jundot/omlx

29.8

Adjusted Score

29.8

Raw Score

100%

Time Factor

2026-08-02

Last Push

18.4K

Stars

Python

Language

391.7K

Lines of Code

751

Files

9.9K

Pattern Hits

2026-08-02

Scan Date

0.12

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 3HIGH 86MEDIUM 1217LOW 8622

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 9928 distinct pattern matches across 21 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

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

Hyper-Verbose Identifiers6406 hits · 5263 pts

Severity	File	Line	Snippet	Context
LOW	setup.py	19	def _custom_kernel_build_kwargs() -> dict:	CODE
LOW	packaging/build.py	450	def _read_pyproject_requirements() -> dict[str, list[str]]:	CODE
LOW	packaging/build.py	468	def _generate_venvstacks_toml() -> Path:	CODE
LOW	packaging/build.py	1036	def _compute_donor_fingerprint() -> str:	CODE
LOW	packaging/build.py	1057	def _write_export_fingerprint():	CODE
LOW⚡	tests/test_store_cache_gate.py	21	def test_note_submitted_increments(self):	CODE
LOW⚡	tests/test_store_cache_gate.py	27	def test_note_done_decrements(self):	CODE
LOW⚡	tests/test_store_cache_gate.py	34	def test_note_done_does_not_underflow(self):	CODE
LOW⚡	tests/test_store_cache_gate.py	40	def test_note_submitted_never_blocks_past_cap(self):	CODE
LOW	tests/test_store_cache_gate.py	76	def test_recovers_after_note_done(self):	CODE
LOW	tests/test_store_cache_gate.py	83	def test_shrinking_cap_below_in_flight_blocks_admission(self):	CODE
LOW	tests/test_store_cache_gate.py	96	def test_clamps_to_minimum_one(self):	CODE
LOW	tests/test_store_cache_gate.py	103	def test_set_cap_updates_value(self):	CODE
LOW	tests/test_store_cache_gate.py	128	def test_ok_clamps_to_max_num_seqs(self):	CODE
LOW	tests/test_store_cache_gate.py	148	def test_no_op_when_gate_missing(self):	CODE
LOW	tests/test_store_cache_gate.py	161	def test_counter_consistent_under_contention(self):	CODE
LOW⚡	tests/test_model_discovery.py	76	def test_dflash_draft_via_architecture(self):	CODE
LOW⚡	tests/test_model_discovery.py	81	def test_dflash_draft_via_config_block(self):	CODE
LOW⚡	tests/test_model_discovery.py	85	def test_assistant_via_model_type(self):	CODE
LOW⚡	tests/test_model_discovery.py	135	def test_detect_embedding_model_by_type(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	144	def test_detect_embedding_model_by_architecture(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	153	def test_detect_modernbert_embedding(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	162	def test_detect_reranker_model(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	171	def test_detect_xlm_roberta_reranker(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	180	def test_detect_jina_reranker_without_name_heuristic(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	314	def test_missing_config_defaults_to_llm(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	318	def test_invalid_json_defaults_to_llm(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	323	def test_empty_config_defaults_to_llm(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	328	def test_detect_vlm_by_model_type(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	338	def test_detect_diffusion_gemma_as_vlm(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	651	def test_detect_vlm_fastvlm_via_mm_vision_tower(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	661	def test_detect_text_only_quant_with_empty_mm_vision_tower_as_llm(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	671	def test_detect_text_only_quant_no_vision_evidence_as_llm(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	683	def test_detect_lfm_text_moe_family_as_llm_not_audio_sts(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	692	def test_detect_lfm_future_moe_variant_as_llm_not_audio_sts(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	701	def test_detect_lfm_audio_architecture_as_sts(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	710	def test_detect_lfm_audio_model_type_as_sts(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	719	def test_detect_unknown_lfm_prefix_without_causal_lm_as_sts(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	732	def test_estimate_from_safetensors(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	742	def test_estimate_from_single_safetensors(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	749	def test_estimate_from_bin_files(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	758	def test_skip_optimizer_files(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	969	def test_nonexistent_directory_raises_error(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	974	def test_file_instead_of_directory_raises_error(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	981	def test_unreadable_directory_is_skipped(self, tmp_path, monkeypatch):	CODE
LOW⚡	tests/test_model_discovery.py	1081	def test_adapter_dir_detected(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	1086	def test_normal_model_not_adapter(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	1092	def test_discover_skips_lora_adapter(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	1187	def test_top_level_takes_precedence_over_nested(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	1194	def test_text_config_fallback(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	1199	def test_language_config_fallback(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	1204	def test_tokenizer_max_length_fallback(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	1209	def test_tokenizer_sentinel_rejected(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	1218	def test_no_config_returns_none(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	1221	def test_invalid_types_rejected(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	1230	def test_malformed_config_is_silent(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	1267	def test_multiple_org_folders(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	1276	def test_empty_org_folder_skipped(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	1285	def test_org_folder_hidden_children_skipped(self, tmp_path):	CODE
LOW⚡	tests/test_model_discovery.py	1295	def test_org_folder_invalid_children_skipped(self, tmp_path):	CODE
6346 more matches not shown…

Decorative Section Separators1124 hits · 3862 pts

Severity	File	Line	Snippet	Context
MEDIUM	tools/repack_ternary_t5.py	80	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tools/repack_ternary_t5.py	82	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tools/repack_ternary_t5.py	148	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tools/repack_ternary_t5.py	150	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tools/repack_ternary_t5.py	175	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tools/repack_ternary_t5.py	177	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tools/repack_ternary_t5.py	364	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tools/repack_ternary_t5.py	366	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tools/repack_ternary_t5.py	426	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	tools/repack_ternary_t5.py	428	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_openai_adapter.py	32	# =========================================================================	COMMENT
MEDIUM⚡	tests/test_openai_adapter.py	34	# =========================================================================	COMMENT
MEDIUM⚡	tests/test_openai_adapter.py	67	# =========================================================================	COMMENT
MEDIUM⚡	tests/test_openai_adapter.py	69	# =========================================================================	COMMENT
MEDIUM⚡	tests/test_openai_adapter.py	128	# =========================================================================	COMMENT
MEDIUM⚡	tests/test_openai_adapter.py	130	# =========================================================================	COMMENT
MEDIUM⚡	tests/test_openai_adapter.py	166	# =========================================================================	COMMENT
MEDIUM⚡	tests/test_openai_adapter.py	168	# =========================================================================	COMMENT
MEDIUM⚡	tests/test_openai_adapter.py	222	# =========================================================================	COMMENT
MEDIUM⚡	tests/test_openai_adapter.py	224	# =========================================================================	COMMENT
MEDIUM⚡	tests/test_openai_adapter.py	234	# =========================================================================	COMMENT
MEDIUM⚡	tests/test_openai_adapter.py	236	# =========================================================================	COMMENT
MEDIUM⚡	tests/test_openai_adapter.py	502	# =========================================================================	COMMENT
MEDIUM⚡	tests/test_openai_adapter.py	504	# =========================================================================	COMMENT
MEDIUM⚡	tests/test_openai_adapter.py	605	# =========================================================================	COMMENT
MEDIUM⚡	tests/test_openai_adapter.py	607	# =========================================================================	COMMENT
MEDIUM⚡	tests/test_openai_adapter.py	699	# =========================================================================	COMMENT
MEDIUM⚡	tests/test_openai_adapter.py	701	# =========================================================================	COMMENT
MEDIUM	tests/test_openai_adapter.py	684	# =========================================================================	COMMENT
MEDIUM	tests/test_openai_adapter.py	686	# =========================================================================	COMMENT
MEDIUM	tests/test_paged_ssd_cache.py	1902	# =============================================================================	COMMENT
MEDIUM	tests/test_paged_ssd_cache.py	1904	# =============================================================================	COMMENT
MEDIUM	tests/e2e_vision_cache.py	58	# ── Step 1: Load model ──────────────────────────────────────	COMMENT
MEDIUM	tests/e2e_vision_cache.py	72	# ── Step 2: Prepare inputs ──────────────────────────────────	COMMENT
MEDIUM	tests/e2e_vision_cache.py	120	# ── Step 3: Test _compute_vision_features ────────────────────	COMMENT
MEDIUM	tests/e2e_vision_cache.py	152	# ── Step 4: Test cached_image_features support ───────────────	COMMENT
MEDIUM	tests/e2e_vision_cache.py	185	# ── Step 5: Test VisionFeatureSSDCache roundtrip ─────────────	COMMENT
MEDIUM	tests/e2e_vision_cache.py	220	# ── Step 6: Cache hit performance ────────────────────────────	COMMENT
MEDIUM⚡	tests/test_ms_downloader.py	116	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_ms_downloader.py	118	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_ms_downloader.py	424	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_ms_downloader.py	426	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_ms_downloader.py	653	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_ms_downloader.py	655	# =============================================================================	COMMENT
MEDIUM	tests/test_ms_downloader.py	27	# =============================================================================	COMMENT
MEDIUM	tests/test_ms_downloader.py	29	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_mcp_config.py	36	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_mcp_config.py	38	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_mcp_config.py	238	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_mcp_config.py	240	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_mcp_config.py	323	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_mcp_config.py	325	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_mcp_config.py	370	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_mcp_config.py	372	# =============================================================================	COMMENT
MEDIUM⚡	tests/test_prefix_cache.py	2153	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_prefix_cache.py	2155	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_prefix_cache.py	2179	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_prefix_cache.py	2181	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_prefix_cache.py	2314	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	tests/test_prefix_cache.py	2316	# ------------------------------------------------------------------	COMMENT
1064 more matches not shown…

Excessive Try-Catch Wrapping820 hits · 702 pts

Severity	File	Line	Snippet	Context
LOW	packaging/build.py	824	except Exception: # pragma: no cover — build runs may not have omlx on path yet	CODE
LOW	tools/repack_ternary_t5.py	191	except Exception as e:	CODE
LOW	tools/repack_ternary_t5.py	206	except Exception as e:	CODE
MEDIUM	tests/test_paged_ssd_cache.py	2741	def do_preload():	CODE
MEDIUM	tests/test_paged_ssd_cache.py	2747	def do_loads():	CODE
LOW	tests/test_paged_ssd_cache.py	2744	except Exception as e:	CODE
LOW	tests/test_paged_ssd_cache.py	2752	except Exception as e:	CODE
LOW	tests/e2e_vision_cache.py	89	except Exception:	CODE
LOW	tests/e2e_vision_cache.py	95	except Exception:	CODE
MEDIUM	tests/test_mlx_lm_mtp_patch.py	74	def _apply(self):	CODE
LOW	tests/test_mlx_lm_mtp_patch.py	1840	except Exception:	CODE
LOW	tests/test_audio_stt.py	1398	except Exception as e:	CODE
LOW	tests/test_glm_moe_dsa_patch.py	342	except Exception as exc: # pragma: no cover - depends on local native build	CODE
LOW	tests/test_glm_moe_dsa_patch.py	646	except Exception as exc: # pragma: no cover - depends on local native build	CODE
LOW	tests/test_glm_moe_dsa_patch.py	755	except Exception as exc: # pragma: no cover - depends on local native build	CODE
LOW	tests/test_glm_moe_dsa_patch.py	814	except Exception as exc: # pragma: no cover - depends on local native build	CODE
LOW⚡	tests/test_mtp_prompt_priming.py	207	except Exception:	CODE
LOW	tests/test_turboquant_batch_memory.py	33	except Exception:	CODE
MEDIUM	tests/test_turboquant_batch_memory.py	28	def _model_path():	CODE
LOW	tests/test_turboquant_ssd.py	27	except Exception:	CODE
MEDIUM	tests/test_turboquant_ssd.py	22	def _model_path():	CODE
LOW	tests/test_prefill_progress.py	110	except Exception as e:	CODE
MEDIUM	tests/test_prefill_progress.py	103	def updater(model_id, start):	CODE
MEDIUM	tests/test_torch_stub.py	423	def worker():	CODE
LOW	tests/test_torch_stub.py	430	except Exception as e:	CODE
LOW⚡	tests/test_grammar_live.py	151	except Exception:	CODE
LOW	tests/test_grammar_live.py	375	except Exception as e:	CODE
MEDIUM	tests/test_grammar_live.py	147	def _server_available():	CODE
LOW	tests/test_embedding.py	1307	except Exception as e:	CODE
LOW	tests/test_audio_tts.py	1424	except Exception as e:	CODE
LOW	tests/test_cache_observability.py	175	except Exception as e:	CODE
LOW	tests/test_cache_observability.py	182	except Exception as e:	CODE
MEDIUM	tests/test_model_settings.py	652	def worker(model_id):	CODE
LOW	tests/test_model_settings.py	657	except Exception as e:	CODE
LOW	tests/test_audio_sts.py	467	except Exception as e:	CODE
LOW	tests/test_audio_sts.py	493	except Exception as e:	CODE
LOW	tests/test_audio_sts.py	521	except Exception as e:	CODE
LOW	tests/test_audio_sts.py	549	except Exception as e:	CODE
MEDIUM	tests/test_hot_cache.py	533	def worker(thread_id):	CODE
LOW	tests/test_hot_cache.py	556	except Exception as e:	CODE
MEDIUM	tests/test_boundary_snapshot_store.py	772	def all_cleaner():	CODE
LOW⚡	tests/test_boundary_snapshot_store.py	759	except Exception as e:	CODE
LOW⚡	tests/test_boundary_snapshot_store.py	769	except Exception as e:	CODE
LOW⚡	tests/test_boundary_snapshot_store.py	777	except Exception as e:	CODE
LOW	tests/test_boundary_snapshot_store.py	711	except Exception as e:	CODE
LOW	tests/test_qwen35_moe_weighted_sum.py	46	except Exception:	CODE
LOW	tests/test_harmony_parser.py	29	except Exception:	CODE
MEDIUM	tests/integration/test_vlm_mrope_integration.py	89	def _apply_chat_template_as_ids(tokenizer, messages) -> List[int]:	CODE
LOW	tests/integration/test_vlm_mrope_integration.py	100	except Exception:	CODE
LOW	tests/integration/test_vlm_mrope_integration.py	172	except Exception:	CODE
LOW	tests/integration/test_vlm_mrope_integration.py	177	except Exception:	CODE
LOW	tests/integration/test_vlm_mrope_integration.py	742	except Exception:	CODE
LOW	tests/integration/test_vlm_mrope_integration.py	850	except Exception as e:	CODE
LOW	tests/integration/test_full_integration.py	106	except Exception:	CODE
LOW	tests/integration/test_full_integration.py	481	except Exception:	CODE
LOW	tests/integration/test_full_integration.py	486	except Exception:	CODE
LOW	tests/integration/test_real_model_inference.py	525	except Exception as e:	CODE
LOW	tests/integration/test_boundary_cache_consistency.py	91	except Exception:	CODE
LOW	tests/integration/test_boundary_cache_consistency.py	105	except Exception:	CODE
LOW	omlx/model_settings.py	429	except Exception as e:	CODE
760 more matches not shown…

Unused Imports558 hits · 456 pts

Severity	File	Line	Context
LOW	tools/repack_ternary_t5.py	51	CODE
LOW	tests/test_qwen35_q4_mlp.py	1	CODE
LOW	tests/test_openai_adapter.py	20	CODE
LOW	tests/test_paged_ssd_cache.py	42	CODE
LOW	tests/test_hybrid_cache.py	9	CODE
LOW	tests/test_hybrid_cache.py	10	CODE
LOW	tests/test_hybrid_cache.py	11	CODE
LOW	tests/test_hybrid_cache.py	11	CODE
LOW	tests/test_hybrid_cache.py	11	CODE
LOW	tests/test_hybrid_cache.py	11	CODE
LOW	tests/test_hybrid_cache.py	12	CODE
LOW	tests/test_hybrid_cache.py	12	CODE
LOW	tests/test_hybrid_cache.py	24	CODE
LOW	tests/test_hybrid_cache.py	29	CODE
LOW	tests/test_hybrid_cache.py	34	CODE
LOW	tests/test_hybrid_cache.py	1070	CODE
LOW	tests/test_m5_gather_qmm.py	4	CODE
LOW	tests/test_utils_hardware.py	8	CODE
LOW	tests/test_cache_ntuple_state.py	18	CODE
LOW	tests/test_cache_ntuple_state.py	286	CODE
LOW	tests/e2e_vision_cache.py	21	CODE
LOW	tests/test_stream_usage.py	6	CODE
LOW	tests/test_v1_models_visibility.py	4	CODE
LOW	tests/test_ms_downloader.py	6	CODE
LOW	tests/test_mcp_config.py	9	CODE
LOW	tests/test_prefix_cache_cachelist_mixed.py	28	CODE
LOW	tests/test_shared_models.py	5	CODE
LOW	tests/test_prefix_cache_rotating_tip_strip.py	34	CODE
LOW	tests/test_mbpp_extract_code.py	9	CODE
LOW	tests/test_admin_restart.py	10	CODE
LOW	tests/test_admin_reload.py	8	CODE
LOW	tests/test_utils_formatting.py	4	CODE
LOW	tests/test_singleton_cache_passthrough.py	10	CODE
LOW	tests/test_gemma4_rendering.py	7	CODE
LOW	tests/test_nested_nstate_serialization.py	24	CODE
LOW	tests/test_admin_hot_cache_clear.py	16	CODE
LOW	tests/test_dflash_lifecycle.py	4	CODE
LOW	tests/test_model_registry.py	10	CODE
LOW	tests/test_admin_api_key.py	15	CODE
LOW	tests/test_mlx_lm_mtp_patch.py	10	CODE
LOW	tests/test_glm_moe_dsa_patch.py	4	CODE
LOW	tests/test_optimizations.py	8	CODE
LOW	tests/test_prefix_cache_v4_block_storage.py	28	CODE
LOW	tests/test_request.py	6	CODE
LOW	tests/test_scheduler_logits_processors.py	39	CODE
LOW	tests/test_scheduler_logits_processors.py	193	CODE
LOW	tests/test_scheduler_logits_processors.py	210	CODE
LOW	tests/test_scheduler_logits_processors.py	228	CODE
LOW	tests/test_scheduler_logits_processors.py	255	CODE
LOW	tests/test_scheduler_logits_processors.py	389	CODE
LOW	tests/test_anthropic_models.py	9	CODE
LOW	tests/test_mlx_vlm_minimax_m3_compat.py	4	CODE
LOW	tests/test_mlx_vlm_minimax_m3_compat.py	19	CODE
LOW	tests/test_mlx_vlm_minimax_m3_compat.py	20	CODE
LOW	tests/test_mcp_tools.py	8	CODE
LOW	tests/test_bonsai_qmv.py	15	CODE
LOW	tests/test_bonsai_qmv.py	18	CODE
LOW	tests/test_bonsai_qmv.py	18	CODE
LOW	tests/test_gemma4_verify_attention.py	9	CODE
LOW	tests/test_proc_memory.py	4	CODE
498 more matches not shown…

Deep Nesting362 hits · 242 pts

Severity	File	Line	Context
LOW	tools/repack_ternary_t5.py	307	CODE
LOW	tools/repack_ternary_t5.py	368	CODE
LOW	tests/test_qwen35_q4_mlp.py	282	CODE
LOW	tests/test_qwen35_q4_mlp.py	372	CODE
LOW	tests/test_engine_core.py	213	CODE
LOW	tests/test_engine_core.py	253	CODE
LOW	tests/test_engine_core.py	957	CODE
LOW	tests/test_engine_core.py	1168	CODE
LOW	tests/test_dflash_multimodal_fallback.py	339	CODE
LOW	tests/test_dflash_multimodal_fallback.py	369	CODE
LOW	tests/test_scheduler_chunked_prefill.py	749	CODE
LOW	tests/test_vlm_engine.py	1374	CODE
LOW	tests/test_glm_mtp_patch.py	67	CODE
LOW	tests/test_oq.py	2201	CODE
LOW	tests/test_thinking_budget.py	458	CODE
LOW	tests/test_boundary_snapshot_store.py	493	CODE
LOW	tests/test_reranker_causal_lm.py	578	CODE
LOW	tests/test_reranker_causal_lm.py	589	CODE
LOW	tests/integration/test_vlm_mrope_integration.py	153	CODE
LOW	tests/integration/test_vlm_mrope_integration.py	297	CODE
LOW	tests/integration/test_e2e_streaming.py	205	CODE
LOW	tests/integration/test_e2e_streaming.py	1120	CODE
LOW	tests/integration/test_full_integration.py	308	CODE
LOW	tests/integration/test_full_integration.py	453	CODE
LOW	tests/integration/test_real_model_inference.py	63	CODE
LOW	omlx/model_settings.py	513	CODE
LOW	omlx/model_settings.py	605	CODE
LOW	omlx/model_settings.py	814	CODE
LOW	omlx/model_settings.py	894	CODE
LOW	omlx/server.py	357	CODE
LOW	omlx/server.py	871	CODE
LOW	omlx/server.py	1233	CODE
LOW	omlx/server.py	1961	CODE
LOW	omlx/server.py	2083	CODE
LOW	omlx/server.py	2530	CODE
LOW	omlx/server.py	3155	CODE
LOW	omlx/server.py	3785	CODE
LOW	omlx/server.py	3961	CODE
LOW	omlx/server.py	4283	CODE
LOW	omlx/server.py	4342	CODE
LOW	omlx/server.py	4768	CODE
LOW	omlx/server.py	5156	CODE
LOW	omlx/server.py	5667	CODE
LOW	omlx/server.py	6086	CODE
LOW	omlx/server.py	3549	CODE
LOW	omlx/server.py	5450	CODE
LOW	omlx/server.py	5937	CODE
LOW	omlx/server_metrics.py	255	CODE
LOW	omlx/process_memory_enforcer.py	1287	CODE
LOW	omlx/process_memory_enforcer.py	1400	CODE
LOW	omlx/engine_core.py	371	CODE
LOW	omlx/engine_core.py	689	CODE
LOW	omlx/engine_core.py	859	CODE
LOW	omlx/cli.py	71	CODE
LOW	omlx/cli.py	351	CODE
LOW	omlx/cli.py	632	CODE
LOW	omlx/cli.py	789	CODE
LOW	omlx/prefill_progress.py	32	CODE
LOW	omlx/prefill_progress.py	86	CODE
LOW	omlx/model_discovery.py	763	CODE
302 more matches not shown…

Modern Structural Boilerplate236 hits · 238 pts

Severity	File	Line	Snippet	Context
LOW	tests/mocks.py	110	def set_responses(self, responses: List[List[MockResponse]]) -> None:	CODE
LOW	tests/mocks.py	193	def set_paged_ssd_cache_manager(self, manager: Any) -> None:	CODE
LOW⚡	tests/mocks.py	278	def set_cold_restore_callback(self, callback: Callable) -> None:	CODE
LOW⚡	tests/mocks.py	286	def set_paged_ssd_cache_manager(self, manager: Any) -> None:	CODE
LOW	omlx/model_settings.py	26	logger = logging.getLogger(__name__)	CODE
LOW	omlx/model_settings.py	513	def set_settings(self, model_id: str, settings: ModelSettings) -> None:	CODE
LOW⚡	omlx/server.py	198	logger = logging.getLogger(__name__)	CODE
LOW	omlx/logging_config.py	83	def set_request_id(request_id: Optional[str]) -> None:	CODE
LOW	omlx/prefill_transient_tracker.py	17	logger = logging.getLogger(__name__)	CODE
LOW⚡	omlx/turboquant_kv.py	45	logger = logging.getLogger(__name__)	CODE
LOW⚡	omlx/turboquant_kv.py	47	__all__ = [	CODE
LOW	omlx/request.py	244	def set_finished(self, status: RequestStatus, reason: Optional[str] = None) -> None:	CODE
LOW	omlx/__init__.py	50	__all__ = [	CODE
LOW	omlx/server_metrics.py	17	logger = logging.getLogger(__name__)	CODE
LOW	omlx/process_memory_enforcer.py	51	logger = logging.getLogger(__name__)	CODE
LOW	omlx/optimizations.py	34	logger = logging.getLogger(__name__)	CODE
LOW	omlx/optimizations.py	36	__all__ = [	CODE
LOW	omlx/engine_core.py	54	logger = logging.getLogger(__name__)	CODE
LOW	omlx/model_discovery.py	26	logger = logging.getLogger(__name__)	CODE
LOW	omlx/settings.py	37	logger = logging.getLogger(__name__)	CODE
LOW	omlx/oq.py	40	logger = logging.getLogger(__name__)	CODE
LOW⚡	omlx/scheduler.py	10863	def _set_model_info_for_monitor(self) -> None:	CODE
LOW	omlx/scheduler.py	282	def set_cap(self, cap: int) -> None:	CODE
LOW	omlx/scheduler.py	351	logger = logging.getLogger(__name__)	CODE
LOW	omlx/_torch_stub.py	31	logger = logging.getLogger(__name__)	CODE
LOW	omlx/engine_pool.py	53	logger = logging.getLogger(__name__)	CODE
LOW	omlx/model_registry.py	22	logger = logging.getLogger(__name__)	CODE
LOW	omlx/memory_monitor.py	29	logger = logging.getLogger(__name__)	CODE
LOW	omlx/memory_monitor.py	259	def set_baseline_memory(self) -> None:	CODE
LOW	omlx/memory_monitor.py	283	def set_request_stats(self, running: int, waiting: int) -> None:	CODE
LOW	omlx/memory_monitor.py	475	def set_fixed_state_bytes(self, n: int) -> None:	CODE
LOW	omlx/memory_monitor.py	972	def set_model_info_from_model(monitor: "MemoryMonitor", model: Any) -> None:	CODE
LOW	omlx/custom_kernels/nax.py	12	__all__ = ["is_nax_available"]	CODE
LOW	omlx/custom_kernels/minimax_m3/__init__.py	5	__all__ = ["fast"]	CODE
LOW	omlx/custom_kernels/minimax_m3/fast.py	11	logger = logging.getLogger(__name__)	CODE
LOW	omlx/custom_kernels/bonsai/__init__.py	20	__all__ = ["fast"]	CODE
LOW	omlx/custom_kernels/bonsai/fast.py	39	logger = logging.getLogger(__name__)	CODE
LOW	omlx/custom_kernels/glm_moe_dsa/__init__.py	5	__all__ = ["fast"]	CODE
LOW	omlx/custom_kernels/glm_moe_dsa/fast.py	11	logger = logging.getLogger(__name__)	CODE
LOW	omlx/custom_kernels/qwen35_prefill/__init__.py	6	__all__ = ["fast", "gated_delta_blocked_seq", "gated_delta_chunked_metal"]	CODE
LOW	omlx/custom_kernels/qwen35_prefill/fast.py	14	logger = logging.getLogger(__name__)	CODE
LOW	omlx/cache/recovery.py	19	logger = logging.getLogger(__name__)	CODE
LOW	omlx/cache/type_handlers.py	17	logger = logging.getLogger(__name__)	CODE
LOW	omlx/cache/__init__.py	83	__all__ = [	CODE
LOW	omlx/cache/type_registry.py	25	logger = logging.getLogger(__name__)	CODE
LOW⚡	omlx/cache/boundary_snapshot_store.py	40	logger = logging.getLogger(__name__)	CODE
LOW	omlx/cache/paged_ssd_cache.py	42	logger = logging.getLogger(__name__)	CODE
LOW	omlx/cache/paged_ssd_cache.py	1089	def update_file_size(self, block_hash: bytes, actual_size: int) -> None:	CODE
LOW	omlx/cache/paged_cache.py	38	logger = logging.getLogger(__name__)	CODE
LOW	omlx/cache/paged_cache.py	579	def set_paged_ssd_cache_manager(self, paged_ssd_cache_manager: Any) -> None:	CODE
LOW	omlx/cache/vision_feature_cache.py	35	logger = logging.getLogger(__name__)	CODE
LOW	omlx/cache/prefix_cache.py	37	logger = logging.getLogger(__name__)	CODE
LOW	omlx/cache/hybrid_cache.py	16	logger = logging.getLogger(__name__)	CODE
LOW	omlx/patches/mlx_audio_compat.py	8	logger = logging.getLogger(__name__)	CODE
LOW⚡	omlx/patches/specprefill.py	33	logger = logging.getLogger(__name__)	CODE
LOW	omlx/patches/gemma4_verify_attention.py	54	logger = logging.getLogger(__name__)	CODE
LOW	omlx/patches/bonsai_t5_load.py	49	logger = logging.getLogger(__name__)	CODE
LOW	omlx/patches/mlx_audio_sampling.py	37	logger = logging.getLogger(__name__)	CODE
LOW	omlx/patches/qwen35_q4_mlp.py	22	logger = logging.getLogger(__name__)	CODE
LOW	omlx/patches/qwen35_verify_qmm.py	51	logger = logging.getLogger(__name__)	CODE
176 more matches not shown…

Cross-Language Confusion31 hits · 169 pts

Severity	File	Line	Snippet	Context
HIGH⚡	tests/test_tool_calling.py	1602	"\"Qwen3.6-35B-A3B-ConfigI-MLX\" --timeout 180 && echo "	CODE
HIGH⚡	tests/test_tool_calling.py	1605	"--timeout 300 && echo \"v2 dynamic completed\"', timeout=400)]"	CODE
HIGH	tests/test_tool_calling.py	1433	"\t\tif len(ce.Args) > 1 && isSubcommand(ce.Args[1]) {"	CODE
HIGH	tests/test_tool_calling.py	1986	result = _gemma4_args_to_json_robust("{data: null}")	CODE
HIGH	tests/test_tool_calling.py	2474	'call:f(a=1, b=<\|"\|>two<\|"\|>, c=true, d=null, e=3.5)'	CODE
HIGH	tests/test_tool_calling.py	364	response_format={"type": "json_schema", "json_schema": null}; the	STRING
HIGH⚡	tests/test_chat_ui_overhaul.py	33	"async streamResponse(streamContext = null, depth = 0)",	CODE
HIGH⚡	tests/test_chat_ui_overhaul.py	39	assert "context._modelOverride \|\| context.model" in stream	CODE
HIGH⚡	tests/test_chat_ui_overhaul.py	47	"async streamResponse(streamContext = null, depth = 0)",	CODE
HIGH	tests/test_chat_ui_overhaul.py	58	assert "_modelOverride: opts.model \|\| null" in regenerate	CODE
HIGH⚡	tests/test_chat_ui_overhaul.py	105	assert "options.touchUpdatedAt === false && existingChat?.updatedAt" in save	CODE
HIGH	tests/test_chat_ui_overhaul.py	143	"async streamResponse(streamContext = null, depth = 0)",	CODE
HIGH	tests/test_admin_profiles_api.py	875	assert "p.display_name \|\| p.name" in html	CODE
HIGH	tests/test_admin_profiles_api.py	876	assert "p.expose_as_model ? (p.api_name \|\| p.name)" not in html	CODE
HIGH	tests/test_admin_profiles_api.py	896	assert "profile.api_name \|\| profile.name" in settings_html	CODE
HIGH	tests/test_admin_profiles_api.py	898	"profile.api_name \|\| profile.name"	CODE
HIGH⚡	omlx/server.py	1878	'"finish_reason":null}]}\n\n'	CODE
HIGH⚡	omlx/server.py	1883	'"choices":[{"index":0,"text":"","logprobs":null,"finish_reason":null}]}\n\n'	CODE
HIGH⚡	omlx/server.py	1892	'"choices":[{"index":0,"text":"","logprobs":null,"finish_reason":null}]}\n\n'	CODE
HIGH	omlx/server.py	1945	'"finish_reason":null}]}\n\n'	CODE
HIGH	omlx/custom_kernels/qwen35_prefill/gdn.py	123	if (j < i && i < tt)	CODE
HIGH	omlx/custom_kernels/qwen35_prefill/gdn.py	181	if (j <= i && i < tt)	CODE
HIGH	omlx/patches/qwen35_verify_qmm.py	339	if (part == 0 && lane < {n_acc}) {{	CODE
HIGH	omlx/patches/dflash_draft_config.py	33	Hoisting is fill-only per key: a root-level key that is set (non-null)	STRING
HIGH⚡	omlx/patches/dflash_draft_config.py	64	that is set (non-null) is never overwritten; an explicit ``null``	STRING
HIGH	omlx/patches/glm_moe_dsa/sparse_mla.py	30	if (CAUSAL_PREFIX_INDICES && q_pos < PREFIX_ROWS) {	CODE
HIGH	omlx/patches/glm_moe_dsa/sparse_mla.py	40	if (q_block >= Q_BLOCKS \|\| k_block >= K_BLOCKS) {	CODE
HIGH	omlx/patches/glm_moe_dsa/sparse_mla.py	67	if (CAUSAL && k_pos > q_abs) {	CODE
HIGH	omlx/patches/glm_moe_dsa/sparse_mla.py	73	if (q_block >= Q_BLOCKS \|\| k_block >= K_BLOCKS) {	CODE
HIGH	omlx/patches/glm_moe_dsa/sparse_mla.py	243	if (CAUSAL && k_pos > K - L + q_pos) {	CODE
HIGH	omlx/api/grammar.py	14	computation (parallel model forward \|\| bitmask fill).	STRING

Docstring Block Structure30 hits · 150 pts

Severity	File	Line	Snippet	Context
HIGH	omlx/server.py	877	Get engine for the specified model and type. This is the unified engine getter that handles LLM, embedding, an	STRING
HIGH	omlx/server.py	1123	Get LLM engine for the specified model (or default). This is a convenience wrapper around get_engine() for LLM	STRING
HIGH	omlx/server.py	1161	Get embedding engine for the specified model. This is a convenience wrapper around get_engine() for embedding	STRING
HIGH	omlx/server.py	1179	Get reranker engine for the specified model. This is a convenience wrapper around get_engine() for reranker mo	STRING
HIGH	omlx/scheduler.py	2994	Run prefill externally (outside BatchGenerator) for a single request. Processes tokens[0:N-1] through the model	STRING
HIGH	omlx/engine_pool.py	789	Get or load engine for the specified model. This method implements pre-load memory checking: 1	STRING
HIGH	omlx/model_registry.py	62	Attempt to acquire ownership of a model. Args: model: The MLX model engine: Th	STRING
HIGH	omlx/cache/paged_cache.py	264	Pop n blocks from the front. Args: n: Number of blocks to allocate Returns:	STRING
HIGH	omlx/cache/paged_cache.py	670	Allocate multiple blocks at once (vLLM style). Args: num_blocks: Number of blocks to alloc	STRING
HIGH	omlx/admin/auth.py	258	FastAPI dependency to require admin authentication. This dependency can be used in route definitions to protect	STRING
HIGH	omlx/admin/ms_downloader.py	696	Start downloading a model from ModelScope. Args: model_id: ModelScope model ID (e.g., "qwen/Qwen2.5	STRING
HIGH	omlx/admin/ms_downloader.py	805	Retry a failed or cancelled download, resuming from existing files. Args: task_id: The task ID of t	STRING
HIGH	omlx/admin/hf_downloader.py	623	Start downloading a model from HuggingFace. Args: repo_id: HuggingFace repository ID (e.g., "mlx-co	STRING
HIGH	omlx/admin/hf_downloader.py	730	Retry a failed or cancelled download, resuming from existing files. Finalized shards are preserved on disk so s	STRING
HIGH	omlx/admin/hf_uploader.py	184	Validate a HuggingFace token and return user info. Args: token: HuggingFace write-access token.	STRING
HIGH	omlx/admin/hf_uploader.py	320	Queue a model upload to HuggingFace Hub. Args: model_path: Local path to the oQ model directory.	STRING
HIGH	omlx/admin/oq_manager.py	268	Start a quantization job. Args: model_path: Path to source model directory. oq_level: o	STRING
HIGH	omlx/admin/routes.py	1420	Authenticate with API key and create session. Requires an API key to be configured on the server. If no API ke	STRING
HIGH	omlx/admin/routes.py	1469	Set up the initial API key when none is configured. This endpoint is only available when no API key is current	STRING
HIGH	omlx/admin/routes.py	1593	Create a new sub API key. Sub keys can only be used for API authentication, not admin login. Args: req	STRING
HIGH	omlx/admin/routes.py	1649	Delete a sub API key. Args: request: DeleteSubKeyRequest with the key to delete. Returns: JSON	STRING
HIGH	omlx/admin/routes.py	2075	Update settings for a specific model. Updates are persisted to the settings file and applied immediately t	STRING
HIGH	omlx/admin/routes.py	2937	Read model config files and return recommended defaults. Reads generation_config.json for sampling parameters	STRING
HIGH	omlx/admin/routes.py	3298	Update global server settings. Updates are persisted to the global settings file. Some settings (log_level	STRING
HIGH	omlx/admin/routes.py	4013	Get server logs. Returns the last N lines of the specified log file (or current log). Supports viewing his	STRING
HIGH	omlx/utils/image.py	87	Load an image from a base64 data URI. Supports: - Data URIs: "data:image/jpeg;base64,..." format Args	STRING
HIGH	omlx/mcp/config.py	30	Load MCP configuration from file. Search order: 1. Explicit path argument 2. OMLX_MCP_CONFIG environme	STRING
HIGH	omlx/mcp/config.py	101	Validate and parse configuration dictionary. Args: data: Raw configuration dictionary Returns:	STRING
HIGH	omlx/mcp/tools.py	50	Parse OpenAI tool call back to MCP format. Args: tool_call: OpenAI tool call from model response	STRING
HIGH	omlx/engine/sts.py	337	Process an audio file through the STS model. For speech enhancement models (DeepFilterNet, MossFormer2	STRING

Over-Commented Block179 hits · 142 pts

Severity	File	Line	Snippet	Context
LOW	pyproject.toml	41	dependencies = [	COMMENT
LOW	pyproject.toml	61	# mistral-common models) first shipped in 5.12.1 — on older 5.x the kwarg	COMMENT
LOW	pyproject.toml	101	"setproctitle>=1.3.3",	COMMENT
LOW	pyproject.toml	141	"modelscope>=1.10.0",	COMMENT
LOW	packaging/build.py	701	# produced fresh each build from pyproject.toml + venvstacks.toml.	COMMENT
LOW	packaging/venvstacks.toml	1	# oMLX venvstacks layer template	COMMENT
LOW	tests/test_paged_ssd_cache.py	3041		COMMENT
LOW	tests/test_hf_downloader.py	2801	assert "dry_run" not in call_kwargs	COMMENT
LOW	omlx/model_settings.py	241	# Maximum chained MTP draft tokens per verify cycle (speculative depth).	COMMENT
LOW	omlx/server.py	221		COMMENT
LOW	omlx/server.py	6881		COMMENT
LOW	omlx/server.py	6921	if __name__ == "__main__":	COMMENT
LOW	omlx/prefill_transient_tracker.py	21	"""EWMA estimator of MLX prefill chunk transient bytes per token.	COMMENT
LOW	omlx/turboquant_kv.py	241	self._batch_size = len(left_padding)	COMMENT
LOW	omlx/turboquant_kv.py	321	# compared each request's sequence length (offset) against the column	COMMENT
LOW	omlx/request.py	281	finish_reason: Optional[str] = None	COMMENT
LOW	omlx/process_memory_enforcer.py	381	self._wake_event: asyncio.Event \| None = None	COMMENT
LOW	omlx/process_memory_enforcer.py	1541	# signaled, eviction can't help further without aborts.	COMMENT
LOW	omlx/engine_core.py	161	# event loop, ping-ponging the GIL with the asyncio loop + uvicorn on the	COMMENT
LOW	omlx/engine_core.py	601		COMMENT
LOW	omlx/model_discovery.py	81	# exposes the text backbone. Route them directly to BatchedEngine instead of	COMMENT
LOW	omlx/model_discovery.py	241	}	COMMENT
LOW	omlx/oq.py	3581	# in the quantization pipeline.	COMMENT
LOW	omlx/oq.py	5601	named_shapes = _collect_named_weight_shapes_from_weights(all_weights)	COMMENT
LOW	omlx/oq.py	7501		COMMENT
LOW	omlx/scheduler.py	461		COMMENT
LOW	omlx/scheduler.py	641	if (	COMMENT
LOW	omlx/scheduler.py	701	# self.logits_processors = [self.logits_processors[idx] for idx in keep]	COMMENT
LOW	omlx/scheduler.py	1621	# shrink has already dropped hot-cache refs and _sync_and_clear_cache	COMMENT
LOW	omlx/scheduler.py	1641	# makes the enforcer abort active requests. Propagated so the	COMMENT
LOW	omlx/scheduler.py	1661	self._memory_hot_cache_reserved_bytes: int = 0	COMMENT
LOW	omlx/scheduler.py	1761	self._vlm_mtp_draft_block_size: int \| None = None	COMMENT
LOW	omlx/scheduler.py	1801	self._boundary_cache_snapshots: dict[str, dict[int, Any]] = {}	COMMENT
LOW	omlx/scheduler.py	1961	self.total_completion_tokens = 0	COMMENT
LOW	omlx/scheduler.py	3361		COMMENT
LOW	omlx/scheduler.py	3821	# pre-chunk guard and the post-chunk memory check abort	COMMENT
LOW	omlx/scheduler.py	6561	layer_idx=layer_idx,	COMMENT
LOW	omlx/scheduler.py	7241		COMMENT
LOW	omlx/scheduler.py	8061	for request in list(self.waiting):	COMMENT
LOW	omlx/scheduler.py	8081	# pops them from ``self.requests`` after the store future completes.	COMMENT
LOW	omlx/scheduler.py	8681	self._ensure_batch_generator(request.sampling_params)	COMMENT
LOW	omlx/scheduler.py	8821	# SpecPrefill: replace tokens with selected subset and pre-fill	COMMENT
LOW	omlx/scheduler.py	9201	# BatchGenerator only handles decode from here.	COMMENT
LOW	omlx/scheduler.py	9561	tracker.remove(rid)	COMMENT
LOW	omlx/scheduler.py	9721	with self._phase_timer("store_cache_main_dispatch"):	COMMENT
LOW	omlx/scheduler.py	9861	del self.running[request_id]	COMMENT
LOW	omlx/scheduler.py	9901		COMMENT
LOW	omlx/scheduler.py	10461	)	COMMENT
LOW	omlx/scheduler.py	10881	if isinstance(obj, dict):	COMMENT
LOW	omlx/scheduler.py	11221	)	COMMENT
LOW	omlx/_torch_stub.py	41	# path), but the symbol is re-exported from ``xgrammar.__init__``.	COMMENT
LOW	omlx/_torch_stub.py	341		COMMENT
LOW	omlx/engine_pool.py	881	# both models resident through the load (swapping for minutes)	COMMENT
LOW	omlx/engine_pool.py	961	if evicted_any:	COMMENT
LOW	omlx/engine_pool.py	1441	# Reset it on teardown so has_active_requests() and the status API stay consistent.	COMMENT
LOW	omlx/engine_pool.py	1461	# the generators are still alive with a local 'engine' variable	COMMENT
LOW	omlx/engine_pool.py	1681	# Wire the correct model_id / model_path into the shared scheduler	COMMENT
LOW	omlx/memory_monitor.py	41	# generation/inference path. Full prefill and short vector kernels support	COMMENT
LOW	omlx/custom_kernels/minimax_m3/csrc/minimax_msa.cpp	1	#include "minimax_msa.h"	COMMENT
LOW	omlx/custom_kernels/bonsai/csrc/bonsai_kernels.h	1	// Copyright © 2026 oMLX contributors	COMMENT
119 more matches not shown…

Cross-File Repetition25 hits · 125 pts

Severity	File	Snippet	Context
HIGH	tests/test_audio_stt.py	register audio routes if not already present (e.g., mlx-audio not installed).	STRING
HIGH	tests/test_audio_tts.py	register audio routes if not already present (e.g., mlx-audio not installed).	STRING
HIGH	tests/test_audio_sts.py	register audio routes if not already present (e.g., mlx-audio not installed).	STRING
HIGH	tests/test_audio_stt.py	testclient using the full omlx server app with mocked sts pool.	STRING
HIGH	tests/test_audio_tts.py	testclient using the full omlx server app with mocked sts pool.	STRING
HIGH	tests/test_audio_sts.py	testclient using the full omlx server app with mocked sts pool.	STRING
HIGH	tests/test_audio_stt.py	enginepool.get_engine() is called with the model id.	STRING
HIGH	tests/test_audio_sts.py	enginepool.get_engine() is called with the model id.	STRING
HIGH	tests/test_audio_tts.py	enginepool.get_engine() is called with the model id.	STRING
HIGH	omlx/custom_kernels/minimax_m3/fast.py	keep the diagnostic message without retaining import caller frames.	STRING
HIGH	omlx/custom_kernels/glm_moe_dsa/fast.py	keep the diagnostic message without retaining import caller frames.	STRING
HIGH	omlx/custom_kernels/qwen35_prefill/fast.py	keep the diagnostic message without retaining import caller frames.	STRING
HIGH	omlx/patches/glm_moe_dsa/kernels.py	keep the diagnostic message without retaining import caller frames.	STRING
HIGH	omlx/custom_kernels/minimax_m3/fast.py	disable the native symbols when the extension rejects mlx arrays. an extension built with a nanobind whose abi tag diffe	STRING
HIGH	omlx/custom_kernels/glm_moe_dsa/fast.py	disable the native symbols when the extension rejects mlx arrays. an extension built with a nanobind whose abi tag diffe	STRING
HIGH	omlx/custom_kernels/qwen35_prefill/fast.py	disable the native symbols when the extension rejects mlx arrays. an extension built with a nanobind whose abi tag diffe	STRING
HIGH	omlx/admin/ms_downloader.py	remove a completed, failed, or cancelled task from the list. args: task_id: the task id to remove. returns: true if the	STRING
HIGH	omlx/admin/hf_downloader.py	remove a completed, failed, or cancelled task from the list. args: task_id: the task id to remove. returns: true if the	STRING
HIGH	omlx/admin/hf_uploader.py	remove a completed, failed, or cancelled task from the list. args: task_id: the task id to remove. returns: true if the	STRING
HIGH	omlx/admin/ms_downloader.py	return all tasks as serializable dicts, ordered by creation time.	STRING
HIGH	omlx/admin/hf_downloader.py	return all tasks as serializable dicts, ordered by creation time.	STRING
HIGH	omlx/admin/hf_uploader.py	return all tasks as serializable dicts, ordered by creation time.	STRING
HIGH	omlx/eval/mbpp.py	override run: generation is batched, code execution is sequential.	STRING
HIGH	omlx/eval/livecodebench.py	override run: generation is batched, code execution is sequential.	STRING
HIGH	omlx/eval/humaneval.py	override run: generation is batched, code execution is sequential.	STRING

Self-Referential Comments28 hits · 81 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tests/test_model_discovery.py	1436	# Create a normal LLM model	COMMENT
MEDIUM⚡	tests/test_model_discovery.py	1444	# Create a whisper ASR model	COMMENT
MEDIUM	tests/test_model_discovery.py	957	# Create a file at top level	COMMENT
MEDIUM	tests/test_model_discovery.py	1328	# Create a small safetensors file	COMMENT
MEDIUM	tests/test_model_discovery.py	1457	# Create a TTS model	COMMENT
MEDIUM	tests/test_paged_ssd_cache.py	2824	# Create a BlockTable	COMMENT
MEDIUM	tests/test_deepseek_v4_patch.py	885	# Create a fake model dir with a non-deepseek config.	COMMENT
MEDIUM	tests/test_engine_core.py	747	# Create a task that calls generate - it will block on event.wait()	COMMENT
MEDIUM	tests/test_mcp_client.py	691	# Create a proper mock tool object with correct attributes	COMMENT
MEDIUM	tests/test_hf_downloader.py	179	# Create a fake model directory to simulate download	COMMENT
MEDIUM	tests/test_hf_downloader.py	959	# Create a mock global settings	COMMENT
MEDIUM	tests/test_hf_downloader.py	2072	# Create a fake README file with YAML front matter	COMMENT
MEDIUM	tests/test_hf_downloader.py	2552	# Create a file so current_size > 0 (needed to trigger stall detection)	COMMENT
MEDIUM	tests/test_hf_downloader.py	2723	# Create a file (size won't change, but mtime will)	COMMENT
MEDIUM	tests/test_scheduler.py	2979	# Create a mock CacheList object	COMMENT
MEDIUM⚡	tests/test_embedding.py	194	# Create a unit vector [0.6, 0.8, 0.0] (norm = 1.0)	COMMENT
MEDIUM	tests/test_embedding.py	213	# Create a vector [1, 1, 1] / sqrt(3) = [0.577, 0.577, 0.577]	COMMENT
MEDIUM⚡	tests/test_batched_engine.py	574	# Create a mock model where config is a dict	COMMENT
MEDIUM	tests/test_audio_tts.py	1185	# Create a base64 string just over the limit	COMMENT
MEDIUM	tests/test_mcp_manager.py	294	# Create a user tool with same name as MCP tool	COMMENT
MEDIUM	tests/test_hot_cache.py	537	# Create a fake hot cache entry with raw bytes	COMMENT
MEDIUM	tests/test_hf_uploader.py	200	# Create a fake safetensors file	COMMENT
MEDIUM	tests/test_index_cache.py	107	# Create a mock model with 4 layers	COMMENT
MEDIUM⚡	tests/test_admin_auth.py	308	# Create a token with the new serializer	COMMENT
MEDIUM	omlx/server.py	5565	# Create a temporary MessagesRequest to reuse existing conversion logic	COMMENT
MEDIUM	omlx/_torch_stub.py	34	# This module is the single source of truth — packaging/build.py imports	COMMENT
MEDIUM	omlx/admin/routes.py	4151	# This file is at omlx/admin/routes.py → package dir is omlx/	COMMENT
MEDIUM	benchmarks/bonsai_decode_bench.py	390	# Create a QuantizedLinear with our construct patch active	COMMENT

Redundant / Tautological Comments35 hits · 47 pts

Severity	File	Line	Snippet	Context
LOW	tests/test_engine_pool.py	1418	# Set limit to allow each model individually but not both together	COMMENT
LOW⚡	tests/test_settings.py	1615	# Set env to port 8888	COMMENT
LOW	tests/integration/test_vlm_mrope_integration.py	731	# Check if model supports cached_image_features	COMMENT
LOW	omlx/cli.py	393	# Check if oMLX server is running	COMMENT
LOW	omlx/cli.py	469	# Check if tool is installed	COMMENT
LOW	omlx/scheduler.py	6207	# Check if it's a list of cache layers	COMMENT
LOW	omlx/scheduler.py	6215	# Check if layer has expected structure	COMMENT
LOW	omlx/scheduler.py	8781	# Check if prompt ends with <think> token for reasoning models.	COMMENT
LOW	omlx/scheduler.py	9303	# Check if this request uses a protocol-specific output parser	COMMENT
LOW	omlx/engine_pool.py	1698	# Check if DFlash is enabled -- takes priority over engine type	COMMENT
LOW	omlx/engine_pool.py	1946	# Check if memory enforcer requested abort during loading	COMMENT
LOW	omlx/engine_pool.py	2240	# Check if model has active requests	COMMENT
LOW	omlx/memory_monitor.py	31	# Check if MLX Metal is available	COMMENT
LOW	omlx/cache/paged_ssd_cache.py	2033	# Check if block was evicted while write was pending.	COMMENT
LOW	omlx/cache/paged_ssd_cache.py	2181	# Check if already exists in index (thread-safe)	COMMENT
LOW	omlx/cache/vision_feature_cache.py	246	# Check if already on SSD	COMMENT
LOW	omlx/cache/prefix_cache.py	309	# Check if this layer is RotatingKVCache	COMMENT
LOW	omlx/cache/prefix_cache.py	472	# Check if cache_data contains extracted tensor states	COMMENT
LOW	omlx/cache/prefix_cache.py	580	# Check if this block already exists (deduplication)	COMMENT
LOW	omlx/cache/prefix_cache.py	1257	# Check if all sub-caches are sliceable 4D KVCache tensors.	COMMENT
LOW	omlx/patches/specprefill.py	871	# Check if model has RoPE (Nemotron-H doesn't)	COMMENT
LOW	omlx/patches/deepseek_v4/cache_extras.py	943	# Check if all caches are empty	COMMENT
LOW	omlx/admin/ms_downloader.py	28	# Check if modelscope SDK is available	COMMENT
LOW	omlx/admin/ms_downloader.py	875	# Check if cancelled while waiting in queue	COMMENT
LOW	omlx/admin/ms_downloader.py	925	# Check if cancelled while downloading - clean up downloaded files	COMMENT
LOW	omlx/admin/hf_downloader.py	809	# Check if cancelled while waiting in queue	COMMENT
LOW	omlx/admin/hf_downloader.py	908	# Check if cancelled while downloading	COMMENT
LOW	omlx/admin/routes.py	2098	# Check if model exists	COMMENT
LOW	omlx/mcp/executor.py	176	# Check if tool exists	COMMENT
LOW	omlx/adapter/harmony.py	293	# Check if this is a special token (should not be streamed)	COMMENT
LOW	omlx/api/thinking.py	272	# Check if this could be a tag start	COMMENT
LOW	omlx/api/thinking.py	299	# Check if it could be a partial tag (not enough chars yet)	COMMENT
LOW	omlx/api/anthropic_utils.py	596	# Check if pre-truncation content was JSON-like	COMMENT
LOW	omlx/engine/vlm.py	3602	# Check if user provided meaningful text	COMMENT
LOW	benchmarks/bonsai_decode_bench.py	335	# Check if this variant is available (not just falling back)	COMMENT

Hallucination Indicators3 hits · 45 pts

Severity	File	Line	Snippet	Context
CRITICAL⚡	omlx/admin/static/js/marked.umd.js	1473	while ((match = this.tokenizer.rules.inline.reflinkSearch.exec(maskedSrc)) != null) {	CODE
CRITICAL⚡	omlx/admin/static/js/marked.umd.js	1481	while ((match = this.tokenizer.rules.inline.blockSkip.exec(maskedSrc)) != null) {	CODE
CRITICAL⚡	omlx/admin/static/js/marked.umd.js	1485	while ((match = this.tokenizer.rules.inline.anyPunctuation.exec(maskedSrc)) != null) {	CODE

Modern AI Meta-Vocabulary17 hits · 42 pts

Severity	File	Line	Snippet	Context
MEDIUM	omlx/model_settings.py	231	# agentic workloads where acceptance drops on the default sliding window.	COMMENT
MEDIUM	omlx/server.py	767	# on the failure mode. Without it, "context window too small"	COMMENT
MEDIUM	omlx/server.py	2982	# Validate context window for each prompt	COMMENT
MEDIUM	omlx/server.py	3357	# Validate context window before sending to model	COMMENT
MEDIUM	omlx/server.py	5395	# Validate context window before sending to model	COMMENT
MEDIUM	omlx/server.py	5809	# Validate context window	COMMENT
MEDIUM	omlx/model_discovery.py	165	# Known embedding model types from mlx-embeddings	COMMENT
MEDIUM	omlx/admin/routes.py	1908	# Native context window from the model's config.json — used by	COMMENT
MEDIUM	omlx/adapter/harmony.py	507	# Extract chain-of-thought text from analysis channel	COMMENT
MEDIUM	omlx/integrations/claude.py	93	# set the detected context window for custom model IDs that	COMMENT
MEDIUM	omlx/integrations/claude.py	102	# built-in context window for those regardless of this variable.	COMMENT
MEDIUM	omlx/api/openai_models.py	443	# effective context window from the listing without a separate call	COMMENT
MEDIUM	omlx/api/tool_calling.py	643	# agentic load (large system prompt + many tool schemas + a big tool result)	COMMENT
MEDIUM	omlx/eval/mmlu.py	76	# Load dev examples for few-shot	COMMENT
MEDIUM	omlx/eval/mmlu.py	109	# Add few-shot examples	COMMENT
MEDIUM	omlx/engine/batched.py	330	# below their context window. The route is memory-aware: it defers to	COMMENT
MEDIUM	apps/omlx-mac/Sources/AppView/AppView.swift	499	// MARK: - Detail scaffold	COMMENT

AI Slop Vocabulary9 hits · 26 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	tests/test_tool_calling.py	1958	# Gemma 4 robust fallback parser tests	COMMENT
LOW	omlx/output_collector.py	70	# Replace: just use the new output	COMMENT
MEDIUM	omlx/scheduler.py	7460	# by omlx) would yield a list. Guard so the path stays robust	COMMENT
LOW	omlx/scheduler.py	2352	# If window_size itself is already >= max, just use window_size.	COMMENT
LOW	omlx/utils/model_loading.py	969	# The quant method may be already supported by mlx-lm; simply return None.	COMMENT
MEDIUM⚡	omlx/api/tool_calling.py	597	# Gemma 4 robust fallback parser	COMMENT
MEDIUM	omlx/api/tool_calling.py	1324	# Gemma 4 only: try robust fallback that handles bare	COMMENT
LOW	omlx/api/tool_calling.py	2241	# Handle None or text format - just return original	COMMENT
MEDIUM⚡	benchmarks/bonsai_decode_bench.py	147	# Timing harness	COMMENT

AI Structural Patterns36 hits · 25 pts

Severity	File	Line	Context
LOW	tests/test_system_sampler.py	19	CODE
LOW	tests/test_mlx_vlm_pixtral_torch_free.py	41	CODE
LOW	tests/test_cache_observability.py	14	CODE
LOW	tests/test_oq_fused_qkv_virtual.py	155	CODE
LOW	omlx/model_settings.py	992	CODE
LOW	omlx/server.py	1233	CODE
LOW	omlx/process_memory_enforcer.py	318	CODE
LOW	omlx/engine_core.py	531	CODE
LOW	omlx/oq.py	5114	CODE
LOW	omlx/cache/paged_ssd_cache.py	1294	CODE
LOW	omlx/patches/specprefill.py	448	CODE
LOW	omlx/patches/mlx_lm_mtp/qwen35_model.py	388	CODE
LOW	omlx/admin/hf_downloader.py	389	CODE
LOW	omlx/admin/oq_manager.py	250	CODE
LOW	omlx/admin/routes.py	5339	CODE
LOW	omlx/utils/sampling.py	132	CODE
LOW	omlx/api/audio_routes.py	440	CODE
LOW	omlx/engine/tts.py	163	CODE
LOW	omlx/engine/tts.py	306	CODE
LOW	omlx/engine/vlm.py	3038	CODE
LOW	omlx/engine/vlm.py	3142	CODE
LOW	omlx/engine/vlm.py	3268	CODE
LOW	omlx/engine/vlm.py	3485	CODE
LOW	omlx/engine/dflash.py	289	CODE
LOW	omlx/engine/dflash.py	1325	CODE
LOW	omlx/engine/dflash.py	1524	CODE
LOW	omlx/engine/dflash.py	1679	CODE
LOW	omlx/engine/dflash.py	1754	CODE
LOW	omlx/engine/batched.py	685	CODE
LOW	omlx/engine/batched.py	760	CODE
LOW	omlx/engine/batched.py	865	CODE
LOW	omlx/engine/batched.py	1021	CODE
LOW	omlx/engine/base.py	129	CODE
LOW	omlx/engine/base.py	161	CODE
LOW	omlx/engine/base.py	193	CODE
LOW	omlx/engine/base.py	225	CODE

Verbosity Indicators11 hits · 22 pts

Severity	File	Line	Snippet	Context
LOW⚡	packaging/build.py	646	# Step 0: Render the resolved venvstacks.toml from pyproject.toml deps	COMMENT
LOW⚡	packaging/build.py	653	# Step 1: Build wheels from git-pinned packages	COMMENT
LOW⚡	packaging/build.py	656	# Step 2: Swap git URLs in the resolved toml for local wheel paths	COMMENT
LOW⚡	packaging/build.py	666	# Step 3: Lock environments (always re-lock to match current wheels)	COMMENT
LOW⚡	packaging/build.py	681	# Step 4: Build environments	COMMENT
LOW⚡	packaging/build.py	689	# Step 5: Export to local directory for app bundle	COMMENT
LOW⚡	tests/integration/test_vlm_mrope_integration.py	543	# Step 1: image request	COMMENT
LOW	tests/integration/test_vlm_mrope_integration.py	561	# Step 2: text-only request (must not be contaminated by prior rope_deltas)	COMMENT
LOW⚡	omlx/cache/prefix_cache.py	899	# Step 2: Fallback - find max seq_len among all 4D tensors	COMMENT
LOW	omlx/cache/prefix_cache.py	852	# Step 1: Search for a sliceable KVCache layer (full attention)	COMMENT
LOW	omlx/cache/prefix_cache.py	945	# Step 3: CacheList fallback — check sub-states for seq_len	COMMENT

Structural Annotation Overuse11 hits · 22 pts

Severity	File	Line	Snippet	Context
LOW⚡	packaging/build.py	646	# Step 0: Render the resolved venvstacks.toml from pyproject.toml deps	COMMENT
LOW⚡	packaging/build.py	653	# Step 1: Build wheels from git-pinned packages	COMMENT
LOW⚡	packaging/build.py	656	# Step 2: Swap git URLs in the resolved toml for local wheel paths	COMMENT
LOW⚡	packaging/build.py	666	# Step 3: Lock environments (always re-lock to match current wheels)	COMMENT
LOW⚡	packaging/build.py	681	# Step 4: Build environments	COMMENT
LOW⚡	packaging/build.py	689	# Step 5: Export to local directory for app bundle	COMMENT
LOW⚡	tests/integration/test_vlm_mrope_integration.py	543	# Step 1: image request	COMMENT
LOW	tests/integration/test_vlm_mrope_integration.py	561	# Step 2: text-only request (must not be contaminated by prior rope_deltas)	COMMENT
LOW⚡	omlx/cache/prefix_cache.py	899	# Step 2: Fallback - find max seq_len among all 4D tensors	COMMENT
LOW	omlx/cache/prefix_cache.py	852	# Step 1: Search for a sliceable KVCache layer (full attention)	COMMENT
LOW	omlx/cache/prefix_cache.py	945	# Step 3: CacheList fallback — check sub-states for seq_len	COMMENT

Dead Code4 hits · 6 pts

Severity	File	Line	Context
MEDIUM	tests/test_audio_stt.py	1080	CODE
MEDIUM	tests/test_audio_tts.py	662	CODE
MEDIUM	tests/test_server_prefill_memory_handler.py	179	CODE
MEDIUM	tests/test_sse_keepalive.py	88	CODE

Fake / Example Data2 hits · 2 pts

Severity	File	Line	Snippet	Context
LOW	omlx/admin/static/js/purify.min.js	2	!function(e,t){"object"==typeof exports&&"undefined"!=typeof module?module.exports=t():"function"==typeof define&&define	CODE
LOW	omlx/admin/static/js/highlight.min.js	317	}),re=["a","abbr","address","article","aside","audio","b","blockquote","body","button","canvas","caption","cite","code",	CODE

Example Usage Blocks1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	apps/omlx-mac/Scripts/build.sh	31	# Usage:	COMMENT

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings