	1398	# Create the user validation journey	COMMENT
MEDIUM	tests/sdk/test_journeys.py	1417	# Create the hotel booking journey	COMMENT
MEDIUM	tests/sdk/test_journeys.py	1552	# Create main customer service journey	COMMENT
MEDIUM⚡	tests/sdk/test_journeys.py	1767	# Create a guideline	COMMENT
MEDIUM⚡	tests/sdk/test_journeys.py	1773	# Create a journey with a custom state ID	COMMENT
MEDIUM⚡	tests/sdk/test_journeys.py	1780	# Create a state with a custom ID	COMMENT
MEDIUM⚡	tests/sdk/test_journeys.py	1788	# Create a session and send a message	COMMENT
MEDIUM	tests/sdk/test_journeys.py	1878	# Create a state with a custom ID	COMMENT
MEDIUM	tests/sdk/test_journeys.py	2063	# Create a linked journey (will be activated via link, not via conditions)	COMMENT
MEDIUM	tests/sdk/test_journeys.py	2077	# Create the parent journey that links to the validation journey	COMMENT
MEDIUM	tests/sdk/test_journeys.py	2141	# Create a state transition and attach retriever to the target state	COMMENT
MEDIUM	tests/sdk/test_journeys.py	2178	# Create a state transition and attach retriever to the target state	COMMENT
MEDIUM	tests/sdk/test_guidelines.py	722	# Create the first guideline	COMMENT
MEDIUM	tests/sdk/test_guidelines.py	951	# Create a canned response with a template that uses a field	COMMENT
MEDIUM	tests/sdk/test_guidelines.py	985	# Create a canned response that uses fields from multiple providers	COMMENT
MEDIUM	tests/sdk/test_sdk_validation.py	183	# Create a fork state	COMMENT
MEDIUM	tests/sdk/test_sdk_validation.py	257	# Create a tool state	COMMENT
MEDIUM	tests/sdk/test_sdk_validation.py	288	# Create a chat state	COMMENT
MEDIUM	tests/sdk/test_sdk_validation.py	601	# Create a fork state to test with	COMMENT
MEDIUM	tests/sdk/test_labels.py	101	# Create a journey with labels that will be propagated when the journey matches	COMMENT
MEDIUM	tests/sdk/test_canned_responses.py	47	# Create a canned response that depends on "order" field	COMMENT
MEDIUM	tests/api/test_guidelines.py	973	# Create a guideline with LOW criticality	COMMENT
MEDIUM	tests/api/test_sessions.py	1911	# Create an event with initial metadata	COMMENT
MEDIUM	tests/api/test_sessions.py	1967	# Create an event with initial metadata	COMMENT
MEDIUM	tests/api/test_sessions.py	2021	# Create a customer message with custom participant info	COMMENT
MEDIUM	tests/api/test_sessions.py	2052	# Create a customer message WITHOUT custom participant	COMMENT
MEDIUM	tests/api/test_relationships.py	15	# Import necessary modules and classes	COMMENT
MEDIUM	examples/travel_voice_agent.py	100	# Create the journey	COMMENT
MEDIUM	examples/travel_voice_agent.py	168	# Create the journey	COMMENT
MEDIUM	examples/healthcare.py	70	# Create the journey	COMMENT
MEDIUM	examples/healthcare.py	130	# Create the journey	COMMENT
MEDIUM	src/parlant/sdk.py	1620	# Create the new state	COMMENT
MEDIUM	src/parlant/sdk.py	1692	# Create a fork state for the condition	COMMENT
MEDIUM	src/parlant/sdk.py	1734	# Create the target state and add it to processing queue	COMMENT
MEDIUM	src/parlant/sdk.py	1813	# Create the transition only if target state is in mapping	COMMENT
MEDIUM	src/parlant/sdk.py	4513	# Create a shim that translates between SDK and core types	COMMENT
MEDIUM	src/parlant/core/engines/alpha/engine.py	1602	# Create a convenient accessor dict for tool-enabled guidelines (and their tools).	COMMENT
MEDIUM	src/parlant/core/services/tools/plugins.py	259	"""This function is specifically used to refresh some of the tool's	STRING
MEDIUM	src/parlant/core/services/tools/mcp_service.py	65	"""This class is a wrapper around the FastMCP server, mainly to be used in testing the MCP client"""	STRING
MEDIUM	…core/services/indexing/behavioral_change_evaluation.py	563	# Create a mapping from guideline payloads to evaluations	COMMENT
MEDIUM	src/parlant/adapters/nlp/openrouter_service.py	606	# Create a dynamic generator for any OpenRouter model	STRING
MEDIUM	src/parlant/adapters/nlp/gemini_service.py	231	# Create a signature from parameters	COMMENT
MEDIUM	src/parlant/adapters/nlp/gemini_service.py	243	# Create a fake callable	COMMENT
MEDIUM	src/parlant/adapters/nlp/gemini_service.py	596	# Create the new class	STRING

Excessive Try-Catch Wrapping198 hits · 176 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_utilities.py	775	except Exception:	STRING
LOW⚡	tests/core/stable/test_health_reporter.py	260	except Exception as e: # noqa: BLE001	CODE
LOW	tests/core/stable/test_health_reporter.py	332	except Exception as e: # noqa: BLE001	CODE
LOW	tests/core/stable/services/tools/test_plugin_client.py	201	except Exception as exc:	CODE
LOW⚡	tests/adapters/db/test_mongodb.py	730	except Exception:	CODE
LOW	tests/e2e/test_server_cli.py	239	except Exception as exc:	CODE
LOW	tests/e2e/test_utilities.py	125	except Exception as exc:	CODE
LOW	tests/e2e/test_utilities.py	157	except Exception as e:	CODE
LOW	tests/e2e/test_utilities.py	164	except Exception:	CODE
LOW	docs/advanced/custom-llms.md	289	except Exception as e:	CODE
LOW	docs/adapters/nlp/vertex.md	344	except Exception as e:	CODE
LOW	docs/production/human-handoff.md	195	except Exception as e:	CODE
LOW	src/parlant/core/background_tasks.py	133	except Exception as exc:	CODE
LOW	src/parlant/core/async_utils.py	226	except Exception as e:	CODE
LOW	src/parlant/core/tools.py	478	except Exception as e:	CODE
LOW	src/parlant/core/tools.py	492	except Exception as e:	CODE
LOW	src/parlant/core/tools.py	569	except Exception as exc:	CODE
LOW	src/parlant/core/app_modules/sessions.py	347	except Exception:	CODE
LOW	src/parlant/core/app_modules/common.py	18	except Exception:	CODE
LOW	src/parlant/core/engines/alpha/prompt_builder.py	156	except Exception as e:	CODE
LOW	src/parlant/core/engines/alpha/message_generator.py	302	except Exception as exc:	CODE
LOW	…arlant/core/engines/alpha/canned_response_generator.py	2048	except Exception as e:	CODE
LOW	…arlant/core/engines/alpha/canned_response_generator.py	1237	except Exception as exc:	STRING
LOW	…arlant/core/engines/alpha/canned_response_generator.py	1290	except Exception as exc:	STRING
LOW	…arlant/core/engines/alpha/canned_response_generator.py	2480	except Exception as exc:	STRING
LOW	…arlant/core/engines/alpha/canned_response_generator.py	2823	except Exception as e:	STRING
LOW	src/parlant/core/engines/alpha/engine.py	213	except Exception as exc:	CODE
LOW	src/parlant/core/engines/alpha/engine.py	273	except Exception as exc:	CODE
LOW	src/parlant/core/engines/alpha/engine.py	412	except Exception:	CODE
LOW	…/engines/alpha/tool_calling/overlapping_tools_batch.py	203	except Exception as exc:	CODE
LOW	…t/core/engines/alpha/tool_calling/single_tool_batch.py	346	except Exception as exc:	CODE
LOW	…t/core/engines/alpha/tool_calling/single_tool_batch.py	1027	except Exception as exc:	STRING
LOW	…parlant/core/engines/alpha/tool_calling/tool_caller.py	290	except Exception as exc:	CODE
LOW	…parlant/core/engines/alpha/tool_calling/tool_caller.py	308	except Exception as e:	CODE
LOW	…ideline_matching/custom_guideline_matching_strategy.py	57	except Exception as e:	CODE
LOW	…viously_applied_actionable_customer_dependent_batch.py	156	except Exception as exc:	CODE
LOW	…lpha/guideline_matching/generic/observational_batch.py	151	except Exception as exc:	CODE
LOW	…pha/guideline_matching/generic/disambiguation_batch.py	217	except Exception as exc:	CODE
LOW	…/guideline_matching/generic/response_analysis_batch.py	206	except Exception as exc:	CODE
LOW	…ideline_matching/generic/guideline_actionable_batch.py	146	except Exception as exc:	CODE
LOW	…neric/guideline_previously_applied_actionable_batch.py	149	except Exception as exc:	CODE
LOW	…ne_matching/generic/guideline_low_criticality_batch.py	123	except Exception as exc:	CODE
LOW	…atching/generic/journey/journey_next_step_selection.py	377	except Exception as exc:	CODE
LOW	…ne_matching/generic/journey/journey_backtrack_check.py	187	except Exception:	CODE
LOW	…ne_matching/generic/journey/journey_backtrack_check.py	363	except Exception as exc:	STRING
LOW	…ng/generic/journey/journey_backtrack_node_selection.py	254	except Exception:	CODE
LOW	…ng/generic/journey/journey_backtrack_node_selection.py	514	except Exception as exc:	STRING
LOW	src/parlant/core/nlp/generation.py	195	except Exception:	CODE
LOW	src/parlant/core/nlp/generation.py	206	except Exception as exc:	CODE
LOW	src/parlant/core/nlp/generation.py	362	except Exception as exc:	CODE
LOW	src/parlant/core/nlp/generation.py	438	except Exception as e:	CODE
LOW	src/parlant/core/nlp/embedding.py	234	except Exception as exc:	CODE
LOW	src/parlant/core/services/tools/plugins.py	235	except Exception:	CODE
LOW	src/parlant/core/services/tools/plugins.py	709	except Exception as exc:	CODE
LOW	src/parlant/core/services/tools/plugins.py	941	except Exception:	CODE
LOW	src/parlant/core/services/tools/plugins.py	999	except Exception as exc:	CODE
LOW	src/parlant/core/services/tools/mcp_service.py	218	except Exception as exc:	CODE
LOW	src/parlant/core/services/tools/mcp_service.py	257	except Exception as exc:	CODE
LOW	src/parlant/core/services/tools/mcp_service.py	282	except Exception as exc:	CODE
LOW	src/parlant/core/services/tools/mcp_service.py	297	except Exception as e:	CODE
138 more matches not shown…

Decorative Section Separators42 hits · 132 pts

Severity	File	Line	Snippet	Context
MEDIUM	…/core/stable/engines/alpha/test_relational_resolver.py	2012	# ── Tag-level dependency tests ──────────────────────────────────────────────	COMMENT
MEDIUM	…/core/stable/engines/alpha/test_relational_resolver.py	2252	# ── ANY-semantics tag dependency tests ─────────────────────────────────────	COMMENT
MEDIUM	…/core/stable/engines/alpha/test_relational_resolver.py	2608	# ── Dependency hierarchy tests ─────────────────────────────────────────────	COMMENT
MEDIUM	…/core/stable/engines/alpha/test_relational_resolver.py	3199	# ── Edge-case tests ─────────────────────────────────────────────────────────	COMMENT
MEDIUM	…/core/stable/engines/alpha/test_relational_resolver.py	3421	# ── Custom journey tag propagation tests ───────────────────────────────────	COMMENT
MEDIUM	…/core/stable/engines/alpha/test_relational_resolver.py	3818	# ── Dependency edge-case tests ─────────────────────────────────────────────	COMMENT
MEDIUM	…/core/stable/engines/alpha/test_relational_resolver.py	4296	# ── Numerical priority + dependency interaction tests ──────────────────────	COMMENT
MEDIUM	…/core/stable/engines/alpha/test_relational_resolver.py	4489	# ── TAG_ALL vs TAG_ANY explicit tests ──────────────────────────────────────	COMMENT
MEDIUM	…/core/stable/engines/alpha/test_relational_resolver.py	4771	# ── DEPENDENCY_ANY (OR group) tests ────────────────────────────────────────	COMMENT
MEDIUM	…/core/stable/engines/alpha/test_relational_resolver.py	5030	# ── DEPENDENCY_ANY edge case tests ─────────────────────────────────────────	COMMENT
MEDIUM	…/core/stable/engines/alpha/test_relational_resolver.py	5741	# ── Resolution attribution edge-case tests ────────────────────────────────	COMMENT
MEDIUM	tests/core/stable/nlp/test_generation.py	417	# ============================================================================	COMMENT
MEDIUM	tests/core/stable/nlp/test_generation.py	419	# ============================================================================	COMMENT
MEDIUM⚡	src/parlant/core/engines/alpha/relational_resolver.py	60	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	src/parlant/core/engines/alpha/relational_resolver.py	62	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	src/parlant/core/engines/alpha/relational_resolver.py	68	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	src/parlant/core/engines/alpha/relational_resolver.py	70	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	src/parlant/core/engines/alpha/relational_resolver.py	180	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	src/parlant/core/engines/alpha/relational_resolver.py	182	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	src/parlant/core/engines/alpha/relational_resolver.py	221	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	src/parlant/core/engines/alpha/relational_resolver.py	223	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	src/parlant/core/engines/alpha/relational_resolver.py	593	# ── Phase 1: Resolve dependency targets ──────────────────────────	COMMENT
MEDIUM	src/parlant/core/engines/alpha/relational_resolver.py	630	# ── Phase 2: Topological sort (Kahn's algorithm) ─────────────────	COMMENT
MEDIUM	src/parlant/core/engines/alpha/relational_resolver.py	634	# ── Phase 3: Evaluate in topological order ───────────────────────	COMMENT
MEDIUM	src/parlant/core/nlp/generation.py	40	# ============================================================================	COMMENT
MEDIUM	src/parlant/core/nlp/generation.py	42	# ============================================================================	COMMENT
MEDIUM	src/parlant/core/nlp/generation.py	259	# ============================================================================	COMMENT
MEDIUM	src/parlant/core/nlp/generation.py	261	# ============================================================================	COMMENT
MEDIUM	src/parlant/adapters/nlp/parlant_cloud_service.py	361	# ============================================================================	COMMENT
MEDIUM	src/parlant/adapters/nlp/parlant_cloud_service.py	363	# ============================================================================	COMMENT
MEDIUM	src/parlant/adapters/nlp/parlant_cloud_service.py	580	# ============================================================================	COMMENT
MEDIUM	src/parlant/adapters/nlp/parlant_cloud_service.py	582	# ============================================================================	COMMENT
MEDIUM	src/parlant/adapters/nlp/openai_service.py	414	# ============================================================================	COMMENT
MEDIUM	src/parlant/adapters/nlp/openai_service.py	416	# ============================================================================	COMMENT
MEDIUM	src/parlant/adapters/nlp/openai_service.py	561	# ============================================================================	COMMENT
MEDIUM	src/parlant/adapters/nlp/openai_service.py	563	# ============================================================================	COMMENT
MEDIUM	src/parlant/adapters/nlp/novita_service.py	272	# ============================================================================	COMMENT
MEDIUM	src/parlant/adapters/nlp/novita_service.py	274	# ============================================================================	COMMENT
MEDIUM	src/parlant/adapters/nlp/emcie_service.py	335	# ============================================================================	COMMENT
MEDIUM	src/parlant/adapters/nlp/emcie_service.py	337	# ============================================================================	COMMENT
MEDIUM	src/parlant/adapters/nlp/emcie_service.py	534	# ============================================================================	COMMENT
MEDIUM	src/parlant/adapters/nlp/emcie_service.py	536	# ============================================================================	COMMENT

Deep Nesting126 hits · 108 pts

Severity	File	Line	Context
LOW	…re/stable/engines/alpha/test_journey_node_selection.py	1098	CODE
LOW	…core/stable/engines/alpha/test_disambiguation_batch.py	269	CODE
LOW	…re/unstable/engines/alpha/test_disambiguation_batch.py	263	CODE
LOW	tests/adapters/db/test_mongodb.py	1078	CODE
LOW	tests/adapters/db/test_mongodb.py	1116	CODE
LOW	tests/adapters/db/test_mongodb.py	1181	CODE
LOW	tests/sdk/utils.py	125	CODE
LOW	tests/sdk/test_agents.py	366	CODE
LOW	tests/e2e/test_utilities.py	95	CODE
LOW	scripts/generate_client_sdk.py	38	CODE
LOW	src/parlant/sdk.py	1902	CODE
LOW	src/parlant/sdk.py	727	CODE
LOW	src/parlant/sdk.py	819	CODE
LOW	src/parlant/sdk.py	953	CODE
LOW	src/parlant/sdk.py	1386	CODE
LOW	src/parlant/sdk.py	1472	CODE
LOW	src/parlant/sdk.py	1586	CODE
LOW	src/parlant/sdk.py	2944	CODE
LOW	src/parlant/sdk.py	4684	CODE
LOW	src/parlant/sdk.py	4878	CODE
LOW	src/parlant/core/journeys.py	1067	CODE
LOW	src/parlant/core/entity_cq.py	382	CODE
LOW	src/parlant/core/capabilities.py	414	CODE
LOW	src/parlant/core/relationships.py	339	CODE
LOW	src/parlant/core/glossary.py	396	CODE
LOW	src/parlant/core/app_modules/context_variables.py	84	CODE
LOW	src/parlant/core/app_modules/journeys.py	116	CODE
LOW	src/parlant/core/engines/alpha/relational_resolver.py	264	CODE
LOW	src/parlant/core/engines/alpha/relational_resolver.py	553	CODE
LOW	src/parlant/core/engines/alpha/relational_resolver.py	725	CODE
LOW	src/parlant/core/engines/alpha/relational_resolver.py	756	CODE
LOW	src/parlant/core/engines/alpha/relational_resolver.py	930	CODE
LOW	src/parlant/core/engines/alpha/relational_resolver.py	1204	CODE
LOW	src/parlant/core/engines/alpha/relational_resolver.py	1353	CODE
LOW	src/parlant/core/engines/alpha/prompt_builder.py	109	CODE
LOW	src/parlant/core/engines/alpha/message_generator.py	197	CODE
LOW	…arlant/core/engines/alpha/canned_response_generator.py	610	CODE
LOW	…arlant/core/engines/alpha/canned_response_generator.py	1020	CODE
LOW	…arlant/core/engines/alpha/canned_response_generator.py	1062	CODE
LOW	src/parlant/core/engines/alpha/engine.py	1043	CODE
LOW	src/parlant/core/engines/alpha/engine.py	1646	CODE
LOW	src/parlant/core/engines/alpha/engine.py	2143	CODE
LOW	…/engines/alpha/tool_calling/overlapping_tools_batch.py	236	CODE
LOW	…/engines/alpha/tool_calling/overlapping_tools_batch.py	661	CODE
LOW	…t/core/engines/alpha/tool_calling/single_tool_batch.py	172	CODE
LOW	…t/core/engines/alpha/tool_calling/single_tool_batch.py	182	CODE
LOW	…t/core/engines/alpha/tool_calling/single_tool_batch.py	355	CODE
LOW	…t/core/engines/alpha/tool_calling/single_tool_batch.py	1254	CODE
LOW	…ngines/alpha/tool_calling/default_tool_call_batcher.py	64	CODE
LOW	…ngines/alpha/tool_calling/default_tool_call_batcher.py	77	CODE
LOW	…viously_applied_actionable_customer_dependent_batch.py	107	CODE
LOW	…lpha/guideline_matching/generic/observational_batch.py	102	CODE
LOW	…pha/guideline_matching/generic/disambiguation_batch.py	148	CODE
LOW	…/guideline_matching/generic/response_analysis_batch.py	148	CODE
LOW	…ideline_matching/generic/guideline_actionable_batch.py	97	CODE
LOW	…neric/guideline_previously_applied_actionable_batch.py	100	CODE
LOW	…atching/generic/generic_guideline_matching_strategy.py	161	CODE
LOW	…ne_matching/generic/guideline_low_criticality_batch.py	73	CODE
LOW	…tching/generic/journey/journey_node_selection_batch.py	159	CODE
LOW	…tching/generic/journey/journey_node_selection_batch.py	264	CODE
66 more matches not shown…

Unused Imports118 hits · 90 pts

Severity	File	Line	Context
LOW	tests/core/test_cancellation_suppression_latch.py	15	CODE
LOW	…/core/stable/engines/alpha/test_relational_resolver.py	18	CODE
LOW	tests/adapters/db/test_snowflake_db.py	15	CODE
LOW	tests/e2e/test_utilities.py	15	CODE
LOW	src/parlant/sdk.py	15	CODE
LOW	src/parlant/sdk.py	76	CODE
LOW	src/parlant/sdk.py	76	CODE
LOW	src/parlant/sdk.py	76	CODE
LOW	src/parlant/sdk.py	76	CODE
LOW	src/parlant/sdk.py	76	CODE
LOW	src/parlant/sdk.py	76	CODE
LOW	src/parlant/sdk.py	76	CODE
LOW	src/parlant/sdk.py	76	CODE
LOW	src/parlant/sdk.py	99	CODE
LOW	src/parlant/sdk.py	132	CODE
LOW	src/parlant/sdk.py	132	CODE
LOW	src/parlant/sdk.py	133	CODE
LOW	src/parlant/sdk.py	134	CODE
LOW	src/parlant/sdk.py	157	CODE
LOW	src/parlant/sdk.py	163	CODE
LOW	src/parlant/sdk.py	163	CODE
LOW	src/parlant/sdk.py	163	CODE
LOW	src/parlant/sdk.py	168	CODE
LOW	src/parlant/sdk.py	183	CODE
LOW	src/parlant/sdk.py	183	CODE
LOW	src/parlant/sdk.py	183	CODE
LOW	src/parlant/sdk.py	230	CODE
LOW	src/parlant/sdk.py	230	CODE
LOW	src/parlant/sdk.py	230	CODE
LOW	src/parlant/sdk.py	230	CODE
LOW	src/parlant/sdk.py	230	CODE
LOW	src/parlant/sdk.py	239	CODE
LOW	src/parlant/sdk.py	239	CODE
LOW	src/parlant/sdk.py	239	CODE
LOW	src/parlant/sdk.py	239	CODE
LOW	src/parlant/sdk.py	239	CODE
LOW	src/parlant/sdk.py	246	CODE
LOW	src/parlant/sdk.py	246	CODE
LOW	src/parlant/sdk.py	252	CODE
LOW	src/parlant/sdk.py	252	CODE
LOW	src/parlant/sdk.py	256	CODE
LOW	src/parlant/sdk.py	256	CODE
LOW	src/parlant/sdk.py	256	CODE
LOW	src/parlant/sdk.py	263	CODE
LOW	src/parlant/sdk.py	263	CODE
LOW	src/parlant/sdk.py	263	CODE
LOW	src/parlant/sdk.py	263	CODE
LOW	src/parlant/sdk.py	274	CODE
LOW	src/parlant/sdk.py	274	CODE
LOW	src/parlant/sdk.py	274	CODE
LOW	src/parlant/sdk.py	274	CODE
LOW	src/parlant/sdk.py	274	CODE
LOW	src/parlant/sdk.py	274	CODE
LOW	src/parlant/sdk.py	274	CODE
LOW	src/parlant/core/tags.py	15	CODE
LOW	src/parlant/core/sessions.py	15	CODE
LOW	src/parlant/core/context_variables.py	15	CODE
LOW	src/parlant/core/async_utils.py	15	CODE
LOW	src/parlant/core/loggers.py	15	CODE
LOW	src/parlant/core/canned_responses.py	15	CODE
58 more matches not shown…

Structural Annotation Overuse42 hits · 61 pts

Severity	File	Line	Snippet	Context
LOW	llms.txt	234	# Step 1: Get order number	COMMENT
LOW	llms.txt	239	# Step 2: Look up the order	COMMENT
LOW	llms.txt	254	# Step 4: Check if they need anything else	COMMENT
LOW	tests/core/common/engines/alpha/steps/journeys.py	2076	# Step 1: Ask for account name	COMMENT
LOW	tests/core/common/engines/alpha/steps/journeys.py	2104	# Step 2: Ask for desired credit limit	COMMENT
LOW	tests/core/common/engines/alpha/steps/journeys.py	2132	# Step 3: Confirm information and move forward politely	COMMENT
LOW	tests/core/common/engines/alpha/steps/journeys.py	2161	# Step 4: Use tool to get the current limit	COMMENT
LOW	tests/core/common/engines/alpha/steps/journeys.py	2211	# Step 5: Use tool to change the limit	COMMENT
LOW	tests/core/common/engines/alpha/steps/journeys.py	2261	# Step 6: Report to customer	COMMENT
LOW	tests/core/common/engines/alpha/steps/journeys.py	2278	# Step 7: Report failure	COMMENT
LOW	docs/production/custom-frontend.md	124	### Step 1: Initialize the Parlant Client	COMMENT
LOW	docs/production/custom-frontend.md	162	### Step 2: Create a Session	COMMENT
LOW	docs/production/custom-frontend.md	216	### Step 3: Send Customer Messages	COMMENT
LOW	docs/production/custom-frontend.md	268	### Step 4: Monitor Session Events	COMMENT
LOW	docs/production/custom-frontend.md	348	### Step 5: Display Messages in Your UI	COMMENT
LOW	docs/production/custom-frontend.md	456	### Step 6: Complete HTML Example	COMMENT
LOW	src/parlant/core/engines/alpha/relational_resolver.py	341	# Step 1: Dependencies	COMMENT
LOW	src/parlant/core/engines/alpha/relational_resolver.py	353	# Step 2: Relational prioritization (includes transitive dep filtering)	COMMENT
LOW	src/parlant/core/engines/alpha/relational_resolver.py	371	# Step 3: Numerical priority filtering.	COMMENT
LOW	src/parlant/core/engines/alpha/relational_resolver.py	393	# Step 4: Entailment.	COMMENT
LOW	…arlant/core/engines/alpha/canned_response_generator.py	2176	# Step 1: Generate the draft message	STRING
LOW	…arlant/core/engines/alpha/canned_response_generator.py	2266	# Step 2: Select the most relevant canned response templates based on the draft message	STRING
LOW	…arlant/core/engines/alpha/canned_response_generator.py	2306	# Step 3: Pre-render these templates so that matching works better	STRING
LOW	…arlant/core/engines/alpha/canned_response_generator.py	2351	# Step 5: Respond based on the match quality	STRING
LOW⚡	src/parlant/core/engines/alpha/engine.py	1243	# Step 1: Retrieve the journeys likely to be activated for this agent	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1248	# Step 2 : Retrieve all the guidelines for the context.	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1277	# Step 4: Filter the best matches out of those.	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1287	# Step 5: Filter the journeys that are activated by the matched guidelines.	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1292	# Step 6: If any of the lower-probability journeys (those originally filtered out)	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1319	# Step 7: Build the set of matched guidelines:	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1329	# Step 8: Let the plan potentially intervene	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1332	# Step 9: Resolve guideline matches by considering relationships	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1351	# Step 1: Retrieve all the possible journeys for this agent	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1356	# Step 2: Reuse the usable guidelines cached during the initial iteration.	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1360	# Step 3: Retrieve guidelines that need reevaluation based on tool calls made	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1370	# Step 4: Reevaluate those guidelines using the latest context.	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1380	# Step 5: Filter out the journeys activated by the matched guidelines.	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1388	# Step 6: If any of the journeys have been activated,	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1426	# Step 8: Let the plan potentially intervene	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1429	# Step 9: Resolve guideline matches by considering relationships	COMMENT
LOW	src/parlant/core/engines/alpha/engine.py	1262	# Step 3: Exclude guidelines whose prerequisite journeys are less likely to be activated	COMMENT
LOW	src/parlant/core/engines/alpha/engine.py	1414	# Step 7: Build the final set of matched guidelines:	COMMENT

Redundant / Tautological Comments35 hits · 50 pts

Severity	File	Line	Snippet	Context
LOW	tests/adapters/vector_db/test_qdrant.py	508	# Check if any documents were successfully migrated to new format	COMMENT
LOW	tests/adapters/db/test_mongodb.py	1106	# Check if this index includes creation_utc field	COMMENT
LOW	tests/adapters/db/test_mongodb.py	1169	# Check if this index includes creation_utc field	COMMENT
LOW	tests/adapters/db/test_mongodb.py	1210	# Check if this index includes creation_utc field	COMMENT
LOW	src/parlant/sdk.py	1768	# Check if this state has no outgoing transitions (leaf state)	COMMENT
LOW	src/parlant/sdk.py	1827	# Add target to queue for further processing	COMMENT
LOW	src/parlant/sdk.py	1873	# Check if this is a journey node guideline	COMMENT
LOW	src/parlant/sdk.py	5021	# Check if the result is a deferred callable	COMMENT
LOW	src/parlant/core/sessions.py	1551	# Check if the event has chunks property	COMMENT
LOW	src/parlant/core/sessions.py	1555	# Check if the last chunk is None (completion signal)	COMMENT
LOW	src/parlant/core/journeys.py	934	# Check if journey with this ID already exists	COMMENT
LOW	src/parlant/core/agents.py	354	# Check if agent with this ID already exists	COMMENT
LOW	src/parlant/core/customers.py	277	# Check if customer with this ID already exists	COMMENT
LOW	src/parlant/core/guidelines.py	699	# Check if guideline with this ID already exists	COMMENT
LOW	src/parlant/core/glossary.py	301	# Check if term with this ID already exists	COMMENT
LOW	…arlant/core/engines/alpha/canned_response_generator.py	709	# Check if this is the first agent message (greeting scenario)	COMMENT
LOW	…arlant/core/engines/alpha/canned_response_generator.py	2016	# Add chunk to the list and update the message	COMMENT
LOW	…t/core/engines/alpha/tool_calling/single_tool_batch.py	1284	# Check if all required parameters are present	STRING
LOW	src/parlant/core/services/tools/plugins.py	339	# Check if it's a list[Enum] type	COMMENT
LOW	src/parlant/adapters/vector_db/qdrant.py	84	# Check if it's a timeout error	COMMENT
LOW	src/parlant/adapters/vector_db/qdrant.py	331	# Check if index exists	COMMENT
LOW	src/parlant/adapters/vector_db/qdrant.py	637	# Check if collections exist	COMMENT
LOW	src/parlant/adapters/vector_db/qdrant.py	780	# Check if metadata collection exists	COMMENT
LOW	src/parlant/adapters/vector_db/mongo.py	113	# Check if the index already exists	COMMENT
LOW	src/parlant/adapters/vector_db/mongo.py	225	# Check if the collection exists in MongoDB	COMMENT
LOW	src/parlant/adapters/vector_db/chroma.py	246	# Check if we have a corresponding embedded collection for the embedder type.	COMMENT
LOW	src/parlant/adapters/nlp/vertex_service.py	776	# Check if it's a short name we recognize	COMMENT
LOW	src/parlant/adapters/nlp/mistral_service.py	350	# Check if any score indicates flagged content (threshold can be adjusted)	COMMENT
LOW	src/parlant/adapters/nlp/azure_service.py	280	# Check if API key is provided (backward compatibility)	COMMENT
LOW	src/parlant/adapters/nlp/openrouter_service.py	178	# Check if it's a JSON mode error	COMMENT
LOW	src/parlant/adapters/nlp/openrouter_service.py	234	# Check if we got empty response	COMMENT
LOW⚡	src/parlant/adapters/nlp/openrouter_service.py	247	# Check if parsed JSON is empty	COMMENT
LOW	src/parlant/adapters/nlp/openrouter_service.py	602	# Check if we have a predefined generator for this model	STRING
LOW	src/parlant/adapters/nlp/gemini_service.py	529	# Check if origin is Mapping or Sequence	STRING
LOW	src/parlant/api/sessions.py	2129	# Check if event is complete (for streaming events)	COMMENT

Verbosity Indicators34 hits · 48 pts

Severity	File	Line	Snippet	Context
LOW	tests/core/common/engines/alpha/steps/journeys.py	2076	# Step 1: Ask for account name	COMMENT
LOW	tests/core/common/engines/alpha/steps/journeys.py	2104	# Step 2: Ask for desired credit limit	COMMENT
LOW	tests/core/common/engines/alpha/steps/journeys.py	2132	# Step 3: Confirm information and move forward politely	COMMENT
LOW	tests/core/common/engines/alpha/steps/journeys.py	2161	# Step 4: Use tool to get the current limit	COMMENT
LOW	tests/core/common/engines/alpha/steps/journeys.py	2211	# Step 5: Use tool to change the limit	COMMENT
LOW	tests/core/common/engines/alpha/steps/journeys.py	2261	# Step 6: Report to customer	COMMENT
LOW	tests/core/common/engines/alpha/steps/journeys.py	2278	# Step 7: Report failure	COMMENT
LOW	src/parlant/core/engines/alpha/relational_resolver.py	341	# Step 1: Dependencies	COMMENT
LOW	src/parlant/core/engines/alpha/relational_resolver.py	353	# Step 2: Relational prioritization (includes transitive dep filtering)	COMMENT
LOW	src/parlant/core/engines/alpha/relational_resolver.py	371	# Step 3: Numerical priority filtering.	COMMENT
LOW	src/parlant/core/engines/alpha/relational_resolver.py	393	# Step 4: Entailment.	COMMENT
LOW	…arlant/core/engines/alpha/canned_response_generator.py	2176	# Step 1: Generate the draft message	STRING
LOW	…arlant/core/engines/alpha/canned_response_generator.py	2266	# Step 2: Select the most relevant canned response templates based on the draft message	STRING
LOW	…arlant/core/engines/alpha/canned_response_generator.py	2306	# Step 3: Pre-render these templates so that matching works better	STRING
LOW	…arlant/core/engines/alpha/canned_response_generator.py	2351	# Step 5: Respond based on the match quality	STRING
LOW⚡	src/parlant/core/engines/alpha/engine.py	1243	# Step 1: Retrieve the journeys likely to be activated for this agent	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1248	# Step 2 : Retrieve all the guidelines for the context.	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1277	# Step 4: Filter the best matches out of those.	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1287	# Step 5: Filter the journeys that are activated by the matched guidelines.	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1292	# Step 6: If any of the lower-probability journeys (those originally filtered out)	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1319	# Step 7: Build the set of matched guidelines:	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1329	# Step 8: Let the plan potentially intervene	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1332	# Step 9: Resolve guideline matches by considering relationships	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1351	# Step 1: Retrieve all the possible journeys for this agent	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1356	# Step 2: Reuse the usable guidelines cached during the initial iteration.	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1360	# Step 3: Retrieve guidelines that need reevaluation based on tool calls made	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1370	# Step 4: Reevaluate those guidelines using the latest context.	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1380	# Step 5: Filter out the journeys activated by the matched guidelines.	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1388	# Step 6: If any of the journeys have been activated,	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1426	# Step 8: Let the plan potentially intervene	COMMENT
LOW⚡	src/parlant/core/engines/alpha/engine.py	1429	# Step 9: Resolve guideline matches by considering relationships	COMMENT
LOW	src/parlant/core/engines/alpha/engine.py	1262	# Step 3: Exclude guidelines whose prerequisite journeys are less likely to be activated	COMMENT
LOW	src/parlant/core/engines/alpha/engine.py	1414	# Step 7: Build the final set of matched guidelines:	COMMENT
LOW	…t/core/engines/alpha/tool_calling/single_tool_batch.py	1773	"The customer wants to purchase a laptop and a mouse and we need to check if those products are available"	STRING

Modern AI Meta-Vocabulary17 hits · 41 pts

Severity	File	Line	Snippet	Context
MEDIUM	README.md	75	Parlant treats misalignment as a core design problem. It builds on [research into model accuracy and consistency](https:	CODE
MEDIUM	README.md	75	Parlant treats misalignment as a core design problem. It builds on [research into model accuracy and consistency](https:	CODE
MEDIUM	…ces/indexing/test_journey_reachable_nodes_evaluator.py	55	# Drop the few-shot examples, which render the same child/condition lines.	COMMENT
MEDIUM	docs/advanced/custom-llms.md	167	# Return the maximum number of tokens in the model's context window.	COMMENT
MEDIUM	docs/adapters/nlp/ollama.md	58	# embedding model required for creating embeddings	COMMENT
MEDIUM	docs/adapters/nlp/ollama.md	92	# Alternative embedding model (512 dimensions)	COMMENT
MEDIUM	docs/adapters/nlp/azure.md	96	# Use any embedding model (examples - check your Azure resource for availability)	COMMENT
MEDIUM	docs/adapters/nlp/azure.md	251	use CustomAzureEmbedder # Any embedding model you specify	CODE
MEDIUM	docs/adapters/nlp/azure.md	253	use AzureTextEmbedding3Large # Default embedding model	CODE
MEDIUM	docs/concepts/customization/tools.md	229	> To learn more about best-practices for designing your agent's tools, we recommend reading our blog post on [Agentic Ba	CODE
MEDIUM	docs/concepts/customization/retrievers.md	31	#### Simple RAG Example	COMMENT
MEDIUM	docs/concepts/entities/agents.md	61	> There's an interesting paper on the [failures of multi-agent systems](https://arxiv.org/abs/2503.13657#:~:text=We%20pr	CODE
MEDIUM	docs/production/agentic-design.md	106	> - [Agentic API Design blog post](https://parlant.io/blog/what-no-one-tells-you-about-agentic-api-design) - Detailed st	CODE
MEDIUM	…/engines/alpha/tool_calling/overlapping_tools_batch.py	298	if tool.parameters: # We check this because sometimes LLMs hallucinate placeholders for no-	CODE
MEDIUM	…t/core/engines/alpha/tool_calling/single_tool_batch.py	424	if tool.parameters: # We check this because sometimes LLMs hallucinate placeholders for no-param to	CODE
MEDIUM	src/parlant/adapters/nlp/openrouter_service.py	364	# Known embedding model dimensions	COMMENT
MEDIUM	src/parlant/adapters/nlp/ollama_service.py	753	else: # its a custom embedding model	CODE

Magic Placeholder Names7 hits · 38 pts

Severity	File	Line	Snippet	Context
HIGH	docs/quickstart/installation.md	70	export OPENAI_API_KEY="<YOUR_API_KEY>"	CODE
HIGH	docs/quickstart/installation.md	70	export OPENAI_API_KEY="<YOUR_API_KEY>"	CODE
HIGH	docs/adapters/vector_db/qdrant.md	51	# api_key="your-api-key-here",	COMMENT
HIGH	docs/adapters/nlp/openrouter.md	17	export OPENROUTER_API_KEY="your-api-key-here"	CODE
HIGH	docs/adapters/nlp/openrouter.md	44	export OPENROUTER_API_KEY="your-api-key-here"	CODE
HIGH	docs/adapters/nlp/openrouter.md	514	export OPENROUTER_API_KEY="your-api-key-here"	CODE
HIGH	docs/adapters/nlp/azure.md	168	export AZURE_API_KEY="your-api-key"	CODE

Modern Structural Boilerplate28 hits · 28 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_utilities.py	143	def set_level(self, log_level: LogLevel) -> None:	CODE
LOW	tests/e2e/test_utilities.py	175	def set_port(self, port: int) -> None:	CODE
LOW	scripts/version.py	36	def set_package_version(version: str, package: Package) -> None:	CODE
LOW	scripts/version.py	72	def update_version_variable_in_code(version: str) -> None:	CODE
LOW⚡	src/parlant/sdk.py	3029	async def set_value_for_customer(self, customer: Customer, value: JSONSerializable) -> None:	CODE
LOW⚡	src/parlant/sdk.py	3038	async def set_value_for_tag(self, tag: TagId, value: JSONSerializable) -> None:	CODE
LOW⚡	src/parlant/sdk.py	3047	async def set_global_value(self, value: JSONSerializable) -> None:	CODE
LOW⚡	src/parlant/sdk.py	3056	async def set_value_for_agent(self, agent: Agent, value: JSONSerializable) -> None:	CODE
LOW	src/parlant/sdk.py	657	def _set_progress(self, key: str, pct: float) -> None:	CODE
LOW	src/parlant/sdk.py	4932	async def _setup_retrievers(self) -> None:	CODE
LOW	src/parlant/sdk.py	5785	__all__ = [	CODE
LOW	src/parlant/core/loggers.py	105	def set_level(self, log_level: LogLevel) -> None:	CODE
LOW	src/parlant/core/loggers.py	184	def set_level(self, log_level: LogLevel) -> None:	CODE
LOW	src/parlant/core/loggers.py	290	def set_level(self, log_level: LogLevel) -> None:	CODE
LOW	src/parlant/core/tracer.py	65	def set_attribute(self, name: str, value: AttributeValue) -> None: ...	CODE
LOW	src/parlant/core/health/__init__.py	42	__all__ = [	CODE
LOW	…ant/core/engines/alpha/perceived_performance_policy.py	287	def set_policy(self, agent_id: AgentId, policy: PerceivedPerformancePolicy) -> None:	CODE
LOW	…arlant/core/engines/alpha/canned_response_generator.py	557	def set_preamble_config(self, agent_id: AgentId, config: PreambleConfiguration) -> None:	STRING
LOW	src/parlant/core/engines/alpha/engine.py	827	async def _update_session_mode(self, context: EngineContext) -> None:	CODE
LOW	src/parlant/core/engines/alpha/engine.py	1043	async def _update_session_labels(self, context: EngineContext) -> None:	CODE
LOW	src/parlant/core/engines/alpha/planners.py	212	def set_planner(self, agent_id: AgentId, planner: Planner) -> None:	CODE
LOW	…core/services/indexing/behavioral_change_evaluation.py	740	async def _update_progress(percentage: float) -> None:	CODE
LOW⚡	src/parlant/bin/client.py	2772	def update_customer(ctx: click.Context, customer_id: str, name: str) -> None:	CODE
LOW⚡	src/parlant/bin/client.py	2892	def update_tag(ctx: click.Context, tag: str, name: str) -> None:	CODE
LOW	src/parlant/bin/client.py	104	def set_exit_status(status: int) -> None:	CODE
LOW	src/parlant/adapters/loggers/opentelemetry.py	90	def set_level(self, log_level: LogLevel) -> None:	CODE
LOW	src/parlant/adapters/vector_db/qdrant.py	442	async def _set_collection_version(self, collection_name: str, version: int) -> None:	CODE
LOW	src/parlant/adapters/db/snowflake_db.py	767	__all__ = [	STRING

AI Structural Patterns39 hits · 24 pts

Severity	File	Line	Context
LOW	tests/test_utilities.py	652	CODE
LOW	…ts/core/stable/engines/alpha/test_guideline_matcher.py	648	CODE
LOW	src/parlant/sdk.py	1902	CODE
LOW	src/parlant/sdk.py	1472	CODE
LOW	src/parlant/sdk.py	2010	CODE
LOW	src/parlant/sdk.py	2027	CODE
LOW	src/parlant/sdk.py	2044	CODE
LOW	src/parlant/sdk.py	2061	CODE
LOW	src/parlant/sdk.py	2085	CODE
LOW	src/parlant/sdk.py	2141	CODE
LOW	src/parlant/sdk.py	2158	CODE
LOW	src/parlant/sdk.py	2175	CODE
LOW	src/parlant/sdk.py	2192	CODE
LOW	src/parlant/sdk.py	2216	CODE
LOW	src/parlant/sdk.py	2275	CODE
LOW	src/parlant/sdk.py	2292	CODE
LOW	src/parlant/sdk.py	2309	CODE
LOW	src/parlant/sdk.py	2326	CODE
LOW	src/parlant/sdk.py	2350	CODE
LOW	src/parlant/sdk.py	2425	CODE
LOW	src/parlant/sdk.py	2442	CODE
LOW	src/parlant/sdk.py	2459	CODE
LOW	src/parlant/sdk.py	2483	CODE
LOW	src/parlant/sdk.py	2711	CODE
LOW	src/parlant/sdk.py	2763	CODE
LOW	src/parlant/sdk.py	3405	CODE
LOW	src/parlant/sdk.py	3476	CODE
LOW	src/parlant/sdk.py	3528	CODE
LOW	src/parlant/sdk.py	4178	CODE
LOW	src/parlant/sdk.py	5121	CODE
LOW	src/parlant/sdk.py	5358	CODE
LOW	src/parlant/core/entity_cq.py	278	CODE
LOW	src/parlant/core/guidelines.py	101	CODE
LOW	src/parlant/core/guidelines.py	674	CODE
LOW	src/parlant/core/health/nlp_view.py	94	CODE
LOW	src/parlant/core/app_modules/context_variables.py	155	CODE
LOW	src/parlant/core/app_modules/customers.py	88	CODE
LOW	src/parlant/bin/client.py	1045	CODE
LOW	src/parlant/adapters/db/mongo_db.py	269	CODE

Fake / Example Data21 hits · 22 pts

Severity	File	Line	Snippet	Context
LOW	tests/adapters/db/test_mongodb.py	392	{"id": "dummy_id", "version": "1.0.0", "name": "Test Document"}	CODE
LOW	tests/adapters/db/test_json_file.py	405	"id": "dummy_id",	CODE
LOW⚡	tests/sdk/test_customers.py	23	name="John Doe", metadata={"email": "john.doe@example.com"}	CODE
LOW⚡	tests/sdk/test_customers.py	31	assert customer.name == "John Doe"	CODE
LOW⚡	tests/sdk/test_customers.py	39	name="John Doe",	CODE
LOW⚡	tests/sdk/test_customers.py	58	name="John Doe",	CODE
LOW⚡	tests/sdk/test_customers.py	65	self.customer = await server.find_customer(name="John Doe")	CODE
LOW⚡	tests/sdk/test_customers.py	75	name="John Doe",	CODE
LOW	tests/sdk/test_variables.py	78	self.customer = await server.create_customer("John Doe")	CODE
LOW	tests/sdk/test_variables.py	187	self.customer = await server.create_customer("Jane Doe")	CODE
LOW	tests/sdk/test_variables.py	244	self.customer = await server.create_customer("Jane Doe")	CODE
LOW	tests/sdk/test_variables.py	286	"Jane Doe",	CODE
LOW	tests/api/test_sessions.py	1812	"participant": {"id": "agent_007", "display_name": "John Doe"},	CODE
LOW	tests/api/test_sessions.py	1823	assert event["data"]["participant"]["display_name"] == "John Doe"	CODE
LOW	tests/api/test_customers.py	29	name = "John Doe"	CODE
LOW	tests/api/test_customers.py	60	"name": "John Doe",	CODE
LOW	tests/modules/bank.py	33	return ToolResult({"name": "John Doe", "account_number": "1234567890"})	CODE
LOW	…ng/generic/journey/journey_backtrack_node_selection.py	1428	_make_event("3", EventSource.CUSTOMER, "Jane Doe"),	STRING
LOW	src/parlant/api/sessions.py	321	examples=["John Doe", "Alice"],	CODE
LOW	src/parlant/api/sessions.py	328	"display_name": "John Doe",	CODE
LOW	src/parlant/api/sessions.py	415	"participant": {"id": "cust_123xy", "display_name": "John Doe"},	CODE

Cross-Language Confusion5 hits · 22 pts

Severity	File	Line	Snippet	Context
HIGH	tests/sdk/utils.py	113	"""Check if the event is still streaming (chunks property exists and not yet terminated with null)."""	STRING
HIGH	scripts/version.py	136	"git diff --quiet && git diff --cached --quiet && git ls-files --others --exclude-standard"	CODE
HIGH	…arlant/core/engines/alpha/canned_response_generator.py	1467	If told so by a guideline or some other contextual condition, send the first message. Otherwise, do not produce a reply	CODE
HIGH	…arlant/core/engines/alpha/canned_response_generator.py	1473	"response_preamble_that_was_already_sent": null,	CODE
HIGH	…arlant/core/engines/alpha/canned_response_generator.py	1486	The only exception where you may not produce a reply (i.e., setting message = null) is if the user, or a provided guidel	CODE

Hallucination Indicators2 hits · 20 pts

Severity	File	Line	Snippet	Context
CRITICAL	src/parlant/adapters/nlp/azure_service.py	144	response = await self._client.beta.chat.completions.parse(	CODE
CRITICAL	src/parlant/adapters/nlp/openai_service.py	200	response = await self._client.beta.chat.completions.parse(	CODE

AI Slop Vocabulary4 hits · 5 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/sdk/test_sdk_validation.py	581	"""Test comprehensive condition validation for ForkJourneyState"""	STRING
LOW	src/parlant/core/journeys.py	1366	# Journey not found, just return node as-is	COMMENT
MEDIUM	…arlant/core/engines/alpha/canned_response_generator.py	1889	# Build recap section to leverage LLM recency bias	STRING
LOW	src/parlant/api/sessions.py	2137	# Non-streaming event, just return it once	COMMENT

Docstring Block Structure1 hit · 5 pts

Severity	File	Line	Snippet	Context
HIGH	src/parlant/adapters/vector_db/qdrant.py	63	Retry an async operation on timeout errors with exponential backoff. Args: operation: The async operat	STRING

Slop Phrases1 hit · 0 pts

Severity	File	Line	Snippet	Context
LOW	src/parlant/core/engines/alpha/prompt_builder.py	326	return f"\nIMPORTANT: Please note that the last message was sent by you, the AI agent (likely as a preamble). Yo	STRING

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings