Support fitsbolt 0.3.1 and cutana 0.4.0

[gomezzz]

Summary

• Relax the fitsbolt pin to >=0.3.1,<0.4 and require cutana>=0.4.0. fitsbolt 0.3.1 fixes the fits_extension=None validation crash that motivated the ==0.2.0 pin (f72b3db). cutana 0.4.0 requires fitsbolt>=0.3.1, so the old pin silently forced pip to fall back to cutana 0.3.1 (noticed in the Euclid EC GPU datalab image).
• Keep old checkpoints working. Models saved with fitsbolt 0.2 store a fitsbolt_cfg that has no *_n_samples keys and keeps the midtones parameters as scalars. Under fitsbolt 0.3, prediction with such a model raised TypeError: '>' not supported between instances of 'int' and 'DotMap' for every normalisation method except ZSCALE. load_checkpoint now upgrades these configs in place (None = use all pixels, which matches the pre-0.3 behaviour).
• Test fixes caused by the upgrade:
  • fitsbolt 0.3 resizes with OpenCV, so interpolation_order is now 0–4 (4 = INTER_AREA, which is identical to nearest neighbour when upscaling). The default (1, linear) is unchanged.
  • cutana 0.4's streaming orchestrator returns batches in completion order. test_cutana_vs_training_normalisation paired images by position and failed under parallel load (max abs diff = 254), so it now pairs them by source ID. The production path in prediction_process_cutana.py already maps results by metadata["source_id"] and is unaffected.

Validation

• I saved a checkpoint in a fitsbolt 0.2.0 env and loaded it in a fitsbolt 0.3.1 env, then pushed an image through process_single_wrapper for all 6 normalisation methods. Before this change: 5/6 fail. After: 6/6 pass. This case is now covered by a unit test.
• I measured how far training and prediction preprocessing drift apart (load_and_process_wrapper vs load_and_process_single_wrapper):
  • CONVERSION_ONLY: about 1 grey level mean difference with both fitsbolt 0.2.0 and 0.3.1.
  • ASINH: 0 with both versions.
  • Resize semantics for trained models are effectively unchanged.

Test plan

• Full suite on fitsbolt 0.3.1 + cutana 0.4.0 (CPU torch, Python 3.11): 377 passed, 3× with -n 8 and 1× serially
• Baseline on fitsbolt 0.2.0 + cutana 0.3.1: 376 passed (no regressions on the old pin)
• ruff check / ruff format --check clean on all touched files
• CI green
• GPU smoke test: train, then predict with a pre-existing v1.3.x model

🤖 Generated with Claude Code

[github-actions]

Coverage Report

File	Stmts	Miss	Cover	Missing
__init__.py	8	0	100%
data_io
SessionIOHandler.py	326	41	87%	111, 128–129, 173–174, 184–185, 215–216, 282–283, 286, 326–328, 370, 388–390, 455, 530, 553, 567–568, 570–571, 573–575, 719–724, 738, 742–743, 747–749
checkpoint_io.py	160	25	84%	68, 74, 76, 78, 95–109, 120, 122, 161, 182, 228, 308
find_images_in_folder.py	21	0	100%
load_images.py	91	28	69%	51–53, 58–60, 81, 93, 110, 140–147, 150, 156–157, 189, 248, 256, 277, 285, 292–294
metadata_handler.py	80	8	90%	70–71, 117, 122–123, 170–172
save_config.py	33	3	91%	92–94
datasets
AnomalyDetectionDataset.py	248	39	84%	126–127, 356, 362–363, 365, 369, 371–372, 374, 395–396, 398, 404–405, 409, 422–423, 484–485, 491–496, 498–499, 503–506, 508–510, 512–514, 525
BasicDataset.py	52	4	92%	59, 61, 97, 103
Label.py	5	0	100%
SSL_Dataset.py	68	3	96%	136, 139, 209
__init__.py	0	0	100%
data_utils.py	56	2	96%	80, 199
datasets/augmentation
randaugment.py	92	11	88%	222, 225–226, 245, 328–330, 332–335
randaugment_multispectral.py	77	23	70%	77–79, 120–121, 134–135, 148–149, 166, 170, 174, 248, 253, 270–272, 274–277, 280–281
image_processing
transforms.py	57	3	95%	46–47, 76
models
FixMatch.py	214	29	86%	108, 201–202, 217, 222, 254, 281–282, 285, 288–290, 293, 301, 306–307, 366, 404, 430–434, 495, 497–498, 502, 519–520
pipeline
SessionTracker.py	122	3	98%	127, 219–220
session.py	541	85	84%	146–149, 399–402, 447, 460, 612, 669, 671–672, 680, 683, 694, 702, 732, 736, 740–741, 745, 750–751, 758, 762–763, 775, 785–786, 788, 792, 806–807, 809–811, 813, 816–817, 875–876, 878–881, 883–887, 893, 899, 904–908, 910, 918, 921–922, 938, 979–980, 986–987, 991–993, 995, 1020, 1046, 1080–1081, 1089, 1100, 1108, 1112, 1116, 1121, 1124, 1168, 1171
utils
accuracy.py	13	0	100%
consistency_loss.py	18	0	100%
create_model_string.py	4	0	100%
cross_entropy_loss.py	9	0	100%
cutana_stream_utils.py	70	9	87%	64–65, 88, 108, 118–122
get_cosine_schedule_with_warmup.py	11	1	91%	39
get_default_cfg.py	61	0	100%
get_net_builder.py	55	7	87%	81–82, 89, 92, 170–171, 175
get_optimizer.py	21	2	90%	54, 58
print_cfg.py	45	4	91%	89, 95, 117, 119
set_log_level.py	15	0	100%
set_seeds.py	13	2	85%	25–26
validate_config.py	131	11	92%	180, 199, 214, 228, 244, 248, 264, 290, 379–381
TOTAL	2717	343	87%

Tests	Skipped	Failures	Errors	Time
377	0 💤	0 ❌	0 🔥	58.478s ⏱️