chore: bump uv.lock and fix ruff 0.16 default-rule lint findings

uv.lock was stale (ty 0.0.50 -> 0.0.78, ruff 0.15 -> 0.16, polars, numpy,
typer, wandb, pytest, and others), all within existing pyproject.toml
bounds. ruff 0.16 widened its default rule selection, taking this repo
from 0 to 274 lint errors under the same config; --fix handled most of
it (import sorting, Optional[X] -> X | None, ...), and the remainder
(unused unpacked variables, dict()-as-literal, subprocess.run without
explicit check=, a couple of intentional broad excepts/naive datetimes)
were fixed or annotated by hand. Also fixes a real type-narrowing gap
ty 0.0.78 caught in test_config_consumed_keys.py's `or`-combined
isinstance check.

torch stays pinned to 2.3.x (deliberate, see CLAUDE.md); pyarrow's <25
ceiling is left as a separate decision.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TMdZFqXXig7i3XkirSUxef

tests/legacy/network_v02_snapshot.py

@@ -17,8 +17,8 @@ import re
 from collections.abc import Sequence
 
 import torch
-import torch.nn as nn
 import torch.nn.functional as F
+from torch import nn
 
 from giant.constants import (
     COND_DIM,
@@ -949,7 +949,7 @@ def _check_router_conditioning_compat(router_types: list[str], conditioning: str
 
 
 def _build_router_from_cfg(router_cfg: dict, pdg_vocab: int, mat_vocab: int, conditioning: str = "embedding") -> Router:
-    shared_vocab = dict(pdg_vocab=pdg_vocab, mat_vocab=mat_vocab)
+    shared_vocab = {"pdg_vocab": pdg_vocab, "mat_vocab": mat_vocab}
     if router_cfg["type"] == "composed":
         axes = _parse_composed_axes(router_cfg)
         _check_router_conditioning_compat([a["type"] for a in axes], conditioning)
@@ -977,15 +977,15 @@ def build_models(model_config: dict) -> tuple[nn.Module, nn.Module]:
     if router_cfg and router_cfg.get("enabled"):
         pdg_vocab = model_config["pdg_vocab"]
         mat_vocab = model_config["mat_vocab"]
-        shared = dict(
-            pdg_vocab=pdg_vocab,
-            mat_vocab=mat_vocab,
-            expert_hidden_dim=model_config.get("expert_hidden_dim") or model_config.get("hidden_dim", 128),
-            expert_n_blocks=model_config.get("expert_n_blocks") or model_config.get("n_blocks", 3),
-            emb_dim=model_config.get("emb_dim", EMB_DIM),
-            dropout=model_config.get("dropout", 0.1),
-            conditioning=model_config.get("conditioning", "embedding"),
-        )
+        shared = {
+            "pdg_vocab": pdg_vocab,
+            "mat_vocab": mat_vocab,
+            "expert_hidden_dim": model_config.get("expert_hidden_dim") or model_config.get("hidden_dim", 128),
+            "expert_n_blocks": model_config.get("expert_n_blocks") or model_config.get("n_blocks", 3),
+            "emb_dim": model_config.get("emb_dim", EMB_DIM),
+            "dropout": model_config.get("dropout", 0.1),
+            "conditioning": model_config.get("conditioning", "embedding"),
+        }
         conditioning = shared["conditioning"]
         stage1 = RoutedDenoisingMLP(
             router=_build_router_from_cfg(router_cfg, pdg_vocab, mat_vocab, conditioning),

tests/test_amp.py

@@ -5,12 +5,12 @@ from pathlib import Path
 
 import pytest
 import torch
+from test_train import _base_cfg, _run_train
 
 from giant.model.routers import EnergyRouter
 from giant.model.wgan import gradient_penalty
 from giant.training.amp import resolve_autocast
 from giant.training.stage2_inputs import _remaining_energy_fraction
-from test_train import _base_cfg, _run_train
 
 # ---------------------------------------------------------------------------
 # resolve_autocast

tests/test_analysis_reduce.py

@@ -184,7 +184,7 @@ def test_weighted_profile_matches_manual_bincount():
     ea = R.entry_axis(lf)
     lf2 = R.attach_entry_axis(lf, ea)
     edges = np.linspace(0.0, 3.0, 4)  # depth bins along +z
-    mean, std = R.weighted_profile(lf2, R.depth_expr(), edges, pl.col("edep"))
+    mean, _ = R.weighted_profile(lf2, R.depth_expr(), edges, pl.col("edep"))
     assert mean.shape == (3,)
     # totals conserved: sum over bins == mean total edep per event
     assert np.isclose(mean.sum() * 1, (90.0 + 30.0) / 2)  # 2 events

tests/test_bump_dataset_version.py

@@ -197,7 +197,7 @@ def test_update_manifest_reports_missing_targets(tmp_path):
     # schema2 dir exists but the parquet file does not
     (tmp_path / "processed" / "steps" / "gen1" / "schema2").mkdir(parents=True)
 
-    lines, missing = plan_update_manifest(manifest, "schema2")
+    _, missing = plan_update_manifest(manifest, "schema2")
     assert len(missing) == 1
     assert "schema2" in str(missing[0])
 
@@ -313,7 +313,7 @@ def test_create_manifest_writes_relative_paths(tmp_path):
 def test_create_manifest_reports_missing_files(tmp_path):
     ghost = tmp_path / "processed" / "gen1" / "schema2" / "shard-000.parquet"
     output = tmp_path / "pools" / "full.manifest"
-    lines, missing, _ = plan_create_manifest(output, [ghost])
+    _, missing, _ = plan_create_manifest(output, [ghost])
     assert len(missing) == 1
     assert missing[0] == ghost.resolve()
 

tests/test_cli_train_overrides.py

@@ -9,7 +9,7 @@ from pathlib import Path
 
 from typer.testing import CliRunner
 
-import giant.cli as cli
+from giant import cli
 
 runner = CliRunner()
 

tests/test_cond_layout.py

@@ -1,4 +1,5 @@
 import pytest
+
 from giant.cond_layout import AXIS_TYPES, CondLayout
 from giant.constants import COND_DIM, COND_DIM_BASE, MATERIAL_PHYS_DIM, PARTICLE_PHYS_DIM
 

tests/test_config.py

@@ -576,7 +576,7 @@ def test_save_config_round_trips_three_level_nesting(tmp_path):
 # default_out_dir_name
 # ---------------------------------------------------------------------------
 
-_NOW = datetime(2026, 7, 29, 14, 30)
+_NOW = datetime(2026, 7, 29, 14, 30)  # noqa: DTZ001 - naive, matching default_out_dir_name's naive datetime.now()
 
 
 def _cfg_with(**dotted_overrides):

tests/test_config_consumed_keys.py

@@ -90,7 +90,7 @@ def _collect_names(source: str, filename: str) -> set[str]:
             names.add(node.attr)
         elif isinstance(node, ast.Constant) and isinstance(node.value, str) and id(node) not in docstring_ids:
             names.add(node.value)
-        elif isinstance(node, ast.arg):
+        elif isinstance(node, ast.arg):  # noqa: SIM114 - kept separate so ty narrows node.arg to str, not str | None
             names.add(node.arg)
         elif isinstance(node, ast.keyword) and node.arg is not None:
             names.add(node.arg)

tests/test_dwarf.py

@@ -1,3 +1,4 @@
+from test_pipeline import _make_synthetic_steps
 from typer.testing import CliRunner
 
 from giant import cli as giant_cli
@@ -5,7 +6,6 @@ from giant.config import Conditioning
 from giant.data import setup_cache
 from giant.tools import dwarf
 from giant.tools.dwarf import app
-from test_pipeline import _make_synthetic_steps
 
 runner = CliRunner()
 

tests/test_flow.py

@@ -1,9 +1,10 @@
 import torch
+
 from giant.config import ConditioningAxisConfig
 from giant.constants import COND_DIM
 from giant.model.network import Stage1Model
 from giant.model.schedule import CosineSchedule, flow_matching_loss
-from giant.sample import sample_flow, sample_ddim
+from giant.sample import sample_ddim, sample_flow
 
 PARTICLE_CFG = ConditioningAxisConfig(type="physical", emb_dim=8, n_layers=1)
 MATERIAL_CFG = ConditioningAxisConfig(type="physical", emb_dim=8, n_layers=1)

tests/test_network.py

@@ -2,8 +2,9 @@ import copy
 
 import pytest
 import torch
+
 from giant import config as gconfig
-from giant.constants import CONT_SLOT_DIM, COND_DIM, PARTICLE_PHYS_DIM, SEC_SLOT_DIM
+from giant.constants import COND_DIM, CONT_SLOT_DIM, PARTICLE_PHYS_DIM, SEC_SLOT_DIM
 from giant.model.network import (
     HISTORY_REGISTRY,
     AttentionHistory,
@@ -1217,18 +1218,18 @@ def test_stage_classes_are_stagemodel_subclasses(cls):
 @pytest.mark.parametrize("cls", [Stage1Model, Stage2OneShot, Stage2Autoregressive])
 @pytest.mark.parametrize("generator", ["flow", "ddpm", "wgan"])
 def test_stagemodel_time_emb_matches_objective_needs_time(cls, generator):
-    kwargs = dict(
-        pdg_vocab=5,
-        mat_vocab=3,
-        particle_cfg=PARTICLE_CFG,
-        material_cfg=MATERIAL_CFG,
-        hidden_dim=_STAGE_HIDDEN_DIM,
-        n_res_blocks=_STAGE_N_BLOCKS,
-        cond_out_dim=_STAGE_COND_OUT_DIM,
-        generator=generator,
-        time_dim=8,
-        noise_dim=8,
-    )
+    kwargs = {
+        "pdg_vocab": 5,
+        "mat_vocab": 3,
+        "particle_cfg": PARTICLE_CFG,
+        "material_cfg": MATERIAL_CFG,
+        "hidden_dim": _STAGE_HIDDEN_DIM,
+        "n_res_blocks": _STAGE_N_BLOCKS,
+        "cond_out_dim": _STAGE_COND_OUT_DIM,
+        "generator": generator,
+        "time_dim": 8,
+        "noise_dim": 8,
+    }
     if cls is Stage1Model:
         kwargs["n_sec_head_k_max"] = 15
     else:

tests/test_phase2.py

@@ -20,7 +20,6 @@ from giant.model.schedule import (
 )
 from giant.sample import sample_secondaries
 
-
 # ── helpers ──────────────────────────────────────────────────────────────────
 
 
@@ -341,7 +340,7 @@ def test_encode_secondaries_energy_conservation():
 def test_encode_secondaries_stick_logits_match_naive_reference():
     """Cumsum-based remaining-budget computation must match a naive
     per-row, per-slot Python reference (no cumsum) within float tolerance."""
-    from giant.data.transforms import encode_secondaries, _EPS, _STICK_LOGIT_CLIP
+    from giant.data.transforms import _EPS, _STICK_LOGIT_CLIP, encode_secondaries
 
     rng = np.random.default_rng(11)
     N = 25
@@ -569,7 +568,7 @@ def test_decode_secondaries_degenerate_row_falls_back_to_even_split():
     e_sec = np.array([0.0, 4.0, 9.0, 30.0], dtype=np.float32)
     pre_dir = np.tile([0.0, 0.0, 1.0], (N, 1)).astype(np.float32)
 
-    sec_E, _sec_dir, _mass, _charge, sec_valid = decode_secondaries(sec_cont, n_sec, e_sec, pre_dir)
+    sec_E, _sec_dir, _mass, _charge, _ = decode_secondaries(sec_cont, n_sec, e_sec, pre_dir)
 
     for i, k in enumerate(n_sec):
         if k == 0:
@@ -593,7 +592,7 @@ def test_decode_secondaries_rescale_preserves_relative_shares():
     n_sec = np.array([4])
     pre_dir = np.array([[0.0, 0.0, 1.0]], dtype=np.float32)
 
-    sec_E_small, _, _, _, sec_valid = decode_secondaries(sec_cont, n_sec, np.array([5.0], dtype=np.float32), pre_dir)
+    sec_E_small, _, _, _, _ = decode_secondaries(sec_cont, n_sec, np.array([5.0], dtype=np.float32), pre_dir)
     sec_E_large, _, _, _, _ = decode_secondaries(sec_cont, n_sec, np.array([50.0], dtype=np.float32), pre_dir)
 
     ratio_small = sec_E_small[0, :4] / sec_E_small[0, 0]

tests/test_render.py

@@ -9,8 +9,8 @@ import pytest
 
 pytest.importorskip("plotstyle")
 
-from giant.analysis import render as render_mod  # noqa: E402
-from giant.analysis.reduced import Reduced  # noqa: E402
+from giant.analysis import render as render_mod
+from giant.analysis.reduced import Reduced
 
 
 def _try_render(reduced: list[Reduced], out: Path):

tests/test_rollout.py

@@ -9,7 +9,7 @@ import pytest
 import torch
 
 from giant.config import ConditioningAxisConfig, ParticleTypeConfig
-from giant.constants import TERM_ESCAPED, TERM_MAX_STEPS, TERM_UNKNOWN_PDG, K_MAX
+from giant.constants import K_MAX, TERM_ESCAPED, TERM_MAX_STEPS, TERM_UNKNOWN_PDG
 from giant.data.loader import TopNMap
 from giant.data.transforms import Normalizer
 from giant.model.network import (
@@ -21,7 +21,7 @@ from giant.model.network import (
 from giant.rollout import L1DistCollector, make_seed_frontier, rollout
 
 pytest.importorskip("sklearn")
-from giant import geometry as g  # noqa: E402
+from giant import geometry as g
 
 PDG_MAP = {22: 0, 11: 1, -11: 2}
 MAT_MAP = {"G4_AIR": 0, "G4_PbWO4": 1}

tests/test_router.py

@@ -1,5 +1,7 @@
 """Tests for the mixture-of-experts routing prototype (giant/model/network.py)."""
 
+import itertools
+
 import pytest
 import torch
 
@@ -7,6 +9,7 @@ from giant.config import ConditioningAxisConfig
 from giant.constants import COND_DIM, K_MAX, SEC_DIM, X_DIM
 from giant.model.network import (
     BLOCK_REGISTRY,
+    ROUTER_REGISTRY,
     TRUNK_REGISTRY,
     AdaLNResBlock,
     ComposedRouter,
@@ -17,7 +20,6 @@ from giant.model.network import (
     NoneRouter,
     PdgRouter,
     ProcessRouter,
-    ROUTER_REGISTRY,
     ResBlock,
     RoutedTrunk,
     Stage1Model,
@@ -397,7 +399,7 @@ def test_energy_router_own_width_controls_own_coverage_independent_of_others():
             router.raw_width[0] = raw
             shares.append(router.gate(cond_cont, cond_cat)[0, 0].item())
 
-    assert all(a <= b + 1e-6 for a, b in zip(shares, shares[1:]))
+    assert all(a <= b + 1e-6 for a, b in itertools.pairwise(shares))
 
 
 def test_build_router_threads_learn_width_kwargs_through():
@@ -1010,9 +1012,7 @@ def test_build_models_routed_pair_composed_router_is_drop_in_for_sample_flow():
     n_sec_pred = stage2.predict_n_sec(cond_cont, cond_cat, stage1_norm).argmax(dim=-1)
     assert n_sec_pred.shape == (B,)
 
-    sec_cont, sec_type_emb, sec_valid = sample_secondaries(
-        stage2, cond_cont, cond_cat, stage1_norm, n_sec_pred, steps=2
-    )
+    sec_cont, _, sec_valid = sample_secondaries(stage2, cond_cont, cond_cat, stage1_norm, n_sec_pred, steps=2)
     assert sec_cont.shape == (B, K_MAX, 4)
     assert sec_valid.shape == (B, K_MAX)
 
@@ -1261,9 +1261,7 @@ def test_build_models_routed_pair_is_drop_in_for_sample_flow():
     n_sec_pred = stage2.predict_n_sec(cond_cont, cond_cat, stage1_norm).argmax(dim=-1)
     assert n_sec_pred.shape == (B,)
 
-    sec_cont, sec_type_emb, sec_valid = sample_secondaries(
-        stage2, cond_cont, cond_cat, stage1_norm, n_sec_pred, steps=2
-    )
+    sec_cont, _, sec_valid = sample_secondaries(stage2, cond_cont, cond_cat, stage1_norm, n_sec_pred, steps=2)
     assert sec_cont.shape == (B, K_MAX, 4)
     assert sec_valid.shape == (B, K_MAX)
 

tests/test_sample.py

@@ -262,7 +262,7 @@ def test_sample_secondaries_ar_first_slot_has_no_history():
     cond_cont, cond_cat = _cond(B)
     stage1_out = torch.randn(B, X_DIM)
     n_sec_pred = torch.tensor([0, 1, 1])
-    sec_cont, sec_type, sec_valid = sample_secondaries_ar(decoder, cond_cont, cond_cat, stage1_out, n_sec_pred, steps=2)
+    sec_cont, _, sec_valid = sample_secondaries_ar(decoder, cond_cont, cond_cat, stage1_out, n_sec_pred, steps=2)
     assert sec_cont.shape == (B, 1, CONT_SLOT_DIM)
     assert sec_valid.tolist() == [[False], [True], [True]]
 
@@ -281,7 +281,7 @@ def test_sample_secondaries_ar_stop_token_forced_stop_gives_zero_secondaries(n_s
     _force_stop_head_logit(decoder, 50.0)
     cond_cont, cond_cat = _cond(B)
     stage1_out = torch.randn(B, X_DIM)
-    sec_cont, sec_type, sec_valid = sample_secondaries_ar(decoder, cond_cont, cond_cat, stage1_out, None, steps=2)
+    _, _, sec_valid = sample_secondaries_ar(decoder, cond_cont, cond_cat, stage1_out, None, steps=2)
     assert sec_valid.shape == (B, k_max)
     assert not sec_valid.any()
 
@@ -296,7 +296,7 @@ def test_sample_secondaries_ar_stop_token_forced_never_stop_runs_to_k_max(n_sec_
     _force_stop_head_logit(decoder, -50.0)
     cond_cont, cond_cat = _cond(B)
     stage1_out = torch.randn(B, X_DIM)
-    sec_cont, sec_type, sec_valid = sample_secondaries_ar(decoder, cond_cont, cond_cat, stage1_out, None, steps=2)
+    _, _, sec_valid = sample_secondaries_ar(decoder, cond_cont, cond_cat, stage1_out, None, steps=2)
     assert sec_valid.all()
 
 
@@ -412,7 +412,7 @@ def test_sample_secondaries_ar_full_length_ignores_n_sec_pred_zero_rows():
     cond_cont, cond_cat = _cond(B)
     stage1_out = torch.randn(B, X_DIM)
     n_sec_pred = torch.tensor([0, 0, 0])
-    sec_cont, sec_type, sec_valid = sample_secondaries_ar(
+    sec_cont, _, sec_valid = sample_secondaries_ar(
         decoder, cond_cont, cond_cat, stage1_out, n_sec_pred, steps=2, full_length=True
     )
     assert not sec_valid.any()

tests/test_train.py

@@ -12,6 +12,7 @@ import pytest
 import torch
 import torch.nn.functional as F
 
+from giant.checkpoint_io import load_for_inference
 from giant.config import ParticleTypeConfig
 from giant.constants import (
     COND_DIM,
@@ -21,7 +22,6 @@ from giant.constants import (
     SEC_SLOT_DIM,
     X_DIM,
 )
-from giant.checkpoint_io import load_for_inference
 from giant.data.dataset import StepBatch
 from giant.data.transforms import Normalizer
 from giant.model.network import Stage2Autoregressive, build_critics, build_models
@@ -36,7 +36,6 @@ from giant.training import (
     train,
 )
 from giant.training.metrics import _wandb_run_config
-from giant.training.trainers import _type_class_weight_vector
 from giant.training.stage2_inputs import (
     _ar_has_prev,
     _assemble_stage2_ar_inputs,
@@ -51,6 +50,7 @@ from giant.training.stage2_inputs import (
     _stop_target_and_mask,
     _type_repr,
 )
+from giant.training.trainers import _type_class_weight_vector
 
 PDG_VOCAB = 6
 MAT_VOCAB = 3
@@ -543,19 +543,18 @@ def test_train_raises_when_no_active_stage():
     model_config = _model_config(cfg)
     models = build_models(model_config)
     critics = build_critics(model_config)
-    with tempfile.TemporaryDirectory() as tmp:
-        with pytest.raises(ValueError, match="no active stage"):
-            train(
-                cfg=cfg,
-                models=models,
-                critics=critics,
-                train_loader=_fake_batches(1, 8),
-                val_loader=_fake_batches(1, 8),
-                device=torch.device("cpu"),
-                out_dir=Path(tmp) / "run",
-                model_config=model_config,
-                total_train_batches=1,
-            )
+    with tempfile.TemporaryDirectory() as tmp, pytest.raises(ValueError, match="no active stage"):
+        train(
+            cfg=cfg,
+            models=models,
+            critics=critics,
+            train_loader=_fake_batches(1, 8),
+            val_loader=_fake_batches(1, 8),
+            device=torch.device("cpu"),
+            out_dir=Path(tmp) / "run",
+            model_config=model_config,
+            total_train_batches=1,
+        )
 
 
 def test_metrics_csv_columns_are_stage_prefixed():

tests/test_training_plots.py

@@ -11,8 +11,8 @@ import pytest
 
 pytest.importorskip("plotstyle")
 
-from giant.training import plots as plots_mod  # noqa: E402
-from giant.training.plots import MetricsTable, derive_metrics_dir, render_metrics  # noqa: E402
+from giant.training import plots as plots_mod
+from giant.training.plots import MetricsTable, derive_metrics_dir, render_metrics
 
 # --- fixtures ----------------------------------------------------------
 

tests/test_transforms.py

@@ -2,9 +2,13 @@ import warnings
 
 import numpy as np
 import pytest
+
 from giant.cond_layout import AXIS_TYPES, CondLayout
 from giant.constants import COND_DIM, COND_DIM_BASE, K_MAX
 from giant.data.transforms import (
+    Normalizer,
+    _vectorized_map_lookup,
+    _WelfordAccumulator,
     build_cond_features,
     build_features,
     encode_secondaries,
@@ -14,12 +18,9 @@ from giant.data.transforms import (
     inv_log_transform,
     local_frame_rotation,
     log_transform,
-    Normalizer,
     reconstruct_post_pos,
     sorted_membership,
     travel_direction,
-    _vectorized_map_lookup,
-    _WelfordAccumulator,
 )