pipecat-ai/pipecat

36.4

Adjusted Score

36.4

Raw Score

100%

Time Factor

2026-08-28

Last Push

14.9K

Stars

Python

Language

382.2K

Lines of Code

1.4K

Files

8.2K

Pattern Hits

2026-08-29

Scan Date

0.80

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 14HIGH 1149MEDIUM 603LOW 6442

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 8208 distinct pattern matches across 26 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.

Cross-File Repetition1057 hits · 5285 pts

Severity	File	Line	Snippet	Context
HIGH	CHANGELOG.md	0	write a long research report on a topic. args: topic: what the report should cover.	STRING
HIGH	…ion-calling/function-calling-openai-responses-async.py	0	write a long research report on a topic. args: topic: what the report should cover.	STRING
HIGH	…ples/function-calling/function-calling-google-async.py	0	write a long research report on a topic. args: topic: what the report should cover.	STRING
HIGH	…ples/function-calling/function-calling-openai-async.py	0	write a long research report on a topic. args: topic: what the report should cover.	STRING
HIGH	…s/function-calling/function-calling-anthropic-async.py	0	write a long research report on a topic. args: topic: what the report should cover.	STRING
HIGH	CONTRIBUTING.md	0	get the output audio sample rate. returns: the output sample rate in hz.	STRING
HIGH	src/pipecat/transports/base_input.py	0	get the output audio sample rate. returns: the output sample rate in hz.	STRING
HIGH	src/pipecat/transports/base_output.py	0	get the output audio sample rate. returns: the output sample rate in hz.	STRING
HIGH	src/pipecat/transports/lemonslice/transport.py	0	get the output audio sample rate. returns: the output sample rate in hz.	STRING
HIGH	src/pipecat/transports/tavus/transport.py	0	get the output audio sample rate. returns: the output sample rate in hz.	STRING
HIGH	src/pipecat/services/heygen/client.py	0	get the output audio sample rate. returns: the output sample rate in hz.	STRING
HIGH	src/pipecat/transports/daily/transport.py	0	get the output audio sample rate. returns: the output sample rate in hz.	STRING
HIGH	src/pipecat/audio/vad/vad_analyzer.py	0	get the output audio sample rate. returns: the output sample rate in hz.	STRING
HIGH	COMMUNITY_INTEGRATIONS.md	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/lmnt/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/cartesia/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/cartesia/turns/stt.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/inworld/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/asyncai/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/speechmatics/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/azure/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/rime/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/google/stt.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/google/gemini_live/stt.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/speechify/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/soniox/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/soniox/stt.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/deepgram/stt.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/deepgram/flux/stt_base.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/deepgram/sagemaker/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/deepgram/sagemaker/stt.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/camb/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/groq/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/tavus/video.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/smallest/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/minimax/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/elevenlabs/tts_base.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/elevenlabs/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/neuphonic/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/gradium/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/piper/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/nvidia/sagemaker/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/nvidia/sagemaker/stt.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/bland/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/resembleai/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/sarvam/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/sarvam/stt.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/xtts/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/aws/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/fish/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/mistral/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/openai/tts.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/openai/base_llm.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	src/pipecat/services/openai/stt.py	0	check if this service can generate processing metrics. returns: true, as fish audio service supports metrics generation.	STRING
HIGH	tests/test_deepgram_tts.py	0	build the exception `websockets` raises when a handshake is rejected.	STRING
HIGH	tests/test_websocket_service_usable.py	0	build the exception `websockets` raises when a handshake is rejected.	STRING
HIGH	tests/test_processor_usable.py	0	build the exception `websockets` raises when a handshake is rejected.	STRING
HIGH	tests/test_cartesia_stt.py	0	build the exception `websockets` raises when a handshake is rejected.	STRING
HIGH	tests/test_auto_register_tools.py	0	get a restaurant recommendation. args: location: the city and state, e.g. "san francisco, ca".	STRING
HIGH	examples/function-calling/function-calling-cerebras.py	0	get a restaurant recommendation. args: location: the city and state, e.g. "san francisco, ca".	STRING
997 more matches not shown…

Hyper-Verbose Identifiers4933 hits · 4621 pts

Severity	File	Line	Snippet	Context
LOW	CHANGELOG.md	13601	async def on_conversation_item_created(llm, item_id, item):	CODE
LOW	CHANGELOG.md	13605	async def on_conversation_item_updated(llm, item_id, item):	CODE
LOW⚡	tests/test_async_tool_messages.py	61	def test_parses_completed_sentinel_result(self):	CODE
LOW⚡	tests/test_async_tool_messages.py	70	def test_returns_none_for_regular_user_message(self):	CODE
LOW⚡	tests/test_async_tool_messages.py	73	def test_returns_none_for_regular_assistant_message(self):	CODE
LOW⚡	tests/test_async_tool_messages.py	76	def test_returns_none_for_regular_tool_message(self):	CODE
LOW⚡	tests/test_async_tool_messages.py	91	def test_returns_none_for_developer_message_without_payload(self):	CODE
LOW⚡	tests/test_async_tool_messages.py	100	def test_returns_none_for_invalid_json_content(self):	CODE
LOW⚡	tests/test_async_tool_messages.py	103	def test_returns_none_for_non_dict_json(self):	CODE
LOW⚡	tests/test_async_tool_messages.py	106	def test_returns_none_for_wrong_payload_type(self):	CODE
LOW	tests/test_async_tool_messages.py	117	def test_returns_none_when_tool_call_id_missing(self):	CODE
LOW	tests/test_async_tool_messages.py	128	def test_returns_none_when_status_invalid(self):	CODE
LOW⚡	tests/test_async_tool_messages.py	141	def test_returns_none_for_non_string_content(self):	CODE
LOW⚡	tests/test_async_tool_messages.py	150	def test_returns_none_for_missing_role(self):	CODE
LOW⚡	tests/test_async_tool_messages.py	157	def test_started_message_shape(self):	CODE
LOW	tests/test_async_tool_messages.py	170	def test_intermediate_message_shape(self):	CODE
LOW	tests/test_async_tool_messages.py	194	def test_final_message_with_completed_sentinel(self):	CODE
LOW	tests/test_async_tool_messages.py	207	def test_cancelled_message_shape(self):	CODE
LOW	tests/test_async_tool_messages.py	218	def test_cancelled_round_trip(self):	CODE
LOW	tests/test_async_tool_messages.py	238	def test_intermediate_round_trip(self):	CODE
LOW	tests/test_ttfb_metrics.py	36	async def test_reports_a_normal_interval(self):	CODE
LOW	tests/test_ttfb_metrics.py	50	async def test_does_not_report_output_that_predates_the_request(self):	CODE
LOW	tests/test_ttfb_metrics.py	59	async def test_a_refused_measurement_does_not_linger(self):	CODE
LOW	tests/test_ttfb_metrics.py	74	async def test_reports_nothing_when_no_measurement_is_running(self):	CODE
LOW	tests/test_ttfb_metrics.py	105	async def test_measures_to_the_last_transcript(self, service):	CODE
LOW	tests/test_ttfb_metrics.py	114	async def test_a_transcript_from_before_speech_ended_reports_nothing(self, service):	CODE
LOW	tests/test_ttfb_metrics.py	134	async def test_an_utterance_with_no_transcript_at_all_reports_nothing(self, service):	CODE
LOW	tests/test_ttfb_metrics.py	143	async def test_an_utterance_with_no_transcript_closes_the_measurement(self, service):	CODE
LOW	tests/test_nova_sonic_usage_metrics.py	36	def test_can_generate_metrics(self):	CODE
LOW	tests/test_nova_sonic_usage_metrics.py	41	async def test_usage_event_reports_collapsed_delta(self):	CODE
LOW	tests/test_nova_sonic_usage_metrics.py	71	async def test_usage_event_with_no_tokens_is_skipped(self):	CODE
LOW	tests/test_nova_sonic_usage_metrics.py	92	async def test_usage_event_with_missing_details_is_safe(self):	CODE
LOW⚡	tests/test_openai_realtime_reasoning.py	32	def test_session_properties_accepts_reasoning_object():	CODE
LOW⚡	tests/test_openai_realtime_reasoning.py	38	def test_session_properties_coerces_reasoning_dict():	CODE
LOW⚡	tests/test_openai_realtime_reasoning.py	45	def test_reasoning_accepts_future_effort_strings():	CODE
LOW⚡	tests/test_openai_realtime_reasoning.py	51	def test_reasoning_serializes_into_session_update():	CODE
LOW	tests/test_openai_realtime_reasoning.py	89	async def test_outgoing_session_update_strips_reasoning_on_unsupported_model():	CODE
LOW	tests/test_openai_realtime_reasoning.py	119	async def test_outgoing_session_update_keeps_reasoning_on_supported_model():	CODE
LOW	tests/test_openai_realtime_reasoning.py	143	async def test_supported_model_variant_keeps_reasoning():	CODE
LOW	tests/test_openai_realtime_reasoning.py	168	async def test_no_warning_when_reasoning_is_unset_on_unsupported_model():	CODE
LOW⚡	tests/test_openai_realtime_reasoning.py	193	async def test_runtime_settings_update_with_reasoning_triggers_session_update():	CODE
LOW	tests/test_openai_realtime_reasoning.py	224	async def test_runtime_settings_update_strips_reasoning_on_unsupported_model():	CODE
LOW	tests/test_markdown_text_filter.py	17	async def test_basic_markdown_removal(self):	CODE
LOW	tests/test_markdown_text_filter.py	59	async def test_repeated_character_removal(self):	STRING
LOW	tests/test_markdown_text_filter.py	81	async def test_preserve_repeated_characters(self):	CODE
LOW	tests/test_markdown_text_filter.py	96	async def test_numbered_list_preservation(self):	CODE
LOW	tests/test_markdown_text_filter.py	113	async def test_html_entity_conversion(self):	CODE
LOW	tests/test_markdown_text_filter.py	167	async def test_numbered_list_marker_handling(self):	CODE
LOW	tests/test_markdown_text_filter.py	185	async def test_inline_code_handling(self):	CODE
LOW	tests/test_markdown_text_filter.py	199	async def test_simple_table_removal(self):	CODE
LOW	tests/test_markdown_text_filter.py	283	async def test_closed_atx_header_stripping(self):	CODE
LOW	tests/test_markdown_text_filter.py	300	async def test_header_trailing_space_preserved(self):	CODE
LOW	tests/test_markdown_text_filter.py	318	async def test_hash_in_content_not_treated_as_header(self):	CODE
LOW	tests/test_shared.py	71	async def test_only_the_first_owner_runs_the_body(self):	CODE
LOW	tests/test_shared.py	78	async def test_later_owners_wait_for_the_first(self):	CODE
LOW	tests/test_shared.py	90	async def test_only_the_last_owner_undoes_it(self):	CODE
LOW	tests/test_shared.py	101	async def test_release_without_acquire_does_nothing(self):	CODE
LOW	tests/test_shared.py	109	async def test_resources_are_counted_separately(self):	CODE
LOW⚡	tests/test_shared.py	124	async def test_instances_count_their_own_owners(self):	CODE
LOW⚡	tests/test_shared.py	134	async def test_first_owner_gets_the_return_value(self):	CODE
4873 more matches not shown…

Decorative Section Separators384 hits · 1323 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tests/test_openai_realtime_reasoning.py	27	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_realtime_reasoning.py	29	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_realtime_reasoning.py	58	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_realtime_reasoning.py	60	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_realtime_reasoning.py	187	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_realtime_reasoning.py	189	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_moq_transport.py	469	# ----------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_moq_transport.py	471	# ----------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_moq_transport.py	709	# ----------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_moq_transport.py	711	# ----------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_moq_transport.py	57	# ----------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_moq_transport.py	59	# ----------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_moq_transport.py	154	# ----------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_moq_transport.py	156	# ----------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_moq_transport.py	372	# ----------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_moq_transport.py	374	# ----------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_service_init.py	59	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_service_init.py	61	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_service_init.py	90	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_service_init.py	92	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_service_init.py	138	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_service_init.py	140	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_service_init.py	161	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_service_init.py	163	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_openai_realtime_audio_frames.py	31	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_openai_realtime_audio_frames.py	33	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_realtime_audio_frames.py	152	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_realtime_audio_frames.py	154	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_realtime_audio_frames.py	193	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_realtime_audio_frames.py	195	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_realtime_audio_frames.py	225	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_realtime_audio_frames.py	227	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_realtime_audio_frames.py	279	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_realtime_audio_frames.py	281	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_realtime_audio_frames.py	322	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_realtime_audio_frames.py	324	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_openai_realtime_usage_metrics.py	26	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_openai_realtime_usage_metrics.py	28	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_openai_realtime_usage_metrics.py	112	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_openai_realtime_usage_metrics.py	114	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_elevenlabs_tts.py	275	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_elevenlabs_tts.py	282	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_elevenlabs_tts.py	411	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_elevenlabs_tts.py	418	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_service_language.py	71	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_service_language.py	73	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_service_language.py	118	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_service_language.py	120	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_service_language.py	160	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_service_language.py	162	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_service_language.py	207	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_service_language.py	209	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_service_language.py	24	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_service_language.py	26	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_responses_http.py	138	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_responses_http.py	140	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_responses_http.py	239	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_responses_http.py	241	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_responses_http.py	529	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_responses_http.py	531	# ---------------------------------------------------------------------------	COMMENT
324 more matches not shown…

Excessive Try-Catch Wrapping656 hits · 688 pts

Severity	File	Line	Snippet	Context
LOW	COMMUNITY_INTEGRATIONS.md	627	except Exception as e:	CODE
LOW⚡	tests/test_service_init.py	80	except Exception:	CODE
LOW⚡	tests/test_service_init.py	175	except Exception:	CODE
LOW	tests/test_pgmq_bus.py	30	except Exception:	CODE
LOW	tests/test_fastapi_websocket.py	176	except Exception:	CODE
MEDIUM	tests/test_fastapi_websocket.py	172	def receive_loop():	CODE
LOW⚡	tests/test_pgmq_backends.py	35	except Exception:	CODE
LOW	tests/openclaw_fake_gateway.py	143	except Exception:	CODE
LOW	tests/test_redis_bus.py	27	except Exception:	CODE
LOW	docs/api/conf.py	355	except Exception as e:	CODE
LOW	examples/transcription/transcription-google-llm.py	187	except Exception as e:	STRING
LOW	examples/features/features-gpu-container-local-bot.py	153	except Exception as e:	CODE
MEDIUM	examples/features/features-gpu-container-local-bot.py	135	def on_app_message(transport, message, sender):	CODE
LOW	examples/multi-worker/code-assistant/code_worker.py	84	except Exception as e:	CODE
LOW	examples/multi-worker/code-assistant/code_worker.py	106	except Exception as e:	CODE
LOW	examples/rag/rag-mem0.py	99	except Exception as e:	CODE
LOW	examples/realtime/realtime-gemini-live-files-api.py	155	except Exception as e:	STRING
LOW	examples/realtime/realtime-gemini-live-files-api.py	228	except Exception as e:	STRING
LOW	examples/realtime/realtime-gemini-live-files-api.py	235	except Exception as e:	STRING
LOW	examples/voice/voice-aws-strands.py	110	except Exception as e:	CODE
LOW	…les/persistent-context/persistent-context-anthropic.py	86	except Exception as e:	CODE
LOW	…les/persistent-context/persistent-context-anthropic.py	104	except Exception as e:	CODE
LOW	…sistent-context/persistent-context-openai-responses.py	86	except Exception as e:	CODE
LOW	…sistent-context/persistent-context-openai-responses.py	105	except Exception as e:	CODE
LOW	…amples/persistent-context/persistent-context-gemini.py	115	except Exception as e:	CODE
LOW	…amples/persistent-context/persistent-context-gemini.py	136	except Exception as e:	CODE
LOW	…rsistent-context/persistent-context-openai-realtime.py	90	except Exception as e:	CODE
LOW	…rsistent-context/persistent-context-openai-realtime.py	113	except Exception as e:	CODE
LOW	…amples/persistent-context/persistent-context-openai.py	86	except Exception as e:	CODE
LOW	…amples/persistent-context/persistent-context-openai.py	105	except Exception as e:	CODE
LOW	…nt-context/persistent-context-openai-responses-http.py	86	except Exception as e:	CODE
LOW	…nt-context/persistent-context-openai-responses-http.py	105	except Exception as e:	CODE
LOW	…ersistent-context/persistent-context-aws-nova-sonic.py	106	except Exception as e:	CODE
LOW	…ersistent-context/persistent-context-aws-nova-sonic.py	143	except Exception as e:	CODE
LOW	…persistent-context/persistent-context-grok-realtime.py	90	except Exception as e:	CODE
LOW	…persistent-context/persistent-context-grok-realtime.py	109	except Exception as e:	CODE
LOW	…urn-management/turn-management-user-assistant-turns.py	78	except Exception as e:	CODE
LOW	scripts/check_licenses.py	108	except Exception as e: # noqa: BLE001 — retry any fetch/parse hiccup	CODE
LOW	scripts/cli/configs/config_generator.py	112	except Exception as e:	CODE
LOW	scripts/cli/configs/config_generator.py	280	except Exception as e:	CODE
LOW	scripts/daily/mock_tavus_server.py	213	except Exception as e:	CODE
MEDIUM	scripts/daily/mock_tavus_server.py	21	def set_result(future, *args):	CODE
LOW	scripts/provider-watch/probe.py	467	except Exception as e: # constructor rejected something — that is a finding	CODE
LOW	scripts/provider-watch/probe.py	493	except Exception as e:	CODE
LOW	scripts/provider-watch/probe.py	670	except Exception as e:	CODE
LOW	scripts/provider-watch/probe.py	726	except Exception as e: # network or unknown package	CODE
LOW	scripts/provider-watch/inventory.py	315	except Exception:	CODE
MEDIUM	scripts/provider-watch/inventory.py	311	def _registry_by_class() -> dict[str, dict]:	CODE
MEDIUM	scripts/krisp/test_krisp_viva_filter_audiofile.py	31	print(f"Error: Missing required dependencies: {e}")	CODE
MEDIUM	scripts/krisp/test_krisp_viva_filter_audiofile.py	47	print(f"Error: Could not import Krisp VIVA filter: {e}")	CODE
MEDIUM	scripts/krisp/test_krisp_viva_filter_audiofile.py	58	print(f"Error: {env_var} environment variable not set")	CODE
MEDIUM	scripts/krisp/test_krisp_viva_filter_audiofile.py	64	print(f"Error: Model file not found: {model_path}")	CODE
MEDIUM	scripts/krisp/test_krisp_viva_filter_audiofile.py	83	print(f"Error: TTS model file not found: {path}")	CODE
MEDIUM	scripts/krisp/test_krisp_viva_filter_audiofile.py	258	print("Error: No filtered audio produced")	CODE
MEDIUM	scripts/krisp/test_krisp_viva_filter_audiofile.py	341	print(f"Error: Input file not found: {args.input}")	STRING
MEDIUM	scripts/krisp/test_krisp_viva_turn_audiofile.py	29	print(f"Error: Missing required dependencies: {e}")	CODE
MEDIUM	scripts/krisp/test_krisp_viva_turn_audiofile.py	45	print(f"Error: Could not import Krisp VIVA turn analyzer: {e}")	CODE
MEDIUM	scripts/krisp/test_krisp_viva_turn_audiofile.py	56	print(f"Error: {env_var} environment variable not set")	CODE
MEDIUM	scripts/krisp/test_krisp_viva_turn_audiofile.py	62	print(f"Error: Model file not found: {model_path}")	CODE
MEDIUM	scripts/krisp/test_krisp_viva_turn_audiofile.py	311	print(f"Error: Input file not found: {args.input}")	STRING
596 more matches not shown…

Docstring Block Structure75 hits · 375 pts

Severity	File	Line	Snippet	Context
HIGH	.claude/skills/docstring/SKILL.md	136	One-line summary of what method does. [Longer description if behavior isn't obvious.] Args: param1: De	STRING
HIGH	.claude/skills/cleanup/SKILL.md	104	Process incoming data with optional configuration. Args: data: The input data to process. options:	STRING
HIGH	examples/flows/utils.py	18	Create an LLM service instance based on environment configuration. Args: provider: LLM provider name. If No	STRING
HIGH	scripts/krisp/audio_file_utils.py	14	Read an audio file and convert to int16 mono format. This function: - Detects the audio format from the file he	STRING
HIGH	src/pipecat/pipeline/job_context.py	72	Fold the deprecated per-argument job spelling into a params object. Dispatch methods accept a params object and, un	STRING
HIGH	src/pipecat/evals/services.py	28	Coerce a config's optional ``language`` value to a :class:`Language`. ``Language`` is a ``StrEnum``, so both a code	STRING
HIGH	src/pipecat/evals/scenario.py	445	Parse a scenario YAML file into an :class:`EvalScenario`. Args: path: Path to a YAML file with the	STRING
HIGH	src/pipecat/evals/judge.py	138	Build an :class:`EvalJudge` from a scenario's ``judge.eval:`` config block. Honors a custom ``factory`` (dotted	STRING
HIGH	src/pipecat/runner/run.py	1581	Parse ICE server configuration into a list of plain dictionaries. Accepts either the raw ``PIPECAT_ICE_SERVERS`` en	STRING
HIGH	src/pipecat/runner/utils.py	114	Parse telephony WebSocket messages and return transport type and call data. Args: websocket: FastAPI WebSoc	STRING
HIGH	src/pipecat/runner/utils.py	463	Get transport parameters from factory function. Args: transport_key: The transport key to look up t	STRING
HIGH	src/pipecat/runner/utils.py	601	Create a transport from runner arguments using factory functions. This function uses the clean transport_params fac	STRING
HIGH	src/pipecat/runner/daily.py	93	Configure Daily room URL and token with optional SIP capabilities. This function will either: 1. Use an existin	STRING
HIGH	src/pipecat/runner/livekit.py	144	Configure LiveKit room with command-line argument parsing. Args: parser: Optional argument parser. If None,	STRING
HIGH	src/pipecat/transports/lemonslice/api.py	55	Create a new session with the specified agent_id, agent_image_url, or agent_image. Args: agent_imag	STRING
HIGH	src/pipecat/transports/smallwebrtc/transport.py	102	Add audio bytes to the buffer for transmission. Args: audio_bytes: Raw audio data to queue for tran	STRING
HIGH	src/pipecat/transports/smallwebrtc/transport.py	265	Convert a video frame to RGB format based on the input format. Args: frame_array: The input frame a	STRING
HIGH	src/pipecat/transports/smallwebrtc/request_handler.py	165	Handle a SmallWebRTC request and resolve the pending answer. This method will: - Reuse an existing We	STRING
HIGH	src/pipecat/transports/daily/utils.py	272	Create a new Daily room. Args: params: Room configuration parameters. Returns:	STRING
HIGH	src/pipecat/transports/daily/utils.py	309	Generate a meeting token for user to join a Daily room. Args: room_url: Daily room URL.	STRING
HIGH	src/pipecat/transports/daily/utils.py	378	Delete a room using its name. Args: room_name: Name of the room to delete. Returns:	STRING
HIGH	src/pipecat/transports/livekit/utils.py	68	Delete a LiveKit room by name. This will forcibly disconnect all participants currently in the room. A	STRING
HIGH	src/pipecat/transports/whatsapp/client.py	132	Handle a verify webhook request from WhatsApp. Args: params: Dictionary containing webhook paramete	STRING
HIGH	src/pipecat/transports/whatsapp/client.py	193	Handle a webhook request from WhatsApp. This method processes incoming webhook requests and handles both	STRING
HIGH	src/pipecat/transports/whatsapp/client.py	318	Handle a CONNECT event by establishing WebRTC connection and accepting the call. This method: 1. Create	STRING
HIGH	src/pipecat/tests/utils.py	137	Run a test pipeline with the specified processor and validate frame flow. This function creates a test pipeline wit	STRING
HIGH	src/pipecat/utils/types.py	78	Extract a value that must have been provided. Intended for reads where ``NOT_GIVEN`` should never appear, such as a	STRING
HIGH	src/pipecat/utils/asyncio/task_manager.py	173	Creates and schedules a new asyncio Task that runs the given coroutine. The task is added to a global set of cr	STRING
HIGH	src/pipecat/cli/registry/service_loader.py	18	Extract the extra names from a package string. Args: package: Package string like "pipecat-ai[deepgram]", "	STRING
HIGH	src/pipecat/cli/generators/project.py	76	Generate the complete project structure. Args: output_dir: Optional directory to create project in	STRING
HIGH	src/pipecat/adapters/services/gemini_adapter.py	103	Recursively adapt a JSON schema to the subset Gemini accepts. Tool schemas are JSON Schema, but Gemini take	STRING
HIGH	src/pipecat/adapters/services/gemini_adapter.py	395	Convert standard universal context message to Google Content object. Handles conversion of text, images, and fu	STRING
HIGH	src/pipecat/adapters/services/bedrock_adapter.py	210	Convert standard format message to AWS Bedrock format. Handles conversion of text content, tool calls, and tool	STRING
HIGH	src/pipecat/adapters/services/anthropic_adapter.py	294	Convert standard universal context message to Anthropic format. Handles conversion of text content, tool calls,	STRING
HIGH	src/pipecat/serializers/telnyx.py	128	Serializes a Pipecat frame to Telnyx WebSocket format. Handles conversion of various frame types to Telnyx WebS	STRING
HIGH	src/pipecat/serializers/telnyx.py	237	Deserializes Telnyx WebSocket data to Pipecat frames. Handles conversion of Telnyx media events to appropriate	STRING
HIGH	src/pipecat/serializers/genesys.py	315	Create a protocol message with common fields. Based on the Genesys AudioHook protocol, responses include:	STRING
HIGH	src/pipecat/audio/utils.py	164	Calculate the loudness level of audio data using ITU-R BS.1770. Args: audio: Audio data as raw bytes (16-bi	STRING
HIGH	src/pipecat/audio/krisp_instance.py	44	Convert integer sample rate to Krisp SDK enum value. Args: sample_rate: Sample rate in Hz (e.g., 16000, 240	STRING
HIGH	src/pipecat/audio/krisp_instance.py	64	Convert integer frame duration to Krisp SDK enum value. Args: frame_duration_ms: Frame duration in millisec	STRING
HIGH	src/pipecat/audio/filters/aic_filter.py	131	Get or load a Model and increment its reference count. Call this when starting a filter. Store the returned key	STRING
HIGH	src/pipecat/audio/turn/krisp_viva_turn.py	162	Create a turn detection session with the specified sample rate. Args: sample_rate: Sample rate for	STRING
HIGH	src/pipecat/audio/vad/krisp_viva_vad.py	95	Create a Krisp VAD session with a specific sample rate. Args: sample_rate: Sample rate for the sess	STRING
HIGH	src/pipecat/transcriptions/language.py	586	Resolve a Language enum to a service-specific language code. Checks the language map first, then falls back to extr	STRING
HIGH	src/pipecat/workers/base_worker.py	1050	Wait for workers to be ready, create a job group, and send requests. Waits for all workers to be registered as	STRING
HIGH	src/pipecat/flows/manager.py	293	Initialize the flow manager. Args: initial_node: Optional initial node configuration. If provided,	STRING
HIGH	src/pipecat/services/llm_service.py	813	Generate a compressed summary of conversation context. Uses the message selection logic to identify which messa	STRING
HIGH	src/pipecat/services/settings.py	142	Merge a delta-mode object into this store-mode object. Only fields in delta that are given (i.e. not ``NO	STRING
HIGH	src/pipecat/services/settings.py	192	Build a delta-mode settings object from a plain dictionary. This exists for backward compatibility with cod	STRING
HIGH	src/pipecat/services/inworld/realtime/events.py	870	Parse a server event from JSON. Args: data: JSON text containing the server event, as delivered by the	STRING
HIGH	src/pipecat/services/google/tts.py	693	Create authenticated Google Text-to-Speech client. Args: credentials: JSON string with service acco	STRING
HIGH	src/pipecat/services/google/tts.py	902	Create authenticated Google Text-to-Speech client. Args: credentials: JSON string with service acco	STRING
HIGH	src/pipecat/services/google/llm.py	557	Yield the model's streamed chunks, re-issuing the request once if it stalls. The API client sends the request l	STRING
HIGH	src/pipecat/services/google/llm.py	608	Yield streamed chunks, giving up if the stream stalls between them. A stream that stops producing without closi	STRING
HIGH	src/pipecat/services/google/image.py	148	Generate images from a text prompt using Google's Imagen model. Args: prompt: The text description	STRING
HIGH	src/pipecat/services/google/stt.py	381	Normalize adaptation input to a SpeechAdaptation message. A ``phrase_sets`` entry may be a resource name string, an	STRING
HIGH	src/pipecat/services/google/vertex/llm.py	196	Retrieve Credentials using Google service account credentials. Supports multiple authentication methods:	STRING
HIGH	src/pipecat/services/google/gemini_live/vertex/llm.py	263	Retrieve Credentials using Google service account credentials JSON. Supports multiple authentication methods:	STRING
HIGH	src/pipecat/services/deepgram/flux/stt.py	121	Initialize the Deepgram Flux STT service. Args: api_key: Deepgram API key for authentication. Requi	STRING
HIGH	src/pipecat/services/deepgram/flux/stt.py	390	Send audio data to Deepgram Flux for transcription. Transmits raw audio bytes to the Deepgram Flux API for real	STRING
15 more matches not shown…

Deep Nesting315 hits · 281 pts

Severity	File	Line	Context
LOW	tests/test_deepgram_flux_sagemaker_tts.py	77	CODE
LOW	tests/test_deepgram_flux_tts.py	41	CODE
LOW	tests/test_deepgram_flux_tts.py	55	CODE
LOW	tests/test_bland_tts.py	56	CODE
LOW	tests/test_bland_tts.py	776	CODE
LOW	tests/test_bland_tts.py	859	CODE
LOW	tests/test_bland_tts.py	919	CODE
LOW	tests/test_bland_tts.py	68	CODE
LOW	tests/test_bland_tts.py	784	CODE
LOW	tests/test_bland_tts.py	863	CODE
LOW	tests/test_bland_tts.py	922	CODE
LOW	tests/test_get_llm_invocation_params.py	482	CODE
LOW	tests/test_gemini_live_user_audio.py	53	CODE
LOW	tests/test_xai_realtime_events.py	104	CODE
LOW	tests/cli/test_client_generation.py	202	CODE
LOW	tests/cli/test_project_generation.py	59	CODE
LOW	tests/cli/test_project_generation.py	414	CODE
LOW	examples/transcription/transcription-google-llm.py	94	CODE
LOW	examples/transcription/transcription-google-llm.py	131	CODE
LOW	examples/features/features-custom-frame-processor.py	39	CODE
LOW	examples/multi-worker/code-assistant/code_worker.py	80	CODE
LOW	examples/multi-worker/openclaw-agent/openclaw_worker.py	103	CODE
LOW	…es/realtime/realtime-gemini-live-grounding-metadata.py	79	CODE
LOW	examples/voice/voice-google-audio-in.py	86	CODE
LOW	examples/voice/voice-google-audio-in.py	128	CODE
LOW	examples/voice/voice-aicoustics-vad-only.py	120	CODE
LOW	examples/flows/llm_switching.py	95	CODE
LOW	scripts/cli/imports/import_generator.py	19	CODE
LOW	scripts/cli/imports/import_generator.py	56	CODE
LOW	scripts/cli/imports/import_generator.py	138	CODE
LOW	scripts/cli/imports/import_generator.py	285	CODE
LOW	scripts/cli/imports/import_generator.py	381	CODE
LOW	scripts/cli/configs/config_generator.py	256	CODE
LOW	scripts/cli/configs/config_generator.py	375	CODE
LOW	scripts/provider-watch/probe.py	284	CODE
LOW	scripts/provider-watch/probe.py	332	CODE
LOW	scripts/provider-watch/publish.py	230	CODE
LOW	scripts/provider-watch/inventory.py	134	CODE
LOW	scripts/provider-watch/inventory.py	167	CODE
LOW	scripts/provider-watch/inventory.py	195	CODE
LOW	scripts/provider-watch/inventory.py	364	CODE
LOW	scripts/krisp/test_krisp_viva_filter_audiofile.py	88	CODE
LOW	scripts/krisp/test_krisp_viva_turn_audiofile.py	68	CODE
LOW	scripts/deprecations/scan.py	128	CODE
LOW	scripts/deprecations/scan.py	296	CODE
LOW	scripts/deprecations/scan.py	312	CODE
LOW	src/pipecat/pipeline/worker.py	279	CODE
LOW	src/pipecat/pipeline/worker.py	913	CODE
LOW	src/pipecat/pipeline/worker.py	974	CODE
LOW	src/pipecat/pipeline/worker.py	1023	CODE
LOW	src/pipecat/pipeline/worker.py	1440	CODE
LOW	src/pipecat/pipeline/worker.py	1505	CODE
LOW	src/pipecat/pipeline/job_decorator.py	51	CODE
LOW	src/pipecat/pipeline/sync_parallel_pipeline.py	252	CODE
LOW	src/pipecat/pipeline/sync_parallel_pipeline.py	291	CODE
LOW	src/pipecat/pipeline/worker_observer.py	194	CODE
LOW	src/pipecat/pipeline/worker_ready_decorator.py	37	CODE
LOW	src/pipecat/evals/harness.py	459	CODE
LOW	src/pipecat/evals/harness.py	680	CODE
LOW	src/pipecat/evals/harness.py	865	CODE
255 more matches not shown…

Self-Referential Comments87 hits · 262 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/test_markdown_text_filter.py	216	# Create a filter with all features disabled	COMMENT
MEDIUM	tests/test_frame_processor.py	299	# Create a frame with mutable fields to test shallow copying	COMMENT
MEDIUM	tests/test_ivr_navigation.py	28	# Create a mock LLM service	COMMENT
MEDIUM	tests/test_krisp_viva_filter.py	56	# Create a temporary .kef model file for testing	COMMENT
MEDIUM	tests/test_piper_tts.py	63	# Create an aiohttp test server	COMMENT
MEDIUM	tests/test_krisp_viva_vad.py	55	# Create a temporary .kef model file for testing	COMMENT
MEDIUM⚡	tests/test_vonage_video_connector.py	1003	# Create an event that will block but can be interrupted	COMMENT
MEDIUM⚡	tests/test_vonage_video_connector.py	2884	# Create a simple RGB image with distinct colors	COMMENT
MEDIUM	tests/test_vonage_video_connector.py	793	# Create an event that will block but can be interrupted	COMMENT
MEDIUM	tests/test_vonage_video_connector.py	1082	# Create a mock coroutine to queue	COMMENT
MEDIUM	tests/test_vonage_video_connector.py	1219	# Create a test RGB image (640x480, 3 channels)	COMMENT
MEDIUM	tests/test_vonage_video_connector.py	1869	# Create a test RGB video frame (4x4, 3 channels)	COMMENT
MEDIUM	tests/test_vonage_video_connector.py	2121	# Create a mock audio frame	COMMENT
MEDIUM	tests/test_vonage_video_connector.py	2139	# Create a test video frame	COMMENT
MEDIUM	tests/test_vonage_video_connector.py	2171	# Create a test video frame	COMMENT
MEDIUM	tests/test_vonage_video_connector.py	2202	# Create a video frame with incorrect size	COMMENT
MEDIUM	tests/test_vonage_video_connector.py	2228	# Create a video frame with incorrect size	COMMENT
MEDIUM	tests/test_service_switcher.py	500	# Create a pipeline with both switchers: switcher1 -> switcher2	COMMENT
MEDIUM	tests/test_openai_llm_timeout.py	69	# Create a context frame to process	COMMENT
MEDIUM	tests/test_context_summarization.py	650	# Create a minimal LLM service - base class raises NotImplementedError	COMMENT
MEDIUM	tests/test_get_llm_invocation_params.py	176	# Create a message with complex content structure (text + image)	COMMENT
MEDIUM	tests/test_get_llm_invocation_params.py	188	# Create a message with multiple text blocks	COMMENT
MEDIUM	tests/test_get_llm_invocation_params.py	487	# Create a message with complex content structure (text + image)	COMMENT
MEDIUM	tests/test_get_llm_invocation_params.py	502	# Create a message with multiple text blocks	COMMENT
MEDIUM	tests/test_get_llm_invocation_params.py	512	# Create a message with audio input (text + audio)	COMMENT
MEDIUM	tests/test_get_llm_invocation_params.py	1212	# Create a complex message with both text and image content	COMMENT
MEDIUM	tests/test_get_llm_invocation_params.py	1740	# Create a complex message with both text and image content	COMMENT
MEDIUM	…ideo-processing/video-processing-custom-video-track.py	157	# Create a blue-tinted copy for the custom destination.	COMMENT
MEDIUM	examples/transports/transports-small-webrtc.py	102	# Create a transport using the WebRTC connection	COMMENT
MEDIUM	examples/rag/rag-mem0.py	84	# Create a personalized greeting based on memories	COMMENT
MEDIUM	examples/realtime/realtime-openai.py	148	# Create a standard OpenAI LLM context object using the normal messages format. The	COMMENT
MEDIUM	examples/realtime/realtime-openai-text.py	145	# Create a standard OpenAI LLM context object using the normal messages format. The	COMMENT
MEDIUM	examples/realtime/realtime-inworld.py	109	# Create the Inworld Realtime LLM service.	COMMENT
MEDIUM	examples/realtime/realtime-grok.py	150	# Create the Grok Realtime LLM service	COMMENT
MEDIUM	…es/realtime/realtime-gemini-live-grounding-metadata.py	120	# Create a processor to capture grounding metadata	COMMENT
MEDIUM	examples/realtime/realtime-azure.py	135	# Create a standard LLM context object using the normal messages format. The	COMMENT
MEDIUM	examples/realtime/realtime-aws-nova-sonic.py	94	# Create the AWS Nova Sonic LLM service	COMMENT
MEDIUM	examples/realtime/realtime-openai-live-video.py	103	# Create a standard OpenAI LLM context object using the normal messages format. The	COMMENT
MEDIUM	examples/realtime/realtime-gemini-live-files-api.py	86	# Create a temporary file	STRING
MEDIUM	examples/realtime/realtime-gemini-live-files-api.py	95	# Create a sample file to upload	STRING
MEDIUM	examples/update-settings/stt/stt-whisper-api.py	59	# This file is meant to exercise Whisper API-based STT services, so we use	COMMENT
MEDIUM	examples/getting-started/04-sync-speech-and-image.py	114	# Create an HTTP session for API calls	COMMENT
MEDIUM	examples/voice/voice-neuphonic-http.py	62	# Create an HTTP session	COMMENT
MEDIUM	examples/voice/voice-elevenlabs-http.py	62	# Create an HTTP session	COMMENT
MEDIUM	examples/voice/voice-bland-http.py	62	# Create an HTTP session	COMMENT
MEDIUM	examples/voice/voice-aicoustics.py	155	# Create the WAV file	COMMENT
MEDIUM	examples/voice/voice-xtts.py	61	# Create an HTTP session	COMMENT
MEDIUM	examples/voice/voice-asyncai-http.py	62	# Create an HTTP session	COMMENT
MEDIUM	examples/voice/voice-sarvam-vad-http.py	63	# Create an HTTP session	COMMENT
MEDIUM	examples/voice/voice-minimax.py	63	# Create an HTTP session	COMMENT
MEDIUM	examples/voice/voice-rime-http.py	62	# Create an HTTP session	COMMENT
MEDIUM	…persistent-context/persistent-context-grok-realtime.py	115	# Define the tools schema	COMMENT
MEDIUM	scripts/cli/imports/update_imports.py	173	# Create the complete file content	STRING
MEDIUM	.github/workflows/update-docs.yml	152	### Creating the docs PR	COMMENT
MEDIUM	src/pipecat/pipeline/worker.py	847	# Create the worker's tasks and wait for the push task, which	COMMENT
MEDIUM	src/pipecat/runner/daily.py	208	# Create a new room	COMMENT
MEDIUM	src/pipecat/transports/websocket/server.py	263	# Create a task to monitor the websocket connection	COMMENT
MEDIUM	src/pipecat/utils/base_object.py	255	# Create the task. Note that this is a task per each function	COMMENT
MEDIUM	src/pipecat/utils/tracing/turn_trace_observer.py	136	# Create a new span for this conversation	COMMENT
MEDIUM	src/pipecat/utils/tracing/turn_trace_observer.py	195	# Create a new span for this turn	COMMENT
27 more matches not shown…

Unused Imports203 hits · 192 pts

Severity	File	Line	Context
LOW	tests/test_stt_usage_metrics.py	167	CODE
LOW	tests/test_runner_run.py	37	CODE
LOW	tests/test_runner_run.py	38	CODE
LOW	tests/test_runner_utils.py	24	CODE
LOW	tests/test_bus_network.py	14	CODE
LOW	tests/test_bus_network.py	21	CODE
LOW	tests/test_processor_usable_gating.py	23	CODE
LOW	scripts/release-changelog.py	29	CODE
LOW	scripts/provider-watch/digest.py	20	CODE
LOW	scripts/provider-watch/probe.py	46	CODE
LOW	scripts/provider-watch/publish.py	35	CODE
LOW	scripts/provider-watch/inventory.py	26	CODE
LOW	scripts/krisp/test_krisp_viva_filter_audiofile.py	28	CODE
LOW	scripts/krisp/test_krisp_viva_turn_audiofile.py	26	CODE
LOW	scripts/deprecations/generate.py	23	CODE
LOW	scripts/deprecations/scan.py	20	CODE
LOW	scripts/deprecations/generate_removals.py	30	CODE
LOW	src/pipecat/pipeline/job_context.py	9	CODE
LOW	src/pipecat/pipeline/task.py	15	CODE
LOW	src/pipecat/pipeline/task.py	15	CODE
LOW	src/pipecat/pipeline/task.py	15	CODE
LOW	src/pipecat/pipeline/task.py	15	CODE
LOW	src/pipecat/pipeline/task.py	15	CODE
LOW	src/pipecat/runner/types.py	22	CODE
LOW	src/pipecat/runner/utils.py	57	CODE
LOW	src/pipecat/runner/utils.py	59	CODE
LOW	src/pipecat/transports/websocket/server.py	24	CODE
LOW	src/pipecat/transports/vonage/video_connector.py	41	CODE
LOW	src/pipecat/bus/bridge_processor.py	37	CODE
LOW	src/pipecat/bus/__init__.py	22	CODE
LOW	src/pipecat/bus/__init__.py	23	CODE
LOW	src/pipecat/bus/__init__.py	24	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
LOW	src/pipecat/bus/__init__.py	25	CODE
143 more matches not shown…

AI Slop Vocabulary48 hits · 151 pts

Severity	File	Line	Snippet	Context
MEDIUM	tests/test_tts_frame_ordering.py	1700	# — an ordering quirk of the test harness sending everything nearly	COMMENT
MEDIUM	tests/test_pipeline.py	500	# is a guaranteed lower bound, so this is robust to scheduling jitter while	COMMENT
MEDIUM	tests/cli/test_project_generation.py	865	# schema (EvalScenario.load is the validator the harness itself uses).	COMMENT
MEDIUM	tests/cli/test_project_generation.py	874	# The project env carries what the harness needs via the `evals` extra: the	COMMENT
LOW	…s/function-calling/function-calling-moondream-video.py	98	# For all other frames, just pass them through	COMMENT
LOW	examples/transcription/transcription-google-llm.py	155	# keep the token count down, but for now, we'll just use the whole thing.	STRING
MEDIUM	examples/features/features-add-tool-change-messages.py	121	# what we want for this validation harness. Pull it with	COMMENT
MEDIUM	examples/realtime/realtime-aws-nova-sonic.py	112	# Session continuation is enabled by default, allowing seamless	COMMENT
MEDIUM	scripts/provider-watch/probe.py	281	# ---------------------------------------------------------------------- harness	COMMENT
MEDIUM	scripts/release-evals/manifest.yaml	364	# LLM responds to, so the harness can assert on the resulting transcription and	COMMENT
MEDIUM	…ripts/release-evals/scenarios/food_ordering_sushi.yaml	28	# pipeline down before the farewell llm_response reaches the harness.	COMMENT
MEDIUM	scripts/release-evals/scenarios/hello_world.yaml	11	# pipeline down before the farewell llm_response reaches the harness.	COMMENT
MEDIUM	…-evals/scenarios/restaurant_reservation_available.yaml	28	# pipeline down before the farewell llm_response reaches the harness.	COMMENT
MEDIUM	…ripts/release-evals/scenarios/keenable_fetch_page.yaml	5	# is a stable documentation domain, so the judged answer is robust over time.	COMMENT
MEDIUM	…ripts/release-evals/scenarios/food_ordering_pizza.yaml	36	# pipeline down before the farewell llm_response reaches the harness.	COMMENT
MEDIUM	…ripts/release-evals/scenarios/acme_handoff_voices.yaml	52	# reaches the harness, so assert the call alone.	COMMENT
MEDIUM	scripts/release-evals/scenarios/insurance_quote.yaml	42	# pipeline down before the farewell llm_response reaches the harness.	COMMENT
MEDIUM	scripts/release-evals/scenarios/acme_handoff.yaml	32	# reaches the harness, so assert the call alone.	COMMENT
MEDIUM	…pts/release-evals/scenarios/language_switch_audio.yaml	5	# check that a non-English answer survives the bot's TTS and the harness's STT.	COMMENT
MEDIUM	…/scenarios/restaurant_reservation_no_availability.yaml	36	# pipeline down before the farewell llm_response reaches the harness.	COMMENT
MEDIUM	…ipts/release-evals/scenarios/multi_worker_handoff.yaml	36	# pipeline down before the farewell llm_response reaches the harness.	COMMENT
MEDIUM	scripts/release-evals/scenarios/capital_question.yaml	8	# robust to transcription than arithmetic: numbers are homophone-prone on both	COMMENT
MEDIUM	src/pipecat/evals/harness.py	122	# harness doesn't pace frames — and no continuous frame stream crosses the wire.	COMMENT
MEDIUM	src/pipecat/evals/harness.py	141	"harness_error", # the harness itself raised (sub-pipeline, judge, ...)	CODE
MEDIUM	src/pipecat/evals/harness.py	334	# Timestamped trace of the harness's own decisions, for diagnosing flakes.	COMMENT
MEDIUM	src/pipecat/evals/harness.py	363	# response (audio modality): the harness captures the bot's actual audio	COMMENT
MEDIUM	src/pipecat/evals/harness.py	583	# An unexpected harness-side error (a sub-pipeline failing to start	COMMENT
MEDIUM	src/pipecat/evals/harness.py	616	# attributed to it rather than leaking into the harness catch-all.	COMMENT
MEDIUM⚡	src/pipecat/evals/suite.py	71	# How long to wait for a freshly spawned bot to start listening (the harness	COMMENT
MEDIUM⚡	src/pipecat/evals/suite.py	74	# How long to wait for a bot subprocess to exit after the harness asks it to	COMMENT
MEDIUM⚡	src/pipecat/evals/suite.py	82	# The harness runs three sub-pipelines in-process and tags each one's logs with an	COMMENT
MEDIUM⚡	src/pipecat/evals/suite.py	83	# ``eval_pipeline`` context value via logger.contextualize (see harness.py),	COMMENT
MEDIUM⚡	src/pipecat/evals/suite.py	85	# connection, harness internals) falls through to "harness". The label is the	COMMENT
MEDIUM	src/pipecat/evals/suite.py	574	# Under --debug, capture the harness's own logs (transcription / voice	COMMENT
MEDIUM	src/pipecat/evals/suite.py	615	# Save the harness's own decision trace next to the bot log.	COMMENT
MEDIUM	src/pipecat/evals/transport.py	310	# The harness sends the image encoded over the wire, but a real camera	COMMENT
MEDIUM	src/pipecat/evals/transcribe.py	80	# Optional sink for timing diagnostics; the harness points this at its	COMMENT
MEDIUM	src/pipecat/evals/judge.py	82	# harness; this just poses the question and is never stored in that context.	COMMENT
MEDIUM	src/pipecat/evals/judge.py	131	# The conversation the judge evaluates against, grown by the harness over	COMMENT
MEDIUM⚡	src/pipecat/evals/serializer.py	67	# ``CancelWorkerFrame``, so the harness can end a scenario by gracefully tearing down the	COMMENT
MEDIUM⚡	src/pipecat/evals/serializer.py	76	# without a real camera. The harness sends the image encoded over the wire; the	COMMENT
MEDIUM⚡	src/pipecat/evals/serializer.py	83	# so the harness reader sees it; the harness transcribes the audio locally.	COMMENT
MEDIUM⚡	src/pipecat/evals/serializer.py	102	# wire so the harness can observe semantic events.	COMMENT
MEDIUM⚡	src/pipecat/evals/serializer.py	108	# The most recent image the harness registered (still-encoded bytes, MIME	COMMENT
MEDIUM	src/pipecat/runner/utils.py	179	# (transport_type, call_data) tuple; isinstance keeps this robust against	COMMENT
MEDIUM	src/pipecat/runner/utils.py	718	# harness connects as an RTVI client; the bot pipeline must include an	COMMENT
MEDIUM	src/pipecat/cli/generators/project.py	353	# The `evals` extra bundles the `pipecat eval` command and the harness's	COMMENT
LOW	src/pipecat/adapters/services/bedrock_adapter.py	88	# To avoid refactoring in AWSBedrockLLMService, we just pass through tool_choice.	COMMENT

Hallucination Indicators14 hits · 140 pts

Severity	File	Line	Snippet	Context
CRITICAL	tests/test_livekit_transport.py	638	transport._client.room.remote_participants.get.assert_not_called()	CODE
CRITICAL	tests/test_livekit_transport.py	656	transport._client.room.remote_participants.get.assert_not_called()	CODE
CRITICAL	tests/test_sarvam_llm.py	335	service._client.chat.completions.create.assert_not_called()	CODE
CRITICAL	tests/test_sarvam_llm.py	408	service._client.chat.completions.create.assert_not_called()	CODE
CRITICAL	tests/test_sarvam_llm.py	465	service._client.chat.completions.create.assert_not_called()	CODE
CRITICAL	tests/test_sarvam_llm.py	492	service._client.chat.completions.create.assert_not_called()	CODE
CRITICAL	tests/test_sarvam_llm.py	532	service._client.chat.completions.create.assert_not_called()	CODE
CRITICAL	tests/test_sarvam_llm.py	608	service._client.chat.completions.create.assert_not_called()	CODE
CRITICAL	tests/test_sarvam_llm.py	648	service._client.chat.completions.create.assert_not_called()	CODE
CRITICAL	tests/test_anthropic_thinking_defaults.py	38	return service._client.beta.messages.create.call_args.kwargs.get("thinking")	CODE
CRITICAL	tests/test_run_inference.py	73	service._client.chat.completions.create.assert_called_once_with(	CODE
CRITICAL	tests/test_run_inference.py	184	service._client.beta.messages.create.assert_called_once_with(	CODE
CRITICAL	tests/test_run_inference.py	256	service._client.aio.models.generate_content.assert_called_once()	CODE
CRITICAL	src/pipecat/services/openai/tts.py	280	async with self._client.audio.speech.with_streaming_response.create(	CODE

Redundant / Tautological Comments80 hits · 120 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_markdown_text_filter.py	52	# Check if spaces are in the same positions	STRING
LOW	tests/test_flows_context_strategies.py	300	# Set nodes to trigger summary generation	COMMENT
LOW	tests/test_flows_context_strategies.py	336	# Set nodes to trigger summary generation	COMMENT
LOW	tests/test_get_llm_invocation_params.py	561	# Check if it's image or audio based on the text content	COMMENT
LOW	tests/test_aic_filter.py	16	# Check if aic_sdk is available	COMMENT
LOW	tests/test_aic_quail_vad.py	12	# Check if aic_sdk is available	COMMENT
LOW	docs/api/build-docs.sh	15	# Check if sphinx-build is available	COMMENT
LOW	examples/flows/restaurant_reservation.py	94	# Check if time is booked	COMMENT
LOW	scripts/cli/imports/import_generator.py	89	# Check if this file contains the class	COMMENT
LOW	scripts/cli/imports/import_generator.py	336	# Check if this is a standard library module that should be imported directly	COMMENT
LOW	scripts/cli/configs/config_generator.py	181	# Check if parameter has a default value	COMMENT
LOW	scripts/cli/configs/config_generator.py	258	# Check if this service has manual_config flag in metadata	COMMENT
LOW	scripts/cli/configs/config_generator.py	262	# Check if this is a special case that needs manual handling	COMMENT
LOW	scripts/cli/configs/config_generator.py	284	# Check if this service uses the Settings pattern	COMMENT
LOW	scripts/cli/configs/config_generator.py	358	# Check if this service has a manual config	COMMENT
LOW	scripts/cli/configs/config_generator.py	396	# Check if multi-line	COMMENT
LOW	scripts/krisp/test_krisp_viva_filter_audiofile.py	119	# Check if sample rate is supported	COMMENT
LOW	scripts/krisp/test_krisp_viva_turn_audiofile.py	92	# Check if sample rate is supported	COMMENT
LOW	scripts/krisp/test_krisp_viva_turn_audiofile.py	214	# Print results	COMMENT
LOW	.github/workflows/generate-changelog.yml	103	# Check if type is valid	COMMENT
LOW	src/pipecat/pipeline/worker_observer.py	90	# Add the observer to the list.	COMMENT
LOW	src/pipecat/runner/run.py	496	# Check if it has a bot function	COMMENT
LOW	src/pipecat/transports/base_output.py	506	# Check if we have an audio mixer for our destination.	COMMENT
LOW	src/pipecat/transports/smallwebrtc/transport.py	736	# Check if there are any pending image requests and create	COMMENT
LOW	src/pipecat/transports/livekit/transport.py	289	# Check if there are already participants in the room	COMMENT
LOW	src/pipecat/utils/string.py	235	# Check if any start tag appears in the text	COMMENT
LOW	src/pipecat/utils/tracing/setup.py	16	# Check if OpenTelemetry is available	COMMENT
LOW	src/pipecat/utils/tracing/service_decorators.py	1012	# Check if tools is not None and not NOT_GIVEN	COMMENT
LOW	src/pipecat/utils/context/llm_context_summarization.py	530	# Check if the first message is a system message (initial system prompt).	COMMENT
LOW	src/pipecat/utils/text/pattern_pair_aggregator.py	229	# Check if this pattern was already processed	COMMENT
LOW	src/pipecat/utils/text/pattern_pair_aggregator.py	330	# Check if we have incomplete patterns	COMMENT
LOW	src/pipecat/utils/text/simple_text_aggregator.py	100	# Check if the new character is non-whitespace	COMMENT
LOW	src/pipecat/utils/text/simple_text_aggregator.py	116	# Check if we just added sentence-ending punctuation	COMMENT
LOW	src/pipecat/cli/registry/service_loader.py	169	# Check if it's in SERVICE_CONFIGS	COMMENT
LOW	src/pipecat/cli/registry/service_loader.py	173	# Check if it's a transport	COMMENT
LOW	src/pipecat/cli/registry/service_loader.py	294	# Check if config exists	COMMENT
LOW	src/pipecat/cli/registry/service_loader.py	298	# Check if imports exist	COMMENT
LOW	src/pipecat/cli/generators/project.py	63	# Check if the new name is available	COMMENT
LOW	src/pipecat/cli/generators/project.py	117	# Check if project already exists	COMMENT
LOW	src/pipecat/cli/generators/project.py	247	# Check if any service config contains "session=" parameter	COMMENT
LOW	src/pipecat/cli/generators/project.py	251	# Check if the config contains session= or aiohttp_session=	COMMENT
LOW	src/pipecat/cli/generators/project.py	295	# Check if we need aiohttp session and add import if needed	COMMENT
LOW	src/pipecat/cli/generators/project.py	534	# Check if this is Daily PSTN or Twilio + Daily SIP (special handling)	COMMENT
LOW	src/pipecat/adapters/services/gemini_adapter.py	369	# Check if we only have function-related messages (no regular text)	COMMENT
LOW	…pecat/processors/aggregators/llm_response_universal.py	1994	# Check if this image is a result of a function call.	COMMENT
LOW	…pecat/processors/aggregators/llm_context_summarizer.py	227	# Check if we've reached the token limit	COMMENT
LOW	…pecat/processors/aggregators/llm_context_summarizer.py	231	# Check if we've exceeded max unsummarized messages	COMMENT
LOW	…pecat/processors/aggregators/llm_context_summarizer.py	360	# Check if this is the result we're waiting for. Both auto and manual	COMMENT
LOW	…pecat/processors/aggregators/llm_context_summarizer.py	395	# Check if we still have enough messages	COMMENT
LOW	src/pipecat/serializers/vonage.py	128	# Check if this is binary audio data	COMMENT
LOW	src/pipecat/audio/filters/rnnoise_filter.py	134	# Check if output is float (needs scaling) or int16 (ready)	COMMENT
LOW	src/pipecat/audio/turn/krisp_viva_turn.py	319	# Check if turn is complete based on probability threshold	COMMENT
LOW	src/pipecat/audio/turn/smart_turn/http_smart_turn.py	75	# Check if successful	COMMENT
LOW	src/pipecat/transcriptions/language.py	614	# Check if language is in the verified map	COMMENT
LOW	src/pipecat/observers/loggers/metrics_log_observer.py	117	# Check if this metrics type should be logged	COMMENT
LOW	src/pipecat/observers/loggers/debug_log_observer.py	151	# Check if this frame type is in our filters	COMMENT
LOW	src/pipecat/observers/loggers/debug_log_observer.py	182	# Check if we should log this frame	COMMENT
LOW⚡	src/pipecat/flows/manager.py	530	# Check if all function calls are complete using Pipecat's state	COMMENT
LOW	src/pipecat/services/websocket_service.py	288	# Check if the connection died too quickly after being established. This	COMMENT
LOW	src/pipecat/services/cartesia/tts.py	504	# Check if this is a Chinese/Japanese language (if language is None, treat as other)	COMMENT
20 more matches not shown…

Over-Commented Block107 hits · 100 pts

Severity	File	Line	Snippet	Context
LOW	pyproject.toml	241	"I", # Import rules	COMMENT
LOW	pyproject.toml	261	# Base classes leave optional hooks empty so subclasses override only what	COMMENT
LOW	tests/test_aggregated_frame_sequencer.py	1241	"force_complete must propagate includes_inter_frame_spaces for CJK slots "	COMMENT
LOW	tests/test_word_completion_tracker.py	1981		COMMENT
LOW	tests/test_websocket_transport.py	1	#	COMMENT
LOW	tests/test_websocket_transport.py	21	# self.serialized_sample_frame = self.transport._serializer.serialize(	COMMENT
LOW	tests/test_websocket_transport.py	41	# mock_websocket.send.call_args[0][0], self.serialized_sample_frame)	COMMENT
LOW	tests/test_websocket_transport.py	61	# TTSStartFrame(),	COMMENT
LOW	tests/test_websocket_transport.py	81	# async def test_serializer_parameter(self):	COMMENT
LOW	tests/test_websocket_transport.py	101	# self.transport = WebsocketTransport(	COMMENT
LOW	examples/features/features-user-email-gathering.py	81	)	COMMENT
LOW	examples/mcp/mcp-streamable-http-gemini-live.py	81	tools=await mcp.tools(),	COMMENT
LOW	…/multi-worker/ui-worker/document-review/client/main.js	41	// In-flight review groups, keyed by job_id. Rendered as cards above	COMMENT
LOW	examples/rag/rag-mem0.py	181	# "model": "claude-3-5-sonnet-20240620",	COMMENT
LOW	examples/realtime/realtime-openai.py	201	# (Though note that tools in your LLMContext take precedence over those	COMMENT
LOW	examples/realtime/realtime-openai.py	221		COMMENT
LOW	examples/realtime/realtime-gemini-live.py	141	# frames, but you can add supplemental local turn frames for consumption	COMMENT
LOW	examples/realtime/realtime-grok.py	181		COMMENT
LOW	examples/realtime/realtime-ultravox.py	181	#	COMMENT
LOW	…es/realtime/realtime-gemini-live-grounding-metadata.py	121	grounding_processor = GroundingMetadataProcessor()	COMMENT
LOW	examples/realtime/realtime-azure.py	121	transcription=InputAudioTranscription(model="whisper-1"),	COMMENT
LOW	examples/realtime/realtime-aws-nova-sonic.py	101	# - us-west-2	COMMENT
LOW	examples/realtime/realtime-aws-nova-sonic.py	121	),	COMMENT
LOW	examples/realtime/realtime-gemini-live-files-api.py	161	"role": "developer",	COMMENT
LOW	examples/update-settings/llm/llm-gemini-live.py	61	context = LLMContext()	COMMENT
LOW	examples/update-settings/llm/llm-gemini-live-vertex.py	61	)	COMMENT
LOW	examples/thinking/thinking-openai-responses.py	121		COMMENT
LOW	examples/thinking/thinking-openai-responses-http.py	121		COMMENT
LOW	examples/getting-started/04-sync-speech-and-image.py	141	# them basically in order (e.g. I1 A1 A1 A1 I2 A2 A2 A2 A2 I3 A3). To do	COMMENT
LOW	…t/turn-management-filter-incomplete-turns-user-idle.py	101	# with one of:	COMMENT
LOW	…management-filter-incomplete-turns-function-calling.py	121	# fires only when the LLM confirms ✓. The LLM marks each response	COMMENT
LOW	…-management/turn-management-smart-turn-local-coreml.py	41	# Example setup:	COMMENT
LOW	examples/flows/warm_transfer.py	81		COMMENT
LOW	examples/flows/warm_transfer.py	101	# - continued_customer_interaction	COMMENT
LOW	scripts/deprecations/scan.py	41	# The first reference in a directive body (role or backtick) — the replacement,	COMMENT
LOW	scripts/release-evals/run.sh	1	#!/usr/bin/env sh	COMMENT
LOW	scripts/release-evals/manifest.yaml	361	#	COMMENT
LOW	…vals/scenarios/async_tool_cancellation_concurrent.yaml	41	# Asking for the call to stop is not the same as it stopping: work that	COMMENT
LOW	…als/scenarios/multi_worker_handoff_back_and_forth.yaml	1	# Exercises a full round-trip multi-worker handoff: the reservation worker hands	COMMENT
LOW	…ripts/release-evals/scenarios/acme_handoff_voices.yaml	1	# Each worker brings its own TTS and its own voice, so a hand-off is two	COMMENT
LOW	.github/PULL_REQUEST_TEMPLATE.md	1	#### Please describe the changes in your PR. If it is addressing an issue, please reference that as well.	COMMENT
LOW	src/pipecat/pipeline/worker.py	561	pipeline = Pipeline([edge_source, pipeline, edge_sink])	COMMENT
LOW	src/pipecat/pipeline/parallel_pipeline.py	141		COMMENT
LOW	src/pipecat/evals/harness.py	341	# One persistent TTS pipeline reused across the scenario's audio turns,	COMMENT
LOW	src/pipecat/evals/harness.py	1041	self._debug(f"FAIL: {event_name}: {failures[-1].reason}")	COMMENT
LOW	src/pipecat/evals/serializer.py	61	# ``RTVIConfigureObserverFrame``. This is the trust boundary for raising the	COMMENT
LOW	src/pipecat/transports/smallwebrtc/transport.py	401	except MediaStreamError:	COMMENT
LOW	src/pipecat/transports/smallwebrtc/connection.py	41	# Clamp aiortc's SCTP DATA-chunk payload size so the on-wire UDP packet fits	COMMENT
LOW	src/pipecat/transports/moq/transport.py	201		COMMENT
LOW	src/pipecat/transports/moq/transport.py	521	# wall-clock duration for pacing.	COMMENT
LOW	src/pipecat/bus/ui/messages.py	41	#: Internal ``event_name`` used by a client-facing worker when republishing	COMMENT
LOW	src/pipecat/utils/tracing/__init__.py	1	#	COMMENT
LOW	src/pipecat/utils/context/text_segment_map.py	261	# Tokenization preserves whitespace, so SequenceMatcher sees:	COMMENT
LOW	src/pipecat/utils/context/text_segment_map.py	281	# original="$42.50",	COMMENT
LOW	src/pipecat/utils/context/text_segment_map.py	301	# A segment is all-or-nothing as soon as it holds a tag, so one tag in	COMMENT
LOW	…pipecat/adapters/services/open_ai_responses_adapter.py	81		COMMENT
LOW	src/pipecat/adapters/services/anthropic_adapter.py	261	The message in Anthropic format, or None for a thought that can't be	COMMENT
LOW	src/pipecat/adapters/services/anthropic_adapter.py	421	List of messages with cache control markers added.	COMMENT
LOW	src/pipecat/processors/frame_processor.py	261	# frames, so they will be returned first from the queue.	COMMENT
LOW	src/pipecat/processors/aggregators/llm_context.py	41	# "Re-export" types from OpenAI that we're using as universal context types.	COMMENT
47 more matches not shown…

Modern AI Meta-Vocabulary32 hits · 96 pts

Severity	File	Line	Snippet	Context
MEDIUM	pyproject.toml	209	# CLI project-scaffolding templates (jinja + client TS/JS/JSON/CSS trees). The	COMMENT
MEDIUM	README.md	50	The [Pipecat CLI](https://docs.pipecat.ai/api-reference/cli/overview) ships with `pipecat-ai` — install it with `uv tool	CODE
MEDIUM	README.md	62	Use [Pipecat Skills](https://github.com/pipecat-ai/skills) with [Claude Code](https://claude.ai/code) to scaffold projec	CODE
MEDIUM	tests/test_llm_service.py	141	# The tool was not advertised, so this is treated as a hallucination	COMMENT
MEDIUM⚡	tests/cli/test_quickstart.py	49	# quickstart is a fixed preset; combining it with scaffold flags should warn rather	COMMENT
MEDIUM⚡	tests/cli/test_quickstart.py	50	# than silently ignore them — but still scaffold the canned (web) bot.	COMMENT
MEDIUM	tests/cli/test_init_interactive.py	53	# The build-method prompt returns "scaffold", so init runs the wizard in-place,	COMMENT
MEDIUM	tests/cli/test_init_interactive.py	70	# init initializes for agent-led dev before scaffolding.	COMMENT
MEDIUM	tests/cli/test_project_generation.py	684	# Mirror the scaffold_quickstart config from cli/scaffold.py.	COMMENT
MEDIUM⚡	tests/cli/test_init_agent_ready.py	230	# Its one still-useful piece (Context Hub setup) lives in the scaffold's README.	COMMENT
MEDIUM⚡	tests/cli/test_init_agent_ready.py	274	# The scaffold lands in init's target dir, in-place, named after it.	COMMENT
MEDIUM⚡	tests/cli/test_init_agent_ready.py	277	# skipped — its place is taken by the scaffold's README (see test_quickstart_*).	COMMENT
MEDIUM	tests/cli/test_init_agent_ready.py	171	# The scaffold path skips the from-scratch developer guide.	COMMENT
MEDIUM	tests/cli/test_init_agent_ready.py	298	# Re-running init to refresh the guide in a scaffolded project must not offer to scaffold.	COMMENT
MEDIUM⚡	tests/cli/test_init_in_place.py	51	# The scaffold path skips GETTING_STARTED.md — the README is the start-here.	COMMENT
MEDIUM	examples/features/features-add-tool-change-messages.py	120	# hallucination-prone of the easily accessible models — exactly	COMMENT
MEDIUM	src/pipecat/evals/transcribe.py	49	# and offset words. Kept short so it can't trigger silence hallucinations.	COMMENT
MEDIUM	src/pipecat/cli/main.py	87	# coding-agent guide and can scaffold a runnable bot (interactively or from flags/a	COMMENT
MEDIUM	src/pipecat/cli/commands/init.py	70	# `--help` panels grouping the scaffold flags, so `pipecat init --help` reads as	COMMENT
MEDIUM	src/pipecat/cli/commands/init.py	505	# Scaffold now: run the wizard in-place. The scaffold lands in the same directory that	COMMENT
MEDIUM	src/pipecat/cli/commands/init.py	554	# Scaffold options that, when present, switch `init` to non-interactive scaffolding.	COMMENT
MEDIUM	src/pipecat/cli/commands/init.py	565	# Every scaffold/feature option, by parameter name — used to detect flags the user	COMMENT
MEDIUM⚡	src/pipecat/cli/commands/init.py	757	pipecat init my-bot --config project-config.json # scaffold from a config file	CODE
MEDIUM⚡	src/pipecat/cli/commands/init.py	761	# `pipecat init quickstart`: scaffold the canned bot in-place, with the coding-agent guide.	STRING
MEDIUM⚡	src/pipecat/cli/commands/init.py	763	# quickstart is a fixed preset — scaffold flags don't apply. Say so instead of	STRING
MEDIUM	src/pipecat/cli/commands/init.py	815	# No scaffold options: write the guide and route to a build method.	STRING
MEDIUM	src/pipecat/cli/agent_templates/AGENTS.md	19	## 1. Start by scaffolding	COMMENT
MEDIUM	src/pipecat/cli/agent_templates/AGENTS.md	31	# Headless: any scaffold flag (--bot-type, a service, or --config) switches off the wizard.	COMMENT
MEDIUM	src/pipecat/cli/agent_templates/AGENTS.md	275	[Pipecat Cloud](https://www.daily.co/products/pipecat-cloud/) is a hosted option — deploying there is optional (run	CODE
MEDIUM	src/pipecat/services/google/gemini_live/llm.py	1175	# Add context window compression to configuration, if enabled.	COMMENT
MEDIUM	src/pipecat/services/google/gemini_live/llm.py	309	trigger_tokens: int \| None = Field(default=None) # None = use default (80% of context window)	CODE
MEDIUM	src/pipecat/services/whisper/stt.py	583	# Drop likely hallucinations	COMMENT

AI Structural Patterns77 hits · 72 pts

Severity	File	Line	Context
LOW	src/pipecat/pipeline/worker.py	279	CODE
LOW	src/pipecat/evals/harness.py	266	CODE
LOW	src/pipecat/evals/harness.py	374	CODE
LOW	src/pipecat/evals/suite.py	271	CODE
LOW	src/pipecat/runner/daily.py	77	CODE
LOW	src/pipecat/transports/lemonslice/api.py	41	CODE
LOW	src/pipecat/tests/utils.py	123	CODE
LOW	src/pipecat/bus/network/pgmq.py	80	CODE
LOW	src/pipecat/utils/string.py	355	CODE
LOW	src/pipecat/utils/tracing/service_attributes.py	122	CODE
LOW	src/pipecat/utils/tracing/service_attributes.py	186	CODE
LOW	src/pipecat/utils/tracing/service_attributes.py	279	CODE
LOW	src/pipecat/utils/tracing/service_attributes.py	384	CODE
LOW	src/pipecat/utils/text/transforms/voice_formatter.py	32	CODE
LOW	src/pipecat/cli/config_validator.py	38	CODE
LOW	src/pipecat/cli/commands/eval.py	294	CODE
LOW	src/pipecat/cli/commands/eval.py	844	CODE
LOW	src/pipecat/cli/commands/init.py	587	CODE
LOW	src/pipecat/audio/resamplers/resampy_resampler.py	64	CODE
LOW	src/pipecat/audio/resamplers/soxr_stream_resampler.py	117	CODE
LOW	src/pipecat/audio/resamplers/soxr_resampler.py	59	CODE
LOW	src/pipecat/audio/vad/aic_quail_vad.py	75	CODE
LOW	src/pipecat/workers/runner.py	109	CODE
LOW	src/pipecat/services/tts_service.py	145	CODE
LOW	src/pipecat/services/cartesia/tts.py	244	CODE
LOW	src/pipecat/services/cartesia/tts.py	811	CODE
LOW	src/pipecat/services/inworld/tts.py	154	CODE
LOW	src/pipecat/services/inworld/tts.py	598	CODE
LOW	src/pipecat/services/inworld/realtime/llm.py	255	CODE
LOW	src/pipecat/services/asyncai/tts.py	102	CODE
LOW	src/pipecat/services/asyncai/tts.py	492	CODE
LOW	src/pipecat/services/openclaw/gateway.py	67	CODE
LOW	src/pipecat/services/openclaw/client.py	227	CODE
LOW	src/pipecat/services/speechmatics/stt.py	385	CODE
LOW	src/pipecat/services/azure/tts.py	281	CODE
LOW	src/pipecat/services/rime/tts.py	169	CODE
LOW	src/pipecat/services/rime/tts.py	930	CODE
LOW	src/pipecat/services/gladia/stt.py	215	CODE
LOW	src/pipecat/services/google/tts.py	1068	CODE
LOW	src/pipecat/services/google/tts.py	1294	CODE
LOW	src/pipecat/services/google/llm.py	205	CODE
LOW	src/pipecat/services/google/stt.py	870	CODE
LOW	src/pipecat/services/google/vertex/llm.py	63	CODE
LOW	src/pipecat/services/google/gemini_live/llm.py	448	CODE
LOW	src/pipecat/services/google/gemini_live/vertex/llm.py	60	CODE
LOW	src/pipecat/services/soniox/stt.py	277	CODE
LOW	src/pipecat/services/fal/stt.py	188	CODE
LOW	src/pipecat/services/deepgram/stt.py	69	CODE
LOW	src/pipecat/services/deepgram/stt.py	298	CODE
LOW	src/pipecat/services/deepgram/flux/stt.py	105	CODE
LOW	src/pipecat/services/deepgram/sagemaker/stt.py	93	CODE
LOW	src/pipecat/services/groq/stt.py	40	CODE
LOW	src/pipecat/services/elevenlabs/tts.py	248	CODE
LOW	src/pipecat/services/elevenlabs/tts.py	681	CODE
LOW	src/pipecat/services/elevenlabs/stt.py	504	CODE
LOW	src/pipecat/services/neuphonic/tts.py	109	CODE
LOW	src/pipecat/services/nvidia/tts.py	150	CODE
LOW	src/pipecat/services/nvidia/stt.py	257	CODE
LOW	src/pipecat/services/nvidia/stt.py	712	CODE
LOW	src/pipecat/services/heygen/api_liveavatar.py	331	CODE
17 more matches not shown…

Modern Structural Boilerplate52 hits · 50 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_ui_worker.py	68	async def _settle() -> None:	CODE
LOW	tests/test_vonage_video_connector.py	355	def _setup_audio_ready_callback(self, client: VonageClient, call_ready_for_audio: bool) -> None:	CODE
LOW	tests/test_vonage_video_connector.py	377	def _setup_subscriber_callbacks(self, client: VonageClient) -> None:	CODE
LOW	tests/test_vonage_video_connector.py	439	async def set_event_when_drained() -> None:	CODE
LOW	tests/test_xai_stt.py	22	def _setup_service(service: XAISTTService, monkeypatch, sample_rate: int) -> None:	CODE
LOW	tests/test_assemblyai_stt.py	31	def _setup_service(service: AssemblyAISTTService, monkeypatch, sample_rate: int) -> None:	CODE
LOW	tests/aic_mocks.py	51	def set_parameter(self, param: Any, value: float) -> None:	CODE
LOW	tests/aic_mocks.py	74	def set_parameter(self, param: Any, value: float) -> None:	CODE
LOW	examples/multi-worker/sensor-controller/sensor.py	98	def set_target(self, value: float) -> None:	CODE
LOW	examples/multi-worker/sensor-controller/sensor.py	102	def set_response_rate(self, rate: float) -> None:	CODE
LOW	src/pipecat/pipeline/task.py	23	__all__ = [	CODE
LOW	src/pipecat/pipeline/runner.py	20	__all__ = ["PipelineRunner", "WorkerRunner"]	CODE
LOW⚡	src/pipecat/evals/serializer.py	112	def set_capture_audio(self, capture: bool) -> None:	CODE
LOW	src/pipecat/transports/smallwebrtc/connection.py	149	def set_enabled(self, enabled: bool) -> None:	CODE
LOW	src/pipecat/bus/__init__.py	58	__all__ = [	CODE
LOW	src/pipecat/bus/ui/__init__.py	19	__all__ = [	CODE
LOW	src/pipecat/bus/network/pgmq_backends.py	342	__all__ = [	CODE
LOW	src/pipecat/bus/network/__init__.py	20	__all__ = ["PgmqBus", "RedisBus"]	CODE
LOW	src/pipecat/bus/local/__init__.py	11	__all__ = ["AsyncQueueBus"]	CODE
LOW	src/pipecat/bus/adapters/__init__.py	17	__all__ = [	CODE
LOW	src/pipecat/bus/serializers/__init__.py	16	__all__ = [	CODE
LOW	src/pipecat/utils/deprecation.py	76	__all__ = ["DEPRECATION_MESSAGE_RE", "deprecated", "warn_deprecated_read"]	CODE
LOW	src/pipecat/utils/errors.py	17	__all__ = [	CODE
LOW	src/pipecat/utils/text/transforms/__init__.py	38	__all__ = [	CODE
LOW	src/pipecat/cli/registry/__init__.py	19	__all__ = [	CODE
LOW	src/pipecat/cli/prompts/__init__.py	11	__all__ = ["ProjectConfig", "ask_project_questions"]	CODE
LOW	src/pipecat/cli/commands/__init__.py	11	__all__ = ["init"]	CODE
LOW	src/pipecat/cli/commands/init.py	418	def _setup_context_hub() -> None:	CODE
LOW	src/pipecat/cli/generators/__init__.py	11	__all__ = ["ProjectGenerator"]	CODE
LOW	src/pipecat/extensions/ivr/ivr_navigator.py	101	def update_saved_messages(self, messages: list[LLMContextMessage]) -> None:	CODE
LOW	src/pipecat/processors/frameworks/rtvi/__init__.py	27	__all__ = [	CODE
LOW	src/pipecat/serializers/genesys.py	243	def set_output_variables(self, variables: dict[str, Any]) -> None:	CODE
LOW	src/pipecat/audio/vad/aic_quail_vad.py	250	def set_sample_rate(self, sample_rate: int) -> None:	CODE
LOW	src/pipecat/registry/__init__.py	11	__all__ = [	CODE
LOW	src/pipecat/workers/runner.py	377	async def _setup_session(self) -> None:	CODE
LOW	src/pipecat/workers/runner.py	540	def _setup_sigint(self) -> None:	CODE
LOW	src/pipecat/workers/runner.py	549	def _setup_sigterm(self) -> None:	CODE
LOW	src/pipecat/workers/ui/__init__.py	34	__all__ = [	CODE
LOW	src/pipecat/workers/llm/__init__.py	13	__all__ = [	CODE
LOW	src/pipecat/workers/proxy/__init__.py	14	__all__ = [	CODE
LOW	src/pipecat/workers/proxy/websocket/__init__.py	12	__all__ = [	CODE
LOW	src/pipecat/turns/user_start/__init__.py	19	__all__ = [	CODE
LOW	src/pipecat/turns/user_stop/__init__.py	15	__all__ = [	CODE
LOW	src/pipecat/turns/user_mute/__init__.py	15	__all__ = [	CODE
LOW	src/pipecat/flows/__init__.py	48	__all__ = [	CODE
LOW	src/pipecat/flows/manager.py	588	async def set_node_from_config(self, node_config: NodeConfig) -> None:	CODE
LOW	src/pipecat/flows/manager.py	602	async def _set_node(self, node_id: str, node_config: NodeConfig) -> None:	CODE
LOW	src/pipecat/services/deepgram/flux/tts.py	29	__all__ = [	CODE
LOW	src/pipecat/services/deepgram/flux/stt.py	31	__all__ = [	CODE
LOW	src/pipecat/services/elevenlabs/tts.py	62	__all__ = [	CODE
LOW	src/pipecat/services/hume/tts.py	261	async def update_setting(self, key: str, value: Any) -> None:	CODE
LOW	src/pipecat/services/openai/responses/llm.py	1454	__all__ = [	CODE

Structural Annotation Overuse28 hits · 47 pts

Severity	File	Line	Snippet	Context
LOW	COMMUNITY_INTEGRATIONS.md	17	### Step 1: Build Your Integration	COMMENT
LOW	COMMUNITY_INTEGRATIONS.md	21	### Step 2: Set Up Your Repository	COMMENT
LOW	COMMUNITY_INTEGRATIONS.md	39	### Step 3: Join Discord	COMMENT
LOW	COMMUNITY_INTEGRATIONS.md	43	### Step 4: Submit Your Documentation	COMMENT
LOW	.claude/skills/update-docs/SKILL.md	33	### Step 1: Resolve docs path and profile	COMMENT
LOW	.claude/skills/update-docs/SKILL.md	45	### Step 2: Create docs branch	COMMENT
LOW	.claude/skills/update-docs/SKILL.md	63	### Step 3: Detect changed source files	COMMENT
LOW	.claude/skills/update-docs/SKILL.md	90	### Step 4: Map source files to doc pages	COMMENT
LOW	.claude/skills/update-docs/SKILL.md	109	### Step 5: Analyze each source-doc pair	COMMENT
LOW	.claude/skills/update-docs/SKILL.md	128	### Step 6: Make targeted edits	COMMENT
LOW	.claude/skills/update-docs/SKILL.md	214	### Step 7: Update guides	COMMENT
LOW	.claude/skills/update-docs/SKILL.md	234	### Step 8: Identify doc gaps	COMMENT
LOW	.claude/skills/update-docs/SKILL.md	266	### Step 9: Format and regenerate llms.txt	COMMENT
LOW	.claude/skills/update-docs/SKILL.md	290	### Step 10: Output summary	COMMENT
LOW	.claude/skills/provider-watch/SKILL.md	30	### Step 1: Resolve paths and prerequisites	COMMENT
LOW	.claude/skills/provider-watch/SKILL.md	46	### Step 2: Build the unit list	COMMENT
LOW	.claude/skills/provider-watch/SKILL.md	54	### Step 3: Research in batches	COMMENT
LOW⚡	.claude/skills/provider-watch/SKILL.md	84	### Step 4: Highlights	COMMENT
LOW⚡	.claude/skills/provider-watch/SKILL.md	88	### Step 5: Publish or ask	COMMENT
LOW⚡	.claude/skills/provider-watch/SKILL.md	94	### Step 6: Clean up and summarize	COMMENT
LOW	src/pipecat/adapters/services/perplexity_adapter.py	129	# Step 1: Convert non-initial system messages to "user".	COMMENT
LOW	src/pipecat/adapters/services/perplexity_adapter.py	140	# Step 2: Merge consecutive same-role messages.	COMMENT
LOW	src/pipecat/adapters/services/perplexity_adapter.py	166	# Step 3: Remove trailing assistant messages.	COMMENT
LOW⚡	src/pipecat/adapters/services/mistral_adapter.py	109	# Step 1: ensure every "tool" message is followed by an "assistant".	COMMENT
LOW⚡	src/pipecat/adapters/services/mistral_adapter.py	119	# Step 2: convert non-initial system messages to "user".	COMMENT
LOW⚡	src/pipecat/adapters/services/mistral_adapter.py	129	# Step 3: set prefix on a trailing assistant message so Mistral will	COMMENT
LOW⚡	src/pipecat/services/google/gemini_live/file_api.py	74	# Step 1: Initial resumable request to get upload URL	COMMENT
LOW	src/pipecat/services/google/gemini_live/file_api.py	100	# Step 2: Upload the actual file data	COMMENT

Magic Placeholder Names13 hits · 32 pts

Severity	File	Line	Snippet	Context
HIGH	src/pipecat/services/together/tts.py	65	api_key="your-api-key",	STRING
HIGH	src/pipecat/services/together/stt.py	57	api_key="your-api-key",	STRING
HIGH	src/pipecat/services/deepgram/flux/stt.py	158	stt = DeepgramFluxSTTService(api_key="your-api-key")	STRING
HIGH	src/pipecat/services/deepgram/flux/stt.py	163	api_key="your-api-key",	STRING
HIGH	src/pipecat/services/deepgram/flux/stt.py	176	api_key="your-api-key",	STRING
HIGH	src/pipecat/services/camb/tts.py	171	api_key="your-api-key",	STRING
HIGH	src/pipecat/services/camb/tts.py	179	api_key="your-api-key",	STRING
HIGH	src/pipecat/services/smallest/tts.py	109	api_key="your-api-key",	STRING
HIGH	src/pipecat/services/smallest/stt.py	145	api_key="your-api-key",	STRING
HIGH	src/pipecat/services/sarvam/tts.py	322	api_key="your-api-key",	STRING
HIGH	src/pipecat/services/sarvam/tts.py	336	api_key="your-api-key",	STRING
HIGH	src/pipecat/services/sarvam/tts.py	681	api_key="your-api-key",	STRING
HIGH	src/pipecat/services/sarvam/tts.py	694	api_key="your-api-key",	STRING

Overly Generic Function Names15 hits · 16 pts

Severity	File	Line	Snippet	Context
LOW⚡	tests/test_flows_direct_functions.py	27	async def my_function(flow_manager: FlowManager):	CODE
LOW⚡	tests/test_flows_direct_functions.py	249	async def my_function(flow_manager: DummyFlowManager, name: str, age: int):	CODE
LOW⚡	tests/test_flows_direct_functions.py	270	async def my_function(flow_manager: FlowManager):	CODE
LOW⚡	tests/test_flows_direct_functions.py	280	async def my_function(flow_manager: FlowManager):	CODE
LOW⚡	tests/test_flows_direct_functions.py	290	async def my_function(flow_manager: FlowManager):	CODE
LOW⚡	tests/test_flows_direct_functions.py	320	async def my_function(flow_manager: FlowManager):	CODE
LOW⚡	tests/test_flows_direct_functions.py	330	async def my_function(flow_manager: FlowManager):	CODE
LOW⚡	tests/test_flows_direct_functions.py	366	async def my_function(flow_manager: FlowManager):	CODE
LOW⚡	tests/test_flows_direct_functions.py	381	async def my_function(flow_manager: FlowManager):	CODE
LOW	tests/test_flows_direct_functions.py	190	async def my_function(flow_manager: FlowManager, name: str, age: int, height: float \| None):	CODE
LOW⚡	tests/test_direct_functions.py	17	async def my_function(params: FunctionCallParams):	CODE
LOW	tests/test_direct_functions.py	156	async def my_function(	CODE
LOW⚡	tests/test_direct_functions.py	212	async def my_function(params: DummyParams, name: str, age: int):	CODE
LOW	…js/src/app/api/sessions/[sessionId]/[...path]/route.ts	3	async function handleRequest(	CODE
LOW	src/pipecat/workers/llm/llm_worker.py	77	async def my_function(self, params, arg: str):	STRING

Cross-Language Confusion3 hits · 15 pts

Severity	File	Line	Snippet	Context
HIGH⚡	tests/test_runner_run.py	872	_parse_ice_servers('{"urls": "stun:stun.example.com:3478", "username": null}'),	CODE
HIGH⚡	src/pipecat/services/openai/realtime/llm.py	1137	- return true	STRING
HIGH⚡	src/pipecat/services/openai/realtime/llm.py	1139	- return false	STRING

Verbosity Indicators8 hits · 15 pts

Severity	File	Line	Snippet	Context
LOW	src/pipecat/adapters/services/perplexity_adapter.py	129	# Step 1: Convert non-initial system messages to "user".	COMMENT
LOW	src/pipecat/adapters/services/perplexity_adapter.py	140	# Step 2: Merge consecutive same-role messages.	COMMENT
LOW	src/pipecat/adapters/services/perplexity_adapter.py	166	# Step 3: Remove trailing assistant messages.	COMMENT
LOW⚡	src/pipecat/adapters/services/mistral_adapter.py	109	# Step 1: ensure every "tool" message is followed by an "assistant".	COMMENT
LOW⚡	src/pipecat/adapters/services/mistral_adapter.py	119	# Step 2: convert non-initial system messages to "user".	COMMENT
LOW⚡	src/pipecat/adapters/services/mistral_adapter.py	129	# Step 3: set prefix on a trailing assistant message so Mistral will	COMMENT
LOW⚡	src/pipecat/services/google/gemini_live/file_api.py	74	# Step 1: Initial resumable request to get upload URL	COMMENT
LOW	src/pipecat/services/google/gemini_live/file_api.py	100	# Step 2: Upload the actual file data	COMMENT

Dead Code6 hits · 12 pts

Severity	File	Line	Context
MEDIUM	tests/test_segmented_stt.py	50	CODE
MEDIUM	tests/test_anthropic_thinking_defaults.py	134	CODE
MEDIUM	src/pipecat/services/stt_service.py	348	CODE
MEDIUM	src/pipecat/services/vision_service.py	63	CODE
MEDIUM	src/pipecat/services/tts_service.py	555	CODE
MEDIUM	src/pipecat/services/image_service.py	61	CODE

Fake / Example Data9 hits · 10 pts

Severity	File	Line	Snippet	Context
LOW⚡	tests/test_voice_formatting.py	299	result = await email_to_speech("user@example.com", "*")	CODE
LOW⚡	tests/test_voice_formatting.py	304	result = await email_to_speech("user@example.com", "*")	CODE
LOW	tests/test_deepgram_stt.py	381	service = DeepgramSTTService(api_key="fake-key-offline-test")	CODE
LOW	tests/test_get_llm_invocation_params.py	1098	"source": {"type": "base64", "media_type": "image/jpeg", "data": "fake_data"},	CODE
LOW	tests/genesys/conftest.py	129	"name": "John Doe",	CODE
LOW⚡	tests/genesys/test_genesys_serializer.py	304	assert serializer.participant["name"] == "John Doe"	CODE
LOW	examples/features/features-text-transforms.py	24	- email_to_speech "user@example.com" → "user at example dot com"	STRING
LOW	…ipecat/cli/templates/client/vanilla-js-vite/src/app.js	53	'placeholder',	CODE
LOW	…ipecat/cli/templates/client/vanilla-js-vite/src/app.js	192	if (role === 'placeholder') {	CODE

AI Response Leakage1 hit · 8 pts

Severity	File	Line	Snippet	Context
HIGH	examples/realtime/realtime-openai-live-video.py	96	# In this example we provide tools through the context, but you could	COMMENT

Slop Phrases3 hits · 5 pts

Severity	File	Line	Snippet	Context
MEDIUM	examples/realtime/realtime-gemini-live.py	141	# frames, but you can add supplemental local turn frames for consumption	STRING
MEDIUM	examples/realtime/realtime-ultravox.py	184	# frames, but you can add supplemental local turn frames for consumption	STRING
MEDIUM	examples/realtime/realtime-aws-nova-sonic.py	130	# frames, but you can add supplemental local turn frames for consumption	COMMENT

TODO Padding1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	src/pipecat/services/google/gemini_live/llm.py	898	# TODO: implement runtime tool updates for Gemini Live.	COMMENT

Example Usage Blocks1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	src/pipecat/services/piper/tts.py	195	# Usage:	COMMENT

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings