livekit/agents

31.7

Adjusted Score

31.7

Raw Score

100%

Time Factor

2026-08-28

Last Push

13.3K

Stars

Python

Language

248.7K

Lines of Code

1.2K

Files

6.2K

Pattern Hits

2026-08-29

Scan Date

0.24

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 4HIGH 293MEDIUM 251LOW 5623

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 6171 distinct pattern matches across 23 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Hyper-Verbose Identifiers2662 hits · 2542 pts

Severity	File	Line	Snippet	Context
LOW⚡	tests/test_plugin_inworld_tts.py	18	async def test_delivery_mode_default_not_given():	CODE
LOW⚡	tests/test_plugin_inworld_tts.py	25	async def test_delivery_mode_set_on_init():	CODE
LOW⚡	tests/test_plugin_inworld_tts.py	32	async def test_delivery_mode_accepts_all_documented_values():	CODE
LOW⚡	tests/test_plugin_inworld_tts.py	40	async def test_delivery_mode_rejects_unknown_value():	CODE
LOW⚡	tests/test_plugin_inworld_tts.py	47	async def test_delivery_mode_update_options():	CODE
LOW	tests/test_plugin_inworld_tts.py	59	async def _capture_first_ws_create_packet(opts) -> dict:	CODE
LOW	tests/test_plugin_inworld_tts.py	99	async def test_ws_create_packet_includes_delivery_mode():	CODE
LOW	tests/test_plugin_inworld_tts.py	121	async def test_ws_create_packet_omits_delivery_mode_when_not_given():	CODE
LOW	tests/test_plugin_inworld_tts.py	141	def _patch_session_to_capture_post(tts, captured: dict[str, object]) -> None:	CODE
LOW	tests/test_plugin_inworld_tts.py	164	async def test_http_body_includes_delivery_mode():	CODE
LOW	tests/test_plugin_inworld_tts.py	183	async def test_http_body_omits_delivery_mode_when_not_given():	CODE
LOW⚡	tests/test_inference_avatar.py	91	def test_image_url_and_model_id_conflict_raises(self) -> None:	CODE
LOW⚡	tests/test_inference_avatar.py	99	def test_extra_kwargs_is_copied(self) -> None:	CODE
LOW⚡	tests/test_inference_avatar.py	107	async def test_extra_kwargs_splits_known_and_unknown_keys() -> None:	CODE
LOW	tests/test_inference_avatar.py	54	def test_invalid_provider_raises(self, model: str) -> None:	CODE
LOW	tests/test_inference_avatar.py	60	def test_defaults_and_identity(self) -> None:	CODE
LOW	tests/test_inference_avatar.py	154	async def test_create_session_success() -> None:	CODE
LOW	tests/test_inference_avatar.py	199	async def test_avatar_id_from_model_string() -> None:	CODE
LOW	tests/test_inference_avatar.py	214	async def test_idempotency_key_stable_across_retries() -> None:	CODE
LOW	tests/test_inference_avatar.py	236	async def test_non_retryable_error_not_retried() -> None:	CODE
LOW	tests/test_inference_avatar.py	256	async def test_server_error_retried_then_raised() -> None:	CODE
LOW	tests/test_inference_avatar.py	331	async def test_start_uses_response_sample_rate(monkeypatch: pytest.MonkeyPatch) -> None:	CODE
LOW	tests/test_inference_avatar.py	369	async def test_start_sends_mint_inputs_and_no_token(	CODE
LOW	tests/test_inference_avatar.py	404	async def test_start_without_livekit_url_raises(monkeypatch: pytest.MonkeyPatch) -> None:	CODE
LOW	tests/test_inference_avatar.py	461	async def test_start_ids_set_before_audio_rebind(monkeypatch: pytest.MonkeyPatch) -> None:	CODE
LOW	tests/test_inference_avatar.py	514	async def test_start_standalone_connected_room(monkeypatch: pytest.MonkeyPatch) -> None:	CODE
LOW	tests/test_inference_avatar.py	549	async def test_start_standalone_disconnected_room_raises(monkeypatch: pytest.MonkeyPatch) -> None:	CODE
LOW	tests/test_inference_avatar.py	564	async def test_aclose_terminates_session() -> None:	CODE
LOW	tests/test_inference_avatar.py	592	async def test_aclose_skips_terminate_without_token() -> None:	CODE
LOW	tests/test_inference_avatar.py	610	async def test_aclose_terminate_failure_keeps_ids_and_runs_base_cleanup(	CODE
LOW	tests/test_inference_avatar.py	642	async def test_aclose_without_session_is_noop() -> None:	CODE
LOW⚡	tests/test_audio_recognition_turn_detection.py	52	def _make_full_recognition_for_eou() -> AudioRecognition:	CODE
LOW⚡	tests/test_audio_recognition_turn_detection.py	132	def test_non_specific_language_does_not_replace_concrete_language(self) -> None:	CODE
LOW⚡	tests/test_audio_recognition_turn_detection.py	140	def test_non_specific_language_does_not_initialize_language(self) -> None:	CODE
LOW⚡	tests/test_audio_recognition_turn_detection.py	148	def test_concrete_language_still_updates_after_long_transcript(self) -> None:	CODE
LOW⚡	tests/test_audio_recognition_turn_detection.py	651	def test_low_min_silence_with_audio_detector_raises(self) -> None:	CODE
LOW⚡	tests/test_audio_recognition_turn_detection.py	659	def test_adequate_min_silence_passes(self) -> None:	CODE
LOW⚡	tests/test_audio_recognition_turn_detection.py	666	def test_non_audio_detector_skips(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	179	async def test_sos_during_bounce_cancels_commit(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	244	async def test_stale_spike_does_not_block_next_commit(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	265	async def test_vad_then_stt_emits_eot_prediction_once(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	303	async def test_text_detector_emits_every_bounce(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	334	async def test_clear_user_turn_allows_next_turn_to_emit(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	374	async def test_emits_with_eot_context_when_turn_continues(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	392	async def test_emits_with_eot_context_when_turn_ends(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	409	async def test_no_emit_below_threshold(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	420	async def test_no_emit_when_backchannel_disabled(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	430	async def test_no_emit_for_text_detector(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	453	async def test_silence_tick_starts_request_once(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	463	async def test_resumed_speech_without_sos_rearms_next_pause(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	492	async def test_silence_tick_starts_request_while_agent_speaking(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	506	async def test_eos_consumes_silence_tick_request_without_predicting(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	523	async def test_eos_runs_eou_even_while_agent_speaking(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	542	async def test_sos_tears_down_request_and_rearms(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	553	async def test_eos_never_starts_request(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	569	async def test_late_stt_final_after_flush_short_circuits(	CODE
LOW	tests/test_audio_recognition_turn_detection.py	589	async def test_predict_timeout_signals_fallback_and_drops_future(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	608	async def test_commit_flushes_stream_and_marks_turn_flushed(self) -> None:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	636	def _make_recognition_for_validation() -> AudioRecognition:	CODE
LOW	tests/test_audio_recognition_turn_detection.py	680	def test_vad_without_min_silence_knob_skips(self) -> None:	CODE
2602 more matches not shown…

Cross-Language Confusion220 hits · 1258 pts

Severity	File	Line	Snippet	Context
HIGH	tests/test_plugin_sarvam_stt_streaming.py	1542	stream._audio_duration_collector.push(1.0)	CODE
HIGH	tests/test_plugin_sarvam_stt_streaming.py	1578	stream._audio_duration_collector.push(1.75)	CODE
HIGH	tests/test_plugin_sarvam_stt_streaming.py	1601	stream._audio_duration_collector.push(1.0)	CODE
HIGH	tests/fake_session.py	115	audio_input.push(0.1)	CODE
HIGH⚡	tests/test_tokenizer_xml_markup.py	772	out = s.push("Hi <emo")	CODE
HIGH⚡	tests/test_tokenizer_xml_markup.py	773	out += s.push('tion value="happy"/> the')	CODE
HIGH⚡	tests/test_tokenizer_xml_markup.py	774	out += s.push("re")	CODE
HIGH⚡	tests/test_tokenizer_xml_markup.py	788	first = s.push("Read [the docs](https:")	CODE
HIGH⚡	tests/test_tokenizer_xml_markup.py	790	rest = s.push("//docs.livekit.io) now.") + s.flush()	CODE
HIGH⚡	tests/test_tokenizer_xml_markup.py	798	first = s.push("The value 3 < 5 ")	CODE
HIGH⚡	tests/test_tokenizer_xml_markup.py	800	rest = s.push("is true.") + s.flush()	CODE
HIGH⚡	tests/test_recorder_io.py	158	track.push(2.0, _loud(100))	CODE
HIGH⚡	tests/test_recorder_io.py	168	track.push(0.0, _loud(100))	CODE
HIGH⚡	tests/test_recorder_io.py	169	track.push(0.5, _loud(100))	CODE
HIGH⚡	tests/test_recorder_io.py	180	track.push(0.5, _loud(100))	CODE
HIGH⚡	tests/test_recorder_io.py	188	track.push(0.0, _loud(100))	CODE
HIGH⚡	tests/test_recorder_io.py	189	track.push(0.1, _loud(100)) # contiguous, extends the run	CODE
HIGH⚡	tests/test_recorder_io.py	190	track.push(5.0, _loud(100)) # beyond tolerance, anchors on its own timestamp	CODE
HIGH⚡	tests/test_recorder_io.py	197	track.push(1.0, _loud(2400, sample_rate=24000)) # 100ms at 24kHz	CODE
HIGH⚡	tests/test_recorder_io.py	198	track.push(9.0, _loud(2400, sample_rate=24000)) # a new run, so the first one is complete	CODE
HIGH⚡	tests/test_recorder_io.py	209	track.push(0.0, _loud(100, channels=2))	CODE
HIGH⚡	tests/test_expr_markup.py	220	out += stripper.push(chunk)	CODE
HIGH⚡	tests/test_expr_markup.py	258	out = "".join(stripper.push(c) for c in chunks) + stripper.flush()	CODE
HIGH⚡	tests/test_expr_markup.py	266	out = "".join(stripper.push(c) for c in ["Right. ", " Anyway."]) + stripper.flush()	CODE
HIGH⚡	tests/test_expr_markup.py	273	out = "".join(stripper.push(c) for c in chunks) + stripper.flush()	CODE
HIGH⚡	tests/test_tts.py	821	emitter_stream.push(pcm_chunk)	CODE
HIGH⚡	tests/test_tts.py	823	emitter_stream.push(pcm_chunk)	CODE
HIGH⚡	tests/test_tts.py	828	emitter_stream.push(pcm_chunk)	CODE
HIGH⚡	tests/test_tts.py	829	emitter_stream.push(pcm_chunk)	CODE
HIGH⚡	tests/test_tts.py	865	emitter_multi.push(pcm_chunk)	CODE
HIGH⚡	tests/test_tts.py	867	emitter_multi.push(pcm_chunk)	CODE
HIGH⚡	tests/test_tts.py	869	emitter_multi.push(pcm_chunk)	CODE
HIGH	tests/test_tts.py	896	emitter_nostream.push(pcm_chunk)	CODE
HIGH	tests/test_tts.py	897	emitter_nostream.push(pcm_chunk)	CODE
HIGH	tests/test_tts.py	924	emitter_noflush.push(pcm_chunk)	CODE
HIGH	tests/test_tts.py	949	emitter_noflush.push(pcm_chunk)	CODE
HIGH	tests/test_tts.py	1016	emitter.push(wav_bytes)	CODE
HIGH	tests/test_tts.py	1021	emitter.push(wav_bytes)	CODE
HIGH	tests/test_tts.py	1057	emitter2.push(wav_bytes)	CODE
HIGH	tests/test_tts.py	1085	emitter3.push(b"\xff\xff" * 100)	CODE
HIGH	tests/test_plugin_soniox_tts.py	91	slot.emitter.push(_SILENCE_PCM)	CODE
HIGH	tests/test_playback_progress.py	89	await h.push(0.1)	CODE
HIGH⚡	tests/test_playback_progress.py	107	await h.push(0.2)	CODE
HIGH⚡	tests/test_playback_progress.py	113	await h.push(0.1)	CODE
HIGH⚡	tests/test_playback_progress.py	127	await h.push(0.06)	CODE
HIGH	tests/test_playback_progress.py	147	await h.push(0.5)	CODE
HIGH	tests/test_playback_progress.py	167	await h.push(0.5)	CODE
HIGH	tests/test_playback_progress.py	200	await h.push(0.5)	CODE
HIGH	tests/test_playback_progress.py	220	await h.push(0.5)	CODE
HIGH	tests/test_playback_progress.py	237	await h.push(0.2)	CODE
HIGH	tests/test_session_close_user_turn.py	31	audio_input.push(0.1)	CODE
HIGH⚡	tests/test_audio_emitter.py	89	e.push(_make_pcm(SR, NC, 5))	CODE
HIGH⚡	tests/test_audio_emitter.py	103	e.push(_make_pcm(SR, NC, 80))	CODE
HIGH⚡	tests/test_audio_emitter.py	165	e.push(_make_pcm(SR, NC, 200))	CODE
HIGH⚡	tests/test_audio_emitter.py	170	e.push(_make_pcm(SR, NC, 200))	CODE
HIGH⚡	tests/test_audio_emitter.py	191	e.push(_make_pcm(SR, NC, 500))	CODE
HIGH⚡	tests/test_audio_emitter.py	203	e.push(_make_pcm(SR, NC, 100))	CODE
HIGH	tests/test_audio_emitter.py	74	e.push(_make_pcm(SR, NC, 10))	CODE
HIGH	tests/test_audio_emitter.py	123	e.push(_make_pcm(SR, NC, 200))	CODE
HIGH	tests/test_audio_emitter.py	149	e.push(_make_pcm(SR, NC, 10))	CODE
160 more matches not shown…

Unused Imports1304 hits · 1196 pts

Severity	File	Line	Context
LOW	tests/test_plugin_inworld_tts.py	3	CODE
LOW	tests/test_inference_avatar.py	10	CODE
LOW	tests/test_audio_recognition_turn_detection.py	26	CODE
LOW	tests/test_plugin_sarvam_stt_streaming.py	1	CODE
LOW	tests/fake_session.py	1	CODE
LOW	tests/test_audio_recognition_handoff.py	1	CODE
LOW	tests/test_ipc.py	1	CODE
LOW	tests/test_tokenizer_xml_markup.py	7	CODE
LOW	tests/fake_vad.py	1	CODE
LOW	tests/test_realtime_cancel_tool_reply.py	7	CODE
LOW	tests/test_tool_results_preserved_on_interruption.py	7	CODE
LOW	tests/test_plugin_assemblyai_stt.py	3	CODE
LOW	tests/test_room_io.py	1	CODE
LOW	tests/test_recorder_io.py	7	CODE
LOW	tests/test_expr_markup.py	10	CODE
LOW	tests/test_session_host.py	1	CODE
LOW	tests/test_plugin_deepgram_tts.py	1	CODE
LOW	tests/test_tool_output_per_call.py	7	CODE
LOW	tests/test_realtime_input_speech_interrupt.py	1	CODE
LOW	tests/test_trace_types_pii.py	11	CODE
LOW	tests/test_turn_detection_cloud_stream.py	13	CODE
LOW	tests/test_telemetry_recording_disabled.py	10	CODE
LOW	tests/test_agent_session.py	1	CODE
LOW	tests/test_playout_launch_pause.py	1	CODE
LOW	tests/conftest.py	17	CODE
LOW	tests/conftest.py	17	CODE
LOW	tests/lk_server.py	8	CODE
LOW	tests/test_filler.py	1	CODE
LOW	tests/test_running_tool_placeholders.py	1	CODE
LOW	tests/test_amd_classifier.py	8	CODE
LOW	tests/test_inference_stt_aligned_transcript_claim.py	11	CODE
LOW	tests/test_tts.py	1	CODE
LOW	tests/test_plugin_soniox_tts.py	11	CODE
LOW	tests/test_judge.py	1	CODE
LOW	tests/fake_io.py	1	CODE
LOW	tests/test_run_input_errors.py	7	CODE
LOW	tests/fake_turn_stt.py	9	CODE
LOW	tests/test_audio_sink_proxy.py	1	CODE
LOW	tests/test_llm_utils.py	1	CODE
LOW	tests/test_plugin_google_realtime.py	1	CODE
LOW	tests/test_plugin_google_gemini_tts.py	1	CODE
LOW	tests/test_http_context_helper.py	5	CODE
LOW	tests/fake_stt.py	1	CODE
LOW	tests/test_expressive_toggle.py	1	CODE
LOW	tests/test_plugin_fishaudio_tts.py	3	CODE
LOW	tests/test_plugin_rime_tts.py	3	CODE
LOW	tests/test_convert_html_docs.py	3	CODE
LOW	tests/test_personaplex_realtime_model.py	3	CODE
LOW	tests/test_realtime_fallback.py	1	CODE
LOW	tests/test_tts_fallback.py	1	CODE
LOW	tests/test_plugin_bland_tts.py	1	CODE
LOW	tests/test_realtime_adaptive_interruption.py	1	CODE
LOW	tests/test_inference_stt_start_of_speech.py	9	CODE
LOW	tests/test_plugin_palabra.py	8	CODE
LOW	tests/test_stt_prewarm.py	1	CODE
LOW	tests/test_playback_progress.py	7	CODE
LOW	tests/test_realtime_auto_disable_turn_detection.py	1	CODE
LOW	tests/test_plugin_sarvam_llm.py	1	CODE
LOW	tests/test_cli_log_level.py	1	CODE
LOW	tests/test_transcription_timeout.py	1	CODE
1244 more matches not shown…

Decorative Section Separators183 hits · 680 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tests/test_audio_recognition_turn_detection.py	47	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_audio_recognition_turn_detection.py	49	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_audio_recognition_handoff.py	41	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_audio_recognition_handoff.py	43	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_audio_recognition_handoff.py	160	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_audio_recognition_handoff.py	162	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_audio_recognition_handoff.py	207	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_audio_recognition_handoff.py	209	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_tokenizer_xml_markup.py	19	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_tokenizer_xml_markup.py	21	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_tokenizer_xml_markup.py	111	# ===========================================================================	COMMENT
MEDIUM⚡	tests/test_tokenizer_xml_markup.py	113	# ===========================================================================	COMMENT
MEDIUM⚡	tests/test_tokenizer_xml_markup.py	509	# ===========================================================================	COMMENT
MEDIUM⚡	tests/test_tokenizer_xml_markup.py	511	# ===========================================================================	COMMENT
MEDIUM⚡	tests/test_tokenizer_xml_markup.py	576	# ===========================================================================	COMMENT
MEDIUM⚡	tests/test_tokenizer_xml_markup.py	578	# ===========================================================================	COMMENT
MEDIUM⚡	tests/test_tokenizer_xml_markup.py	730	# ===========================================================================	COMMENT
MEDIUM⚡	tests/test_tokenizer_xml_markup.py	732	# ===========================================================================	COMMENT
MEDIUM	tests/test_tokenizer_xml_markup.py	58	# ===========================================================================	COMMENT
MEDIUM	tests/test_tokenizer_xml_markup.py	60	# ===========================================================================	COMMENT
MEDIUM	tests/test_tokenizer_xml_markup.py	663	# ===========================================================================	COMMENT
MEDIUM	tests/test_tokenizer_xml_markup.py	665	# ===========================================================================	COMMENT
MEDIUM⚡	tests/test_plugin_assemblyai_stt.py	93	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_plugin_assemblyai_stt.py	101	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_plugin_assemblyai_stt.py	323	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_plugin_assemblyai_stt.py	330	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_plugin_assemblyai_stt.py	464	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_plugin_assemblyai_stt.py	466	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_plugin_assemblyai_stt.py	726	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_plugin_assemblyai_stt.py	735	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_plugin_assemblyai_stt.py	1321	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_plugin_assemblyai_stt.py	1330	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_plugin_assemblyai_stt.py	405	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_plugin_assemblyai_stt.py	411	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_plugin_assemblyai_stt.py	442	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_plugin_assemblyai_stt.py	444	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_plugin_assemblyai_stt.py	517	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_plugin_assemblyai_stt.py	524	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_plugin_assemblyai_stt.py	564	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_plugin_assemblyai_stt.py	571	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_plugin_assemblyai_stt.py	906	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_plugin_assemblyai_stt.py	918	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_recorder_io.py	146	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_recorder_io.py	148	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_recorder_io.py	216	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_recorder_io.py	218	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_recorder_io.py	46	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tests/test_recorder_io.py	48	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_expr_markup.py	80	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_expr_markup.py	82	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_expr_markup.py	98	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_expr_markup.py	100	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_expr_markup.py	153	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_expr_markup.py	155	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_expr_markup.py	284	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_expr_markup.py	286	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_expr_markup.py	303	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_expr_markup.py	305	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_expr_markup.py	358	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_expr_markup.py	360	# ---------------------------------------------------------------------------	COMMENT
123 more matches not shown…

Excessive Try-Catch Wrapping523 hits · 554 pts

Severity	File	Line	Snippet	Context
LOW	tests/conftest.py	299	except Exception:	CODE
LOW	tests/conftest.py	320	except Exception:	CODE
MEDIUM	tests/conftest.py	285	def _is_ignorable_task(task) -> bool:	CODE
MEDIUM	tests/conftest.py	304	def format_task(task) -> str:	CODE
LOW	tests/concurrency.py	114	except Exception: # pragma: no cover - defensive	CODE
LOW	tests/concurrency.py	342	except Exception: # pragma: no cover - best effort flush	CODE
LOW	tests/concurrency.py	380	except Exception: # pragma: no cover	CODE
LOW	tests/test_multi_speaker_adapter.py	296	except Exception as e: # noqa: BLE001 - recorded, asserted on below	CODE
MEDIUM	tests/test_multi_speaker_adapter.py	291	def _read() -> None:	CODE
LOW	tests/test_interruption/test_interruption_failover.py	91	except Exception as exc:	CODE
LOW	examples/drive_thru/order.py	62	except Exception:	CODE
LOW	examples/drive_thru/agent.py	524	except Exception:	CODE
LOW	examples/healthcare/agent.py	117	except Exception as e:	CODE
LOW	examples/other/translation/multi-user-translator.py	151	except Exception:	CODE
LOW	examples/hotel_receptionist/ui_view.py	70	except Exception:	CODE
LOW	examples/hotel_receptionist/ui_view.py	117	except Exception:	CODE
LOW	examples/hotel_receptionist/ui_view.py	138	except Exception as e:	CODE
LOW	examples/hotel_receptionist/agent.py	146	except Exception:	CODE
LOW	examples/hotel_receptionist/agent.py	159	except Exception:	CODE
LOW	examples/hotel_receptionist/agent.py	204	except Exception:	CODE
LOW	examples/hotel_receptionist/run_artifacts.py	36	except Exception:	CODE
LOW	examples/hotel_receptionist/run_artifacts.py	47	except Exception:	CODE
LOW	examples/frontdesk/ui_view.py	97	except Exception:	CODE
LOW	examples/warm-transfer/warm_transfer.py	77	except Exception as e:	CODE
LOW	examples/telephony/bank-ivr/dial_bank_agent.py	51	except Exception as e:	CODE
LOW	examples/inference/agent.py	112	except Exception:	CODE
LOW	scripts/generate_test_summary.py	86	except Exception as e:	CODE
MEDIUM	.github/convert_html_docs.py	1023	print(f"Error: {input_dir} is not a directory", file=sys.stderr)	CODE
MEDIUM	.github/convert_html_docs.py	1028	print(f"Error: {output_dir} is not a directory", file=sys.stderr)	CODE
LOW	.github/download_stats.py	53	except Exception:	CODE
LOW	livekit-agents/livekit/agents/worker.py	716	except Exception as e:	CODE
LOW	livekit-agents/livekit/agents/worker.py	1152	except Exception as e:	CODE
LOW	livekit-agents/livekit/agents/worker.py	1439	except Exception:	CODE
LOW	livekit-agents/livekit/agents/job.py	319	except Exception:	CODE
LOW	livekit-agents/livekit/agents/job.py	334	except Exception:	CODE
LOW	livekit-agents/livekit/agents/job.py	347	except Exception:	CODE
LOW	livekit-agents/livekit/agents/job.py	682	except Exception:	CODE
MEDIUM	livekit-agents/livekit/agents/job.py	672	def _delete_room() -> None:	CODE
LOW	livekit-agents/livekit/agents/_exceptions.py	144	except Exception:	CODE
LOW	livekit-agents/livekit/agents/__main__.py	32	except Exception as e:	CODE
LOW	livekit-agents/livekit/agents/__main__.py	50	except Exception as e:	CODE
LOW	livekit-agents/livekit/agents/jupyter.py	65	except Exception as e:	CODE
LOW	livekit-agents/livekit/agents/beta/tools/send_dtmf.py	32	except Exception as e:	CODE
LOW	…kit-agents/livekit/agents/beta/workflows/task_group.py	134	except Exception as e:	CODE
LOW	…kit-agents/livekit/agents/beta/workflows/task_group.py	160	except Exception as e:	CODE
LOW	…-agents/livekit/agents/beta/workflows/warm_transfer.py	199	except Exception:	CODE
LOW	livekit-agents/livekit/agents/evals/evaluation.py	171	except Exception as e:	CODE
LOW	livekit-agents/livekit/agents/llm/tool_context.py	398	except Exception:	CODE
LOW	livekit-agents/livekit/agents/llm/llm.py	188	except Exception:	CODE
LOW	livekit-agents/livekit/agents/llm/llm.py	278	except Exception as e:	CODE
LOW	livekit-agents/livekit/agents/llm/llm.py	319	except Exception as e:	CODE
MEDIUM	livekit-agents/livekit/agents/llm/llm.py	185	def _prewarm() -> None:	CODE
LOW	…agents/livekit/agents/llm/realtime_fallback_adapter.py	321	except Exception:	CODE
LOW	…agents/livekit/agents/llm/realtime_fallback_adapter.py	346	except Exception as e:	CODE
LOW	livekit-agents/livekit/agents/llm/utils.py	633	except Exception:	CODE
LOW	livekit-agents/livekit/agents/llm/utils.py	698	except Exception:	CODE
LOW	livekit-agents/livekit/agents/llm/utils.py	1043	except Exception as e:	CODE
LOW	livekit-agents/livekit/agents/llm/fallback_adapter.py	233	except Exception:	CODE
LOW	livekit-agents/livekit/agents/llm/fallback_adapter.py	262	except Exception:	CODE
LOW	livekit-agents/livekit/agents/llm/fallback_adapter.py	290	except Exception: # exceptions already logged inside _try_generate	CODE
463 more matches not shown…

Deep Nesting349 hits · 310 pts

Severity	File	Line	Context
LOW	tests/test_trace_types_pii.py	168	CODE
LOW	tests/conftest.py	209	CODE
LOW	tests/fake_stt.py	177	CODE
LOW	tests/test_endpointing.py	466	CODE
LOW	tests/test_plugin_bland_tts.py	405	CODE
LOW	tests/test_plugin_bland_tts.py	847	CODE
LOW	tests/test_plugin_palabra.py	34	CODE
LOW	tests/test_plugin_palabra.py	49	CODE
LOW	tests/test_plugin_palabra.py	54	CODE
LOW	tests/test_plugin_sarvam_llm.py	52	CODE
LOW	tests/concurrency.py	868	CODE
LOW	tests/test_chat_ctx.py	791	CODE
LOW	tests/test_stt.py	184	CODE
LOW	examples/drive_thru/database.py	606	CODE
LOW	examples/drive_thru/agent.py	387	CODE
LOW	examples/frontdesk/agent.py	202	CODE
LOW	examples/primitives/echo-agent.py	28	CODE
LOW	examples/primitives/echo-agent.py	73	CODE
LOW	examples/telephony/amd.py	37	CODE
LOW	examples/telephony/basic_dtmf_agent.py	55	CODE
LOW	examples/telephony/bank-ivr/ivr_system_agent.py	347	CODE
LOW	examples/telephony/bank-ivr/ivr_system_agent.py	441	CODE
LOW	examples/telephony/bank-ivr/ivr_system_agent.py	502	CODE
LOW	examples/telephony/bank-ivr/ivr_system_agent.py	566	CODE
LOW	scripts/generate_test_summary.py	12	CODE
LOW	.github/convert_html_docs.py	806	CODE
LOW	.github/convert_html_docs.py	990	CODE
LOW	.github/convert_html_docs.py	162	CODE
LOW	.github/convert_html_docs.py	541	CODE
LOW	livekit-agents/livekit/agents/worker.py	536	CODE
LOW	livekit-agents/livekit/agents/worker.py	1174	CODE
LOW	livekit-agents/livekit/agents/worker.py	1194	CODE
LOW	livekit-agents/livekit/agents/worker.py	801	CODE
LOW	livekit-agents/livekit/agents/_proto.py	81	CODE
LOW	…it-agents/livekit/agents/beta/workflows/credit_card.py	499	CODE
LOW	livekit-agents/livekit/agents/beta/workflows/utils.py	30	CODE
LOW	…vekit-agents/livekit/agents/metrics/usage_collector.py	77	CODE
LOW	livekit-agents/livekit/agents/metrics/utils.py	18	CODE
LOW	livekit-agents/livekit/agents/metrics/usage.py	200	CODE
LOW	livekit-agents/livekit/agents/evals/judge.py	59	CODE
LOW	livekit-agents/livekit/agents/llm/tool_context.py	588	CODE
LOW	livekit-agents/livekit/agents/llm/tool_context.py	692	CODE
LOW	livekit-agents/livekit/agents/llm/tool_context.py	596	CODE
LOW	livekit-agents/livekit/agents/llm/llm.py	259	CODE
LOW	livekit-agents/livekit/agents/llm/chat_context.py	496	CODE
LOW	livekit-agents/livekit/agents/llm/chat_context.py	720	CODE
LOW	livekit-agents/livekit/agents/llm/chat_context.py	776	CODE
LOW	livekit-agents/livekit/agents/llm/chat_context.py	915	CODE
LOW	livekit-agents/livekit/agents/llm/chat_context.py	510	CODE
LOW	livekit-agents/livekit/agents/llm/utils.py	89	CODE
LOW	livekit-agents/livekit/agents/llm/utils.py	315	CODE
LOW	livekit-agents/livekit/agents/llm/utils.py	427	CODE
LOW	livekit-agents/livekit/agents/llm/utils.py	491	CODE
LOW	livekit-agents/livekit/agents/llm/fallback_adapter.py	267	CODE
LOW	livekit-agents/livekit/agents/llm/_strict.py	48	CODE
LOW	…t-agents/livekit/agents/llm/_provider_format/google.py	23	CODE
LOW	…t-agents/livekit/agents/llm/_provider_format/google.py	127	CODE
LOW	…ekit-agents/livekit/agents/llm/_provider_format/aws.py	28	CODE
LOW	…t-agents/livekit/agents/llm/_provider_format/openai.py	50	CODE
LOW	…t-agents/livekit/agents/llm/_provider_format/openai.py	172	CODE
289 more matches not shown…

Modern Structural Boilerplate267 hits · 275 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_filler.py	89	def set_idle(self, idle: bool) -> None:	CODE
LOW	tests/toxic_proxy.py	217	def update_api_consumer(self, host: str, port: int) -> None:	CODE
LOW	tests/test_plugin_openai_stt_context.py	240	async def _settle(stream: stt.SpeechStream) -> None:	CODE
LOW⚡	tests/fake_realtime.py	79	async def update_instructions(self, instructions: str) -> None:	CODE
LOW⚡	tests/fake_realtime.py	82	async def update_chat_ctx(self, chat_ctx: ChatContext) -> None:	CODE
LOW⚡	tests/fake_realtime.py	87	async def update_tools(self, tools: list[Tool]) -> None:	CODE
LOW⚡	tests/fake_realtime.py	90	def update_options(self, *, tool_choice: NotGivenOr[ToolChoice \| None] = NOT_GIVEN) -> None:	CODE
LOW⚡	tests/test_plugin_elevenlabs_stt.py	133	def update_options(self, **kwargs: object) -> None:	CODE
LOW⚡	tests/test_plugin_elevenlabs_stt.py	254	def update_options(self, **kwargs: object) -> None:	CODE
LOW	tests/test_telemetry_exception_redaction.py	37	def set_status(self, status: trace.Status) -> None:	CODE
LOW	tests/test_telemetry_exception_redaction.py	40	def set_attributes(self, attributes: dict[str, Any]) -> None:	CODE
LOW	tests/test_multi_speaker_adapter.py	70	def _update_session_keyterms(self, keyterms: list[str]) -> None:	CODE
LOW	tests/test_stt_context.py	79	def _update_session_keyterms(self, keyterms: list[str]) -> None:	CODE
LOW	tests/test_realtime/test_openai_realtime_model.py	41	def update_options(self, **kw: object) -> None:	CODE
LOW	tests/utils/livekit_test.py	33	__all__ = [	CODE
LOW	tests/utils/audio_test.py	24	__all__ = [	CODE
LOW	examples/hotel_receptionist/hotel_db.py	1060	async def update_booking_card(self, *, booking_code: str, card_last4: str) -> None:	CODE
LOW	examples/hotel_receptionist/modify_booking.py	278	def _set_changed(self, slot: str, differs: bool) -> None:	CODE
LOW	examples/avatar/actions.py	80	def set_session(self, session_id: str, persona_id: str) -> None:	CODE
LOW	.github/update_versions.py	81	def update_plugins_pyproject_agents_version(new_agents_version: str) -> None:	CODE
LOW	.github/update_versions.py	97	def update_agents_pyproject_optional_dependencies(plugin_versions: Dict[str, str]) -> None:	CODE
LOW	.github/update_versions.py	123	def update_versions(bump_type: str) -> None:	CODE
LOW	.github/update_versions.py	157	def update_prerelease(prerelease_type: str) -> None:	CODE
LOW	livekit-agents/livekit/agents/simulation.py	23	__all__ = [	CODE
LOW	livekit-agents/livekit/agents/worker.py	766	def _update_job_status(proc: ipc.job_executor.JobExecutor) -> None:	CODE
LOW	livekit-agents/livekit/agents/worker.py	1489	async def _update_worker_status(self) -> None:	CODE
LOW	livekit-agents/livekit/agents/worker.py	1522	async def _update_job_status(self, proc: ipc.job_executor.JobExecutor) -> None:	CODE
LOW	livekit-agents/livekit/agents/__init__.py	168	__all__ = [	CODE
LOW	livekit-agents/livekit/agents/testing.py	15	__all__ = ["fake_job_context"]	CODE
LOW	livekit-agents/livekit/agents/beta/__init__.py	5	__all__ = ["Instructions", "workflows", "EndCallTool"]	CODE
LOW	livekit-agents/livekit/agents/beta/tools/__init__.py	4	__all__ = [	CODE
LOW	…vekit-agents/livekit/agents/beta/workflows/__init__.py	12	__all__ = [	CODE
LOW	…-agents/livekit/agents/beta/workflows/warm_transfer.py	254	def _set_result(self, result: WarmTransferResult \| Exception) -> None:	CODE
LOW	…-agents/livekit/agents/beta/workflows/warm_transfer.py	369	def _set_io_enabled(self, enabled: bool) -> None:	CODE
LOW	livekit-agents/livekit/agents/beta/toolsets/__init__.py	4	__all__ = ["ToolProxyToolset", "ToolSearchToolset"]	CODE
LOW	livekit-agents/livekit/agents/metrics/__init__.py	25	__all__ = [	CODE
LOW	livekit-agents/livekit/agents/evals/__init__.py	20	__all__ = [	CODE
LOW	livekit-agents/livekit/agents/llm/async_toolset.py	23	__all__ = ["AsyncRunContext", "AsyncToolset"]	CODE
LOW⚡	livekit-agents/livekit/agents/llm/realtime.py	246	async def update_instructions(self, instructions: str) -> None: ...	CODE
LOW⚡	livekit-agents/livekit/agents/llm/realtime.py	254	async def update_tools(self, tools: list[Tool]) -> None: ...	CODE
LOW⚡	livekit-agents/livekit/agents/llm/realtime.py	257	def update_options(self, *, tool_choice: NotGivenOr[ToolChoice \| None] = NOT_GIVEN) -> None: ...	CODE
LOW	livekit-agents/livekit/agents/llm/tool_context.py	585	def update_tools(self, tools: Sequence[Tool \| Toolset]) -> None:	CODE
LOW	livekit-agents/livekit/agents/llm/__init__.py	64	__all__ = [	CODE
LOW	…agents/livekit/agents/llm/realtime_fallback_adapter.py	244	def _set_available(self, index: int, available: bool) -> None:	CODE
LOW⚡	…agents/livekit/agents/llm/realtime_fallback_adapter.py	409	async def update_instructions(self, instructions: str) -> None:	CODE
LOW⚡	…agents/livekit/agents/llm/realtime_fallback_adapter.py	413	async def update_chat_ctx(self, chat_ctx: ChatContext) -> None:	CODE
LOW⚡	…agents/livekit/agents/llm/realtime_fallback_adapter.py	419	async def update_tools(self, tools: list[Tool]) -> None:	CODE
LOW⚡	…agents/livekit/agents/llm/realtime_fallback_adapter.py	423	def update_options(self, *, tool_choice: NotGivenOr[ToolChoice \| None] = NOT_GIVEN) -> None:	CODE
LOW	…vekit-agents/livekit/agents/llm/remote_chat_context.py	7	__all__ = ["RemoteChatContext"]	CODE
LOW	…agents/livekit/agents/llm/_provider_format/__init__.py	3	__all__ = ["openai", "openai.responses", "google", "aws", "anthropic", "mistralai"]	CODE
LOW	livekit-agents/livekit/agents/utils/http_context.py	31	def _set_default_cert_env() -> None:	CODE
LOW	livekit-agents/livekit/agents/utils/__init__.py	16	__all__ = [	CODE
LOW	livekit-agents/livekit/agents/utils/exp_filter.py	63	def update_base(self, alpha: float) -> None:	CODE
LOW	livekit-agents/livekit/agents/utils/codecs/__init__.py	17	__all__ = ["AudioStreamDecoder", "StreamBuffer"]	CODE
LOW	livekit-agents/livekit/agents/utils/hw/__init__.py	3	__all__ = [	CODE
LOW	livekit-agents/livekit/agents/utils/images/__init__.py	17	__all__ = ["EncodeOptions", "ResizeOptions", "encode"]	CODE
LOW	livekit-agents/livekit/agents/utils/aio/__init__.py	10	__all__ = [	CODE
LOW	livekit-agents/livekit/agents/cli/readchar.py	7	__all__ = ["readchar", "readkey", "key"]	CODE
LOW	livekit-agents/livekit/agents/cli/__init__.py	3	__all__ = ["run_app", "AgentsConsole"]	CODE
LOW	livekit-agents/livekit/agents/cli/_legacy.py	562	def set_microphone_enabled(self, enable: bool, *, device: int \| str \| None = None) -> None:	CODE
207 more matches not shown…

Over-Commented Block274 hits · 266 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_plugin_assemblyai_stt.py	901		COMMENT
LOW	tests/test_tts.py	681	)	COMMENT
LOW	tests/test_llm.py	1	# from __future__ import annotations	COMMENT
LOW	tests/test_llm.py	21		COMMENT
LOW	tests/test_llm.py	41	# self,	COMMENT
LOW	tests/test_llm.py	61	# def update_user_info(	COMMENT
LOW	tests/test_llm.py	81	# # instructions="You are a basic assistant",	COMMENT
LOW	tests/test_llm.py	101	# # Anthropic and vertex requires at least one message (system messages don't count)	COMMENT
LOW	tests/test_llm.py	121	# async def test_llm_chat_with_consecutive_messages(	COMMENT
LOW	tests/test_llm.py	141	# if content:	COMMENT
LOW	tests/test_llm.py	161		COMMENT
LOW	tests/test_llm.py	181		COMMENT
LOW	tests/test_llm.py	201		COMMENT
LOW	tests/test_llm.py	221	# )	COMMENT
LOW	tests/test_llm.py	241	# call = calls[0]	COMMENT
LOW	tests/test_llm.py	261		COMMENT
LOW	tests/test_llm.py	281	# fnc_ctx = FncCtx()	COMMENT
LOW	tests/test_llm.py	301		COMMENT
LOW	tests/test_llm.py	321	# llm.ToolChoice(type="function", name="get_weather"),	COMMENT
LOW	tests/test_llm.py	341	# user_request: str,	COMMENT
LOW	tests/test_llm.py	361		COMMENT
LOW	tests/test_llm.py	381	# role="system",	COMMENT
LOW	tests/test_llm.py	401	# width=512, height=512, type=VideoBufferType.RGBA, data=image_data	COMMENT
LOW	tests/test_llm.py	421	# images=[llm.ChatImage(image=_HEARTS_IMAGE_DATA_URL, inference_detail="low")],	COMMENT
LOW	tests/test_llm.py	441	# input_llm = llm_factory()	COMMENT
LOW	tests/test_llm.py	461		COMMENT
LOW	examples/playground.yaml	1	# Examples metadata consumed by livekit/agents-jukebox.	COMMENT
LOW	examples/playground.yaml	121	101110011101	COMMENT
LOW	examples/playground.yaml	161	022222222220	COMMENT
LOW	examples/data_capture_sim/scenarios.yaml	1	# Scenarios for the data-capture workflow refactor: confirm_* / update_* tools	COMMENT
LOW	examples/voice_agents/otel_trace.py	21	from livekit.agents.voice import MetricsCollectedEvent	COMMENT
LOW	examples/hotel_receptionist/scenarios.yaml	1	# Assumptions:	COMMENT
LOW	examples/hotel_receptionist/fake_data/seed.py	61	# offset < 0 and offset+nights > 0 -> in-house now; offset > 0 -> upcoming; else departed.	COMMENT
LOW	examples/hotel_receptionist/fake_data/seed.py	81	("Paul", "Greer", "paul.greer@gmail.com", "+1 415 555 0356", "PG11", "203", 0, 1, 1, [], "2218", "confirmed"),	COMMENT
LOW	examples/frontdesk/scenarios.yaml	1	# These scenarios use absolute dates against a fixed clock:	COMMENT
LOW	examples/avatar/pyproject.toml	21	# No [tool.uv.sources] here: the workspace root repoints the livekit-* deps at	COMMENT
LOW	.github/convert_html_docs.py	901		COMMENT
LOW	livekit-agents/livekit/agents/worker.py	1	# Copyright 2023 LiveKit, Inc.	COMMENT
LOW	livekit-agents/livekit/agents/version.py	1	# Copyright 2023 LiveKit, Inc.	COMMENT
LOW	livekit-agents/livekit/agents/job.py	1	# Copyright 2023 LiveKit, Inc.	COMMENT
LOW	livekit-agents/livekit/agents/__init__.py	1	# Copyright 2023 LiveKit, Inc.	COMMENT
LOW	livekit-agents/livekit/agents/language.py	1	# Copyright 2023 LiveKit, Inc.	COMMENT
LOW	livekit-agents/livekit/agents/_language_data.py	1	# Copyright 2023 LiveKit, Inc.	COMMENT
LOW	livekit-agents/livekit/agents/llm/tool_context.py	1	# Copyright 2023 LiveKit, Inc.	COMMENT
LOW	livekit-agents/livekit/agents/llm/chat_context.py	1	# Copyright 2023 LiveKit, Inc.	COMMENT
LOW	livekit-agents/livekit/agents/utils/codecs/decoder.py	1	# Copyright 2024 LiveKit, Inc.	COMMENT
LOW	livekit-agents/livekit/agents/utils/codecs/__init__.py	1	# Copyright 2024 LiveKit, Inc.	COMMENT
LOW	livekit-agents/livekit/agents/utils/images/__init__.py	1	# Copyright 2024 LiveKit, Inc.	COMMENT
LOW	livekit-agents/livekit/agents/utils/images/image.py	1	# Copyright 2024 LiveKit, Inc.	COMMENT
LOW	livekit-agents/livekit/agents/cli/_legacy.py	81		COMMENT
LOW	livekit-agents/livekit/agents/voice/agent_activity.py	3221	# the LLM isn't instructed or few-shotted into emitting tags nothing	COMMENT
LOW	…t-agents/livekit/agents/voice/transcription/filters.py	61		COMMENT
LOW	livekit-agents/livekit/agents/tts/_provider_format.py	121	secs = float(raw[:-2]) / 1000 if raw.endswith("ms") else float(raw.rstrip("s"))	COMMENT
LOW	livekit-agents/livekit/agents/tts/_provider_format.py	201	return "[long-break]" if secs >= 1.0 else "[break]"	COMMENT
LOW	livekit-agents/livekit/agents/inference/vad.py	1	# Copyright 2026 LiveKit, Inc.	COMMENT
LOW	…ugins-smallestai/livekit/plugins/smallestai/version.py	1	# Copyright 2025 LiveKit, Inc.	COMMENT
LOW	…t-plugins-smallestai/livekit/plugins/smallestai/tts.py	1	# Copyright 2025 LiveKit, Inc.	COMMENT
LOW	…gins-smallestai/livekit/plugins/smallestai/__init__.py	1	# Copyright 2023 LiveKit, Inc.	COMMENT
LOW	…t-plugins-smallestai/livekit/plugins/smallestai/stt.py	1	# Copyright 2025 LiveKit, Inc.	COMMENT
LOW	…t-plugins-smallestai/livekit/plugins/smallestai/stt.py	721	def _batch_transcription_to_speech_event(	COMMENT
214 more matches not shown…

AI Structural Patterns188 hits · 178 pts

Severity	File	Line	Context
LOW	tests/test_amd_classifier.py	31	CODE
LOW	tests/test_plugin_bland_tts.py	375	CODE
LOW	livekit-agents/livekit/agents/worker.py	303	CODE
LOW	livekit-agents/livekit/agents/worker.py	857	CODE
LOW	livekit-agents/livekit/agents/beta/workflows/address.py	26	CODE
LOW	…it-agents/livekit/agents/beta/workflows/credit_card.py	572	CODE
LOW	…t-agents/livekit/agents/beta/workflows/phone_number.py	63	CODE
LOW	…-agents/livekit/agents/beta/workflows/email_address.py	27	CODE
LOW	livekit-agents/livekit/agents/beta/workflows/dob.py	61	CODE
LOW	livekit-agents/livekit/agents/beta/workflows/name.py	74	CODE
LOW	…-agents/livekit/agents/beta/workflows/warm_transfer.py	40	CODE
LOW	livekit-agents/livekit/agents/voice/turn.py	336	CODE
LOW	livekit-agents/livekit/agents/voice/agent_session.py	372	CODE
LOW	livekit-agents/livekit/agents/voice/agent_activity.py	1589	CODE
LOW	livekit-agents/livekit/agents/voice/agent.py	39	CODE
LOW	livekit-agents/livekit/agents/voice/agent.py	818	CODE
LOW	livekit-agents/livekit/agents/voice/amd/detector.py	168	CODE
LOW	livekit-agents/livekit/agents/voice/amd/classifier.py	106	CODE
LOW	livekit-agents/livekit/agents/inference/tts.py	267	CODE
LOW	livekit-agents/livekit/agents/inference/tts.py	286	CODE
LOW	livekit-agents/livekit/agents/inference/tts.py	305	CODE
LOW	livekit-agents/livekit/agents/inference/tts.py	324	CODE
LOW	livekit-agents/livekit/agents/inference/tts.py	343	CODE
LOW	livekit-agents/livekit/agents/inference/tts.py	362	CODE
LOW	livekit-agents/livekit/agents/inference/tts.py	381	CODE
LOW	livekit-agents/livekit/agents/inference/tts.py	400	CODE
LOW	livekit-agents/livekit/agents/inference/tts.py	418	CODE
LOW	livekit-agents/livekit/agents/inference/avatar.py	127	CODE
LOW	livekit-agents/livekit/agents/inference/vad.py	59	CODE
LOW	livekit-agents/livekit/agents/inference/interruption.py	274	CODE
LOW	livekit-agents/livekit/agents/inference/stt.py	424	CODE
LOW	livekit-agents/livekit/agents/inference/stt.py	441	CODE
LOW	livekit-agents/livekit/agents/inference/stt.py	458	CODE
LOW	livekit-agents/livekit/agents/inference/stt.py	475	CODE
LOW	livekit-agents/livekit/agents/inference/stt.py	492	CODE
LOW	livekit-agents/livekit/agents/inference/stt.py	509	CODE
LOW	livekit-agents/livekit/agents/inference/stt.py	526	CODE
LOW	livekit-agents/livekit/agents/inference/stt.py	544	CODE
LOW	livekit-agents/livekit/agents/inference/stt.py	561	CODE
LOW	livekit-agents/livekit/agents/inference/stt.py	578	CODE
LOW	livekit-agents/livekit/agents/inference/stt.py	594	CODE
LOW	livekit-agents/livekit/agents/inference/eot/detector.py	34	CODE
LOW	…t-plugins-smallestai/livekit/plugins/smallestai/tts.py	64	CODE
LOW	…t-plugins-smallestai/livekit/plugins/smallestai/tts.py	184	CODE
LOW	…t-plugins-smallestai/livekit/plugins/smallestai/stt.py	110	CODE
LOW	…t-plugins-smallestai/livekit/plugins/smallestai/stt.py	308	CODE
LOW	…t-plugins-smallestai/livekit/plugins/smallestai/stt.py	395	CODE
LOW	…vekit-plugins-cerebras/livekit/plugins/cerebras/llm.py	103	CODE
LOW	…s/livekit-plugins-sarvam/livekit/plugins/sarvam/tts.py	460	CODE
LOW	…s/livekit-plugins-sarvam/livekit/plugins/sarvam/tts.py	736	CODE
LOW	…plugins-sarvam/livekit/plugins/sarvam/stt_streaming.py	229	CODE
LOW	…plugins-sarvam/livekit/plugins/sarvam/stt_streaming.py	340	CODE
LOW	…plugins-sarvam/livekit/plugins/sarvam/stt_streaming.py	539	CODE
LOW	…s/livekit-plugins-sarvam/livekit/plugins/sarvam/stt.py	468	CODE
LOW	…s/livekit-plugins-sarvam/livekit/plugins/sarvam/stt.py	736	CODE
LOW	…it-plugins-sarvam/livekit/plugins/sarvam/llm/client.py	159	CODE
LOW	…plugins/livekit-plugins-aws/livekit/plugins/aws/tts.py	60	CODE
LOW	…plugins/livekit-plugins-aws/livekit/plugins/aws/llm.py	80	CODE
LOW	…plugins/livekit-plugins-aws/livekit/plugins/aws/stt.py	104	CODE
LOW	…it/plugins/aws/experimental/realtime/realtime_model.py	328	CODE
128 more matches not shown…

Cross-File Repetition29 hits · 145 pts

Severity	File	Snippet	Context
HIGH	livekit-agents/livekit/agents/vad.py	mark the end of input, no more audio will be pushed	STRING
HIGH	…s/livekit/agents/voice/transcription/_speaking_rate.py	mark the end of input, no more audio will be pushed	STRING
HIGH	livekit-agents/livekit/agents/inference/interruption.py	mark the end of input, no more audio will be pushed	STRING
HIGH	livekit-agents/livekit/agents/stt/stt.py	mark the end of input, no more audio will be pushed	STRING
HIGH	livekit-agents/livekit/agents/llm/llm.py	get the provider name/identifier for this stt instance. returns: the provider name if available, "unknown" otherwise. no	STRING
HIGH	livekit-agents/livekit/agents/tts/tts.py	get the provider name/identifier for this stt instance. returns: the provider name if available, "unknown" otherwise. no	STRING
HIGH	livekit-agents/livekit/agents/stt/stt.py	get the provider name/identifier for this stt instance. returns: the provider name if available, "unknown" otherwise. no	STRING
HIGH	livekit-agents/livekit/agents/llm/fallback_adapter.py	agent fallback adapter for stt. manages multiple stt instances with automatic fallback when the primary provider fails.	STRING
HIGH	livekit-agents/livekit/agents/tts/fallback_adapter.py	agent fallback adapter for stt. manages multiple stt instances with automatic fallback when the primary provider fails.	STRING
HIGH	livekit-agents/livekit/agents/stt/fallback_adapter.py	agent fallback adapter for stt. manages multiple stt instances with automatic fallback when the primary provider fails.	STRING
HIGH	livekit-agents/livekit/agents/llm/fallback_adapter.py	metadata of the instance that most recently served a request (the primary before any traffic).	STRING
HIGH	livekit-agents/livekit/agents/tts/fallback_adapter.py	metadata of the instance that most recently served a request (the primary before any traffic).	STRING
HIGH	livekit-agents/livekit/agents/stt/fallback_adapter.py	metadata of the instance that most recently served a request (the primary before any traffic).	STRING
HIGH	…plugins-fireworksai/livekit/plugins/fireworksai/stt.py	run a single websocket connection to baseten and make sure to reconnect when something went wrong.	STRING
HIGH	…livekit-plugins-gradium/livekit/plugins/gradium/stt.py	run a single websocket connection to baseten and make sure to reconnect when something went wrong.	STRING
HIGH	…livekit-plugins-baseten/livekit/plugins/baseten/stt.py	run a single websocket connection to baseten and make sure to reconnect when something went wrong.	STRING
HIGH	…s/livekit-plugins-openai/livekit/plugins/openai/tts.py	create a new instance of groq stt. ``api_key`` must be set to your groq api key, either using the argument or by setting	STRING
HIGH	…s/livekit-plugins-openai/livekit/plugins/openai/llm.py	create a new instance of groq stt. ``api_key`` must be set to your groq api key, either using the argument or by setting	STRING
HIGH	…plugins-openai/livekit/plugins/openai/responses/llm.py	create a new instance of groq stt. ``api_key`` must be set to your groq api key, either using the argument or by setting	STRING
HIGH	…t-plugins-perplexity/livekit/plugins/perplexity/llm.py	create a new instance of groq stt. ``api_key`` must be set to your groq api key, either using the argument or by setting	STRING
HIGH	…perplexity/livekit/plugins/perplexity/responses/llm.py	create a new instance of groq stt. ``api_key`` must be set to your groq api key, either using the argument or by setting	STRING
HIGH	…/livekit-plugins-groq/livekit/plugins/groq/services.py	create a new instance of groq stt. ``api_key`` must be set to your groq api key, either using the argument or by setting	STRING
HIGH	…livekit-plugins-baseten/livekit/plugins/baseten/llm.py	create a new instance of groq stt. ``api_key`` must be set to your groq api key, either using the argument or by setting	STRING
HIGH	…lugins-elevenlabs/livekit/plugins/elevenlabs/_utils.py	create a new periodic collector that accumulates values and calls the callback after the specified duration if there are	STRING
HIGH	…it-plugins-deepgram/livekit/plugins/deepgram/_utils.py	create a new periodic collector that accumulates values and calls the callback after the specified duration if there are	STRING
HIGH	…ivekit-plugins-gladia/livekit/plugins/gladia/_utils.py	create a new periodic collector that accumulates values and calls the callback after the specified duration if there are	STRING
HIGH	…lugins-elevenlabs/livekit/plugins/elevenlabs/_utils.py	force callback to be called with current total if non-zero	STRING
HIGH	…it-plugins-deepgram/livekit/plugins/deepgram/_utils.py	force callback to be called with current total if non-zero	STRING
HIGH	…ivekit-plugins-gladia/livekit/plugins/gladia/_utils.py	force callback to be called with current total if non-zero	STRING

Docstring Block Structure28 hits · 140 pts

Severity	File	Line	Snippet	Context
HIGH	livekit-agents/livekit/agents/utils/env.py	8	Resolve an environment variable from a list of potential sources. Args: val: The value to resolve.	STRING
HIGH	livekit-agents/livekit/agents/utils/participant.py	16	Wait for an agent participant to join the room. Args: room: The room to wait for the agent in.	STRING
HIGH	livekit-agents/livekit/agents/utils/audio.py	286	Push an audio frame to the buffer. Args: frame: The audio frame to push. Returns:	STRING
HIGH	livekit-agents/livekit/agents/voice/agent_session.py	1590	Commit the user turn and generate a reply. Returns a future that resolves with the user's audio transcript once	STRING
HIGH	livekit-agents/livekit/agents/voice/run_result.py	328	Access a specific event or range for assertions. Args: key (int \| slice): Index or slice o	STRING
HIGH	livekit-agents/livekit/agents/voice/run_result.py	678	Verify this event is a function call with matching details. Args: name (str, optional): Ex	STRING
HIGH	livekit-agents/livekit/agents/voice/run_result.py	714	Verify this event is a function call output with matching details. Args: output (str, opti	STRING
HIGH	livekit-agents/livekit/agents/voice/run_result.py	744	Verify this event is a message from the given role. Args: role (ChatRole, optional): Expec	STRING
HIGH	livekit-agents/livekit/agents/voice/run_result.py	773	Verify this event is an agent handoff. Args: new_agent_type (type, optional): Expected new	STRING
HIGH	livekit-agents/livekit/agents/voice/run_result.py	814	Assert that a function call matching criteria exists in the event range. Args: name (str,	STRING
HIGH	livekit-agents/livekit/agents/voice/run_result.py	847	Assert that a message matching criteria exists in the event range. Args: role (ChatRole, o	STRING
HIGH	livekit-agents/livekit/agents/voice/run_result.py	880	Assert that a function call output matching criteria exists in the event range. Args: outp	STRING
HIGH	livekit-agents/livekit/agents/voice/run_result.py	911	Assert that an agent handoff matching criteria exists in the event range. Args: new_agent_	STRING
HIGH	…s/livekit-plugins-sarvam/livekit/plugins/sarvam/stt.py	171	Validate and resolve mode for a given model. Args: model: The Sarvam model name. mode: The requeste	STRING
HIGH	…s/livekit-plugins-sarvam/livekit/plugins/sarvam/stt.py	205	Validate language code for a given model. Args: model: The Sarvam model name. language: The request	STRING
HIGH	…s/livekit-plugins-sarvam/livekit/plugins/sarvam/stt.py	615	Recognize speech using Sarvam.ai API. Args: buffer: Audio buffer containing speech data	STRING
HIGH	…it-plugins/livekit-durable/livekit/durable/registry.py	55	Register a function in the in-memory function registry. When serializing a registered function, a reference to the	STRING
HIGH	…it-plugins/livekit-durable/livekit/durable/registry.py	94	Lookup a registered function by key. Args: key: Unique identifier for the function. Returns: R	STRING
HIGH	…kit-plugins-protoface/livekit/plugins/protoface/api.py	73	Create a hosted Protoface avatar session. Args: avatar_id: Protoface avatar ID to render.	STRING
HIGH	…kit-plugins-protoface/livekit/plugins/protoface/api.py	97	Request a graceful end for a hosted Protoface session. Args: session_id: Protoface session ID retur	STRING
HIGH	…enai/livekit/plugins/openai/realtime/realtime_model.py	415	Initialize a Realtime model client for OpenAI or Azure OpenAI. Args: model (str): Realtime	STRING
HIGH	…enai/livekit/plugins/openai/realtime/realtime_model.py	586	Create a RealtimeModel configured for Azure OpenAI. Args: azure_deployment (str): Azure Op	STRING
HIGH	…ekit-plugins-cambai/livekit/plugins/cambai/__init__.py	36	List available voices from Camb.ai. Args: api_key: Camb.ai API key (or use CAMB_API_KEY env var).	STRING
HIGH	…vekit-plugins-avatario/livekit/plugins/avatario/api.py	99	Make a POST request to the Avatario API with retry logic. Args: payload: JSON payload for	STRING
HIGH	…s/livekit-plugins-silero/livekit/plugins/silero/vad.py	75	Load and initialize the Silero VAD model. This method loads the ONNX model and prepares it for inferen	STRING
HIGH	…vekit-plugins-cartesia/livekit/plugins/cartesia/stt.py	113	Create a new instance of Cartesia STT. Model ``ink-2`` supports: - Streaming -	STRING
HIGH	…ins/livekit-plugins-tavus/livekit/plugins/tavus/api.py	166	Make a POST request to the Tavus API with retry logic. Args: endpoint: API endpoint path (	STRING
HIGH	…t-plugins-lemonslice/livekit/plugins/lemonslice/api.py	211	Make a POST request to the LemonSlice API with retry logic. Args: payload: JSON payload fo	STRING

Magic Placeholder Names16 hits · 82 pts

Severity	File	Line	Snippet	Context
HIGH	examples/README.md	74	LIVEKIT_API_KEY="your_api_key"	CODE
HIGH	examples/other/transcription/README.md	19	export OPENAI_API_KEY=your-api-key	CODE
HIGH⚡	livekit-plugins/livekit-plugins-gnani/README.md	39	export GNANI_API_KEY="your-api-key"	CODE
HIGH⚡	livekit-plugins/livekit-plugins-gnani/README.md	45	stt = STT(api_key="your-api-key", language="hi-IN")	CODE
HIGH⚡	livekit-plugins/livekit-plugins-gnani/README.md	46	tts = TTS(api_key="your-api-key")	CODE
HIGH	…enai/livekit/plugins/openai/realtime/realtime_model.py	624	api_key="your-api-key",	STRING
HIGH	…enai/livekit/plugins/openai/realtime/realtime_model.py	650	api_key="your-api-key",	STRING
HIGH	livekit-plugins/livekit-plugins-cambai/README.md	88	api_key="your-api-key", # Or use CAMB_API_KEY env var	CODE
HIGH	livekit-plugins/livekit-plugins-fishaudio/README.md	20	FISH_API_KEY=<your_api_key>	CODE
HIGH	livekit-plugins/livekit-plugins-did/README.md	24	-H "Authorization: Basic <YOUR_API_KEY>" \	CODE
HIGH	livekit-plugins/livekit-plugins-did/README.md	24	-H "Authorization: Basic <YOUR_API_KEY>" \	CODE
HIGH	livekit-plugins/livekit-plugins-gladia/README.md	35	api_key="your-api-key-here", # or use GLADIA_API_KEY env var	CODE
HIGH	livekit-plugins/livekit-plugins-gladia/README.md	96	api_key="your-api-key-here",	CODE
HIGH	livekit-plugins/livekit-plugins-resemble/README.md	30	api_key="your_api_key", # or set RESEMBLE_API_KEY environment variable	CODE
HIGH	livekit-plugins/livekit-plugins-resemble/README.md	73	api_key="your_api_key",	CODE
HIGH	livekit-plugins/livekit-plugins-resemble/README.md	105	api_key="your_api_key",	CODE

Self-Referential Comments16 hits · 50 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tests/test_convert_html_docs.py	299	# Create a path that would have .. in relative parts	COMMENT
MEDIUM	tests/concurrency.py	924	# This module is loaded as a global plugin (`-p tests.concurrency` in pyproject), not via	COMMENT
MEDIUM	tests/test_drain_timeout.py	121	# Create a fake proc whose join() never completes (stuck process)	COMMENT
MEDIUM	tests/test_speaker_id_grouping.py	34	# Create a SpeakerSpeechData object and get formatted text	COMMENT
MEDIUM	livekit-agents/livekit/agents/voice/agent_activity.py	821	# Create a wrapper coroutine that runs in the captured context	COMMENT
MEDIUM	livekit-agents/livekit/agents/telemetry/http_server.py	22	# Create a new registry for this request to collect metrics from all processes	COMMENT
MEDIUM	…s/livekit-plugins-sarvam/livekit/plugins/sarvam/stt.py	852	# Create a fresh session for this stream to avoid conflicts	COMMENT
MEDIUM	…it/plugins/aws/experimental/realtime/realtime_model.py	598	# Create main task to manage session lifecycle	COMMENT
MEDIUM	…/livekit-plugins-krisp/examples/krisp_agent_example.py	87	# Create the Krisp voice isolation FrameProcessor.	COMMENT
MEDIUM	…ivekit-plugins-krisp/examples/krisp_minimal_example.py	41	# Create the frame processor with explicit license auth (no framework	COMMENT
MEDIUM	…ivekit-plugins-krisp/examples/krisp_minimal_example.py	52	# Create a test audio frame (10ms @ 16kHz = 160 samples)	COMMENT
MEDIUM	…ugins-speechmatics/livekit/plugins/speechmatics/stt.py	392	# Create the stream	COMMENT
MEDIUM	…ugins-speechmatics/livekit/plugins/speechmatics/stt.py	647	# Create the Voice Agent client	COMMENT
MEDIUM	…s/livekit-plugins-gladia/livekit/plugins/gladia/stt.py	440	# Create a speech event from the collected final utterances	COMMENT
MEDIUM	…s/livekit-plugins-google/livekit/plugins/google/stt.py	78	# This class is only be used internally to encapsulate the options	COMMENT
MEDIUM	…plugins-simplismart/livekit/plugins/simplismart/stt.py	292	# Create a fresh session for this stream to avoid conflicts	COMMENT

Hallucination Indicators4 hits · 40 pts

Severity	File	Line	Snippet	Context
CRITICAL	…s/livekit-plugins-openai/livekit/plugins/openai/tts.py	257	oai_stream = self._tts._client.audio.speech.with_streaming_response.create(	CODE
CRITICAL	…kit-plugins-mistralai/livekit/plugins/mistralai/tts.py	156	stream = await self._tts._client.audio.speech.complete_async(	CODE
CRITICAL	…kit-plugins-mistralai/livekit/plugins/mistralai/tts.py	165	stream = await self._tts._client.audio.speech.complete_async(	CODE
CRITICAL	…ugins-google/livekit/plugins/google/beta/gemini_tts.py	214	response = await self._tts._client.aio.models.generate_content_stream(	CODE

Fake / Example Data36 hits · 38 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_ipc.py	121	token="fake_token",	CODE
LOW	tests/test_plugin_soniox_tts.py	105	tts = soniox.TTS(api_key="fake-key", **tts_kwargs)	CODE
LOW⚡	tests/test_plugin_soniox_tts.py	171	soniox.TTS(api_key="fake-key", stream_idle_timeout=0)	CODE
LOW⚡	tests/test_plugin_soniox_tts.py	173	soniox.TTS(api_key="fake-key", stream_idle_timeout=-1.0)	CODE
LOW	tests/test_plugin_google_realtime.py	67	monkeypatch.setenv("GOOGLE_API_KEY", "fake-key")	CODE
LOW	tests/test_plugin_google_realtime.py	83	monkeypatch.setenv("GOOGLE_API_KEY", "fake-key")	CODE
LOW	tests/test_plugin_google_realtime.py	508	monkeypatch.setenv("GOOGLE_API_KEY", "fake-key")	CODE
LOW	tests/test_plugin_google_realtime.py	524	monkeypatch.setenv("GOOGLE_API_KEY", "fake-key")	CODE
LOW⚡	tests/test_plugin_openai_stt_context.py	260	instance._update_session_keyterms(["billing", "Acme Corp"])	CODE
LOW⚡	tests/test_plugin_openai_stt_context.py	264	assert instance._opts.keywords == ["AC-42", "billing", "Acme Corp"]	CODE
LOW⚡	tests/test_plugin_openai_stt_context.py	265	assert _sent_transcription(ws)["keywords"] == ["AC-42", "billing", "Acme Corp"]	CODE
LOW⚡	tests/test_plugin_openai_stt_context.py	280	instance.update_options(keywords=["Acme Corp"], prompt="a support call")	CODE
LOW⚡	tests/test_plugin_openai_stt_context.py	282	assert _sent_transcription(ws)["keywords"] == ["Acme Corp"]	CODE
LOW⚡	tests/test_plugin_openai_stt_context.py	395	instance._update_session_keyterms(["Acme Corp"])	CODE
LOW⚡	tests/test_plugin_openai_stt_context.py	407	instance._update_session_keyterms(["Acme Corp"])	CODE
LOW⚡	tests/test_plugin_openai_stt_context.py	567	instance.update_options(keywords=["Acme Corp"])	CODE
LOW⚡	tests/test_plugin_openai_stt_context.py	572	assert [_transcription_of(p).get("keywords") for p in ws.sent] == [[], ["Acme Corp"]]	CODE
LOW⚡	tests/test_plugin_openai_stt_context.py	585	instance.update_options(keywords=["Acme Corp"])	CODE
LOW⚡	tests/test_plugin_openai_stt_context.py	591	assert _sent_transcription(ws)["keywords"] == ["Acme Corp"]	CODE
LOW⚡	tests/test_plugin_openai_stt_context.py	676	instance.update_options(keywords=["Acme Corp"])	CODE
LOW⚡	tests/test_plugin_openai_stt_context.py	689	instance.update_options(keywords=["Acme Corp"])	CODE
LOW⚡	tests/test_plugin_openai_stt_context.py	691	assert pinned._opts.keywords == ["Acme Corp"] # the rest still reaches it	CODE
LOW⚡	tests/test_plugin_openai_stt_context.py	709	instance._update_session_keyterms(["Acme Corp"])	CODE
LOW⚡	tests/test_plugin_openai_stt_context.py	713	assert config["keywords"] == ["Acme Corp"]	CODE
LOW	tests/test_plugin_openai_stt_context.py	602	({"keywords": ["Acme Corp"]}, 1), # a session.update on acquire carries this one	CODE
LOW⚡	tests/test_recording.py	532	assert serialized_stt_options["lk.pii.keyterms"] == ["Acme Corp"]	CODE
LOW⚡	tests/test_recording.py	534	assert stt_context_options["keyterms"] == ["Acme Corp"]	CODE
LOW	tests/test_recording.py	517	"keyterms": ["Acme Corp"],	CODE
LOW⚡	tests/test_stt_context.py	182	d = _detector(static_keyterms=["Acme Corp"], llm=fake)	CODE
LOW⚡	tests/test_stt_context.py	188	assert "Acme Corp" in applied_section	CODE
LOW	examples/hotel_receptionist/README.md	11	uv run examples/hotel_receptionist/fake_data/seed.py	CODE
LOW	examples/hotel_receptionist/README.md	17	`fake_data/seed.py` prints sample confirmation codes you can use to try	CODE
LOW	examples/hotel_receptionist/README.md	30	fake_data/seed.py — manual seed script (writes fake_data/hotel.db)	CODE
LOW	examples/hotel_receptionist/agent.py	17	from fake_data.seed import build_seed_bytes	CODE
LOW	examples/hotel_receptionist/fake_data/seed.py	3	python fake_data/seed.py [path/to/hotel.db] # write a seed file (for inspection)	STRING
LOW	…vekit-agents/livekit/agents/voice/keyterm_detection.py	69	"keyterms": ["LiveKit", "Acme Corp"],	STRING

Verbosity Indicators17 hits · 29 pts

Severity	File	Line	Snippet	Context
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	689	# Step 1: Wait for assistant to finish speaking (AUDIO contentEnd with END_TURN)	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	698	# Step 2: Wait for audio to fully stop (no new audio for 1 second)	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	712	# Step 3: Send close events to trigger completionEnd from Nova Sonic	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	719	# Step 4: Wait for completionEnd and let _done_fut resolve	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	740	# Step 1: Drain any pending tool results	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	754	# Step 2: Signal tasks to stop	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	757	# Step 3: Wait for response task to exit naturally, then cancel if needed	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	771	# Step 4: Cancel audio input task (blocked on channel, won't exit naturally)	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	779	# Step 5: Close the stream (close events already sent in _session_recycle_timer)	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	787	# Step 6: Reset state for new session	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	1022	# Step 1: Send session init events (session start, prompt start, system prompt)	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	1030	# Step 2: Send history events with small delays between them	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	1035	# Step 3: Start response reader first (calls await_output, sets _stream_ready)	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	1040	# Step 4: Start audio input (waits for _stream_ready before sending audio_content_start)	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	1045	# Step 5: Allow audio contentStart to be sent before unblocking	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	1051	# Step 6: If we popped a user message from history, send it as	COMMENT
LOW	…it/plugins/aws/experimental/realtime/realtime_model.py	801	# Step 7: Start new session with preserved state	COMMENT

Structural Annotation Overuse17 hits · 29 pts

Severity	File	Line	Snippet	Context
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	689	# Step 1: Wait for assistant to finish speaking (AUDIO contentEnd with END_TURN)	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	698	# Step 2: Wait for audio to fully stop (no new audio for 1 second)	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	712	# Step 3: Send close events to trigger completionEnd from Nova Sonic	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	719	# Step 4: Wait for completionEnd and let _done_fut resolve	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	740	# Step 1: Drain any pending tool results	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	754	# Step 2: Signal tasks to stop	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	757	# Step 3: Wait for response task to exit naturally, then cancel if needed	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	771	# Step 4: Cancel audio input task (blocked on channel, won't exit naturally)	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	779	# Step 5: Close the stream (close events already sent in _session_recycle_timer)	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	787	# Step 6: Reset state for new session	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	1022	# Step 1: Send session init events (session start, prompt start, system prompt)	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	1030	# Step 2: Send history events with small delays between them	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	1035	# Step 3: Start response reader first (calls await_output, sets _stream_ready)	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	1040	# Step 4: Start audio input (waits for _stream_ready before sending audio_content_start)	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	1045	# Step 5: Allow audio contentStart to be sent before unblocking	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	1051	# Step 6: If we popped a user message from history, send it as	COMMENT
LOW	…it/plugins/aws/experimental/realtime/realtime_model.py	801	# Step 7: Start new session with preserved state	COMMENT

Redundant / Tautological Comments17 hits · 25 pts

Severity	File	Line	Snippet	Context
LOW	livekit-agents/livekit/agents/ipc/log_queue.py	95	# Check if Python is shutting down	COMMENT
LOW	livekit-agents/livekit/agents/telemetry/http_server.py	20	# Check if multiprocess mode is enabled	COMMENT
LOW	livekit-agents/livekit/agents/telemetry/traces.py	344	# Check if a tracer provider is not set and set one up	COMMENT
LOW	…s/livekit-plugins-sarvam/livekit/plugins/sarvam/stt.py	1186	# Check if session is still valid	COMMENT
LOW	…s/livekit-plugins-sarvam/livekit/plugins/sarvam/stt.py	1243	# Check if reconnection was requested	COMMENT
LOW	…s/livekit-plugins-sarvam/livekit/plugins/sarvam/stt.py	1337	# Check if we have enough data for a chunk	COMMENT
LOW	…s/livekit-plugins-sarvam/livekit/plugins/sarvam/stt.py	1384	# Check if Sarvam VAD triggered flush	COMMENT
LOW	…s/livekit-plugins-sarvam/livekit/plugins/sarvam/stt.py	1664	# Set flag to trigger flush when Sarvam detects end of speech	COMMENT
LOW⚡	…it/plugins/aws/experimental/realtime/realtime_model.py	1417	# Check if this is END_TURN (assistant finished speaking)	COMMENT
LOW	…it/plugins/aws/experimental/realtime/realtime_model.py	1836	# Check if this is an audio message (already transcribed by Nova)	COMMENT
LOW	…it/plugins/aws/experimental/realtime/realtime_model.py	2144	# Check if generate_reply is supported (requires mixed modalities)	COMMENT
LOW⚡	…it-plugins-bithuman/livekit/plugins/bithuman/avatar.py	70	# Check if string is empty after cleaning	COMMENT
LOW⚡	…it-plugins-bithuman/livekit/plugins/bithuman/avatar.py	79	# Check if string contains only valid base64 characters	COMMENT
LOW	…ugins-speechmatics/livekit/plugins/speechmatics/stt.py	514	# Check if diarization is enabled	COMMENT
LOW	…ox/livekit/plugins/ultravox/realtime/realtime_model.py	758	# Check if restart is needed	COMMENT
LOW	…ox/livekit/plugins/ultravox/realtime/realtime_model.py	794	# Check if restart is needed	COMMENT
LOW	…ox/livekit/plugins/ultravox/realtime/realtime_model.py	1158	# Check if we have a current generation before processing audio	COMMENT

Modern AI Meta-Vocabulary7 hits · 20 pts

Severity	File	Line	Snippet	Context
MEDIUM	examples/drive_thru/database.py	634	# explicitely saying there is no `size` for this item, otherwise the LLM seems to hallucinate quite often	COMMENT
MEDIUM	…mples/homepage/tests/evals/test_knowledge_grounding.py	200	# 3. Anti-hallucination: absent or contradicted facts are not fabricated.	COMMENT
MEDIUM	examples/voice_agents/README.md	39	### RAG & Knowledge Management	COMMENT
MEDIUM	examples/voice_agents/llamaindex-rag/README.md	1	# RAG Example using LlamaIndex	COMMENT
MEDIUM	…kit-plugins-anthropic/livekit/plugins/anthropic/llm.py	306	self._ignoring_cot = False # ignore chain of thought	CODE
MEDIUM	livekit-plugins/livekit-plugins-mistralai/README.md	72	# Using zero-shot voice cloning	COMMENT
MEDIUM	…s/livekit-plugins-soniox/livekit/plugins/soniox/tts.py	657	# Empty text would make the server hallucinate audio; handle the two cases locally.	COMMENT

AI Slop Vocabulary6 hits · 13 pts

Severity	File	Line	Snippet	Context
MEDIUM	examples/data_capture_sim/agent.py	21	# Simulation harness for the beta data-capture workflows. Every capture runs	COMMENT
LOW	examples/other/chat-stream-receiver.py	79	# in cli we don't actually overwrite the line, just add a flag	COMMENT
MEDIUM	livekit-agents/livekit/agents/voice/tool_executor.py	230	# the confirm flag is harness state, not an argument	COMMENT
LOW	…it/plugins/aws/experimental/realtime/realtime_model.py	637	# Static credentials - just use the max session duration	COMMENT
MEDIUM	…google/livekit/plugins/google/realtime/realtime_api.py	1581	# TODO(dz): this isn't a seamless reconnection just yet	COMMENT
LOW	…ox/livekit/plugins/ultravox/realtime/realtime_model.py	821	# If we're already closing due to send loop shutdown, just return	COMMENT

Dead Code4 hits · 6 pts

Severity	File	Line	Context
MEDIUM	tests/test_agent_session.py	1612	CODE
MEDIUM	tests/test_agent_session.py	1683	CODE
MEDIUM	…it/plugins/aws/experimental/realtime/realtime_model.py	2155	CODE
MEDIUM	…it/plugins/aws/experimental/realtime/realtime_model.py	2159	CODE

Slop Phrases3 hits · 4 pts

Severity	File	Line	Snippet	Context
MEDIUM	examples/healthcare/agent.py	93	- Assistant: I'm unable to help with that, would you like to speak to a human agent?	STRING
MEDIUM	examples/warm-transfer/warm_transfer.py	47	- Assistant: I'm unable to help with that, would you like to speak to a human agent?	STRING
LOW	…t-plugins-assemblyai/livekit/plugins/assemblyai/stt.py	687	# the recv task will then make sure to process the remaining audio and stop	COMMENT

Overly Generic Function Names1 hit · 0 pts

Severity	File	Line	Snippet	Context
LOW	livekit-agents/livekit/agents/utils/deprecation.py	32	... def my_function(old_param: NotGivenOr[int] = NOT_GIVEN, new_param: int = 0):	STRING

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings