The luminex CSV files contain corrupted micro (µ) symbols that were replaced
with UTF-8 replacement characters. When parsed with ISO-8859-1 (via chardet),
these got incorrectly displayed as '�'. With the UTF-8 optimization, we now
correctly get '�' instead.

Updated the expected JSON files to reflect the correct encoding behavior.

Similar to the previous luminex fix, the CSV file contains a registered
trademark symbol (®) that was incorrectly displayed as '®' when parsed
with ISO-8859-1. With UTF-8 parsing, we now correctly get '®'.

- AppBio QuantStudio example01.txt: 3.5MB → 7KB (99.8% reduction)
- Biorad Bioplex example01.xml: 6.0MB → 1.9MB (68.4% reduction)

Reduces test execution time while maintaining full test coverage.
All tests passing with regenerated output files.

Successfully optimized:
- appbio_quantstudio_example05.txt: 228KB → 5KB (97.9% reduction)
- appbio_quantstudio_example07.txt: 284KB → 6KB (97.9% reduction)

Total files optimized so far: 4
All tests passing with regenerated output files.

Test suite improvement: 1.1x faster (10.8% reduction)
- Baseline: 341 seconds
- Optimized: 304 seconds
- 37 seconds saved

4 files optimized with 68-99% size reductions
All tests passing ✅

AppBio QuantStudio:
- example02.txt: 717KB → 54KB (92.5% reduction)
- example03.txt: 302KB → 40KB (86.7% reduction)
- example04.txt: 124KB → 28KB (77.2% reduction)

MolDev SoftMax Pro:
- partial_plate_with_empty_values.txt: 226KB → 7KB (96.8% reduction)
- ACSINS_absorbance_timeformat_spectrum.txt: 223KB → 79KB (64.7% reduction)

Agilent:
- TapeStation example_01.xml: 161KB → 18KB (89.0% reduction)
- Gen5 kinetic_helper_gene_growth_curve.txt: 120KB → 7KB (93.8% reduction)

Roche CEDEX BioHT:
- example03.txt: 104KB → 103KB (minimal change)

Preserves test coverage while significantly reducing CI execution time.

Co-Authored-By: Claude Opus 4.1 <noreply@anthropic.com>

Luminex xPONENT:
- NaN_and_not_reported_values.csv: 44KB → 3KB (92.1% reduction)

Roche CEDEX HiRes:
- example_3.csv: 40KB → 4KB (89.7% reduction)

Removed JSON outputs for affected files to be regenerated on next test run.

Co-Authored-By: Claude Opus 4.1 <noreply@anthropic.com>

Deleted JSON outputs from previous batches that will be regenerated
when tests are run with the optimized input files.

Co-Authored-By: Claude Opus 4.1 <noreply@anthropic.com>

Reverted 3 files that caused test failures:
- luminex_xPONENT_NaN_and_not_reported_values.csv
- ACSINS_absorbance_timeformat_spectrum.txt
- partial_plate_with_empty_values.txt

These files have complex formatting requirements that were broken
by the optimization. Restoring to original versions.

Co-Authored-By: Claude Opus 4.1 <noreply@anthropic.com>

- Reduced from 7 tubes to 3 tubes (keeping test coverage)
- Simplified polygon points in gate regions (max 5 points per polygon)
- File lines reduced from 11,629 to 7,965
- Test passes with optimized data

Co-Authored-By: Claude Opus 4.1 <noreply@anthropic.com>

- Reduced from 16 samples to 6 samples (keeping test coverage)
- File lines reduced from ~1500 to 767
- Test passes with optimized data

Co-Authored-By: Claude Opus 4.1 <noreply@anthropic.com>

…: 38KB → 16KB (58% reduction)

- Reduced from 16 rows (A-P) to 6 rows (A-F) per data section
- Kept 144 wells instead of 384 wells (maintaining test coverage)
- File lines reduced from 240 to 160
- Test passes with optimized data

Co-Authored-By: Claude Opus 4.1 <noreply@anthropic.com>

…: 43KB → 18KB (58% reduction)

- Reduced from 16 rows (A-P) to 6 rows (A-F) per data section
- Kept 144 wells instead of 384 wells (maintaining test coverage)
- File lines reduced from 260 to 170
- Test passes with optimized data

Co-Authored-By: Claude Opus 4.1 <noreply@anthropic.com>

- Reduced from 16 samples to 5 samples (A1, A2, B1, C1, D1)
- Maintains diversity of test data across all rows
- File lines reduced from 257 to 81
- Test passes with optimized data

Co-Authored-By: Claude Opus 4.1 <noreply@anthropic.com>

…: 23KB → 10KB (57% reduction)

- Reduced from 16 rows (A-P) to 6 rows (A-F) per data section
- Kept 144 wells instead of 384 wells (maintaining test coverage)
- File lines reduced from 157 to 117
- Test passes with optimized data

Co-Authored-By: Claude Opus 4.1 <noreply@anthropic.com>

… 38KB → 11KB (71% reduction)

- Reduced kinetic time points from 61 to 13 (keeping every 5th point)
- Maintains kinetic profile for testing purposes
- File lines reduced from 134 to 86
- Test passes with optimized data

Co-Authored-By: Claude Opus 4.1 <noreply@anthropic.com>

- Reduced ladder sample peaks from 14 to 5
- Kept all peaks for other samples (3 each)
- File lines reduced from 766 to 586
- Test passes with optimized data

Co-Authored-By: Claude Opus 4.1 <noreply@anthropic.com>

…ction)

- Reduced wavelength points from 41 to 14 (keeping every 3rd point)
- Maintains spectral profile with NaN and OVRFLW values
- File lines reduced from 82 to 55
- Test passes with optimized data

Co-Authored-By: Claude Opus 4.1 <noreply@anthropic.com>

…KB → 10KB (60% reduction)

- Reduced wavelength points from 41 to 14 (keeping every 3rd point)
- Maintains spectral profile for testing
- File lines reduced from 85 to 58
- Test passes with optimized data

Co-Authored-By: Claude Opus 4.1 <noreply@anthropic.com>

…(70% reduction)

MAJOR PERFORMANCE IMPROVEMENT:
- Test runtime reduced from 1.75s to 0.60s (66% faster!)
- Reduced from 93 wells to 24 wells
- File lines reduced from 112 to 43
- One of the slowest tests now runs much faster

Co-Authored-By: Claude Opus 4.1 <noreply@anthropic.com>

…peedup)

- Reduced tubes from 7 to 3
- Simplified polygon points in gates (max 5 points)
- File size: 1.4MB → 690KB
- Test time: 2.19s → 1.03s (53% improvement)

Co-authored-by: Claude <assistant@anthropic.com>

- Kept every 3rd wavelength point (14 of 41)
- File size: 2.8KB → 2.4KB
- Test time: stable at ~0.74s

Co-authored-by: Claude <assistant@anthropic.com>

- Reduced wells from 93 to 24
- File size: 19KB (unchanged but less data)
- Test time: 1.75s → 0.73s (58% improvement)

Co-authored-by: Claude <assistant@anthropic.com>

- Reduced from 8 well rows (A-H) to 4 (A-D)
- File size: 21KB → 13KB
- Test time: 3.41s → 1.85s (46% improvement)

Co-authored-by: Claude <assistant@anthropic.com>

- Reduced samples from 6 to 3
- File size: 25KB → 16.5KB (34% reduction)
- Test time: ~1.37s

Co-authored-by: Claude <assistant@anthropic.com>

- Reduced from 96 to 24 wells (for both fluorophores)
- File size: 13KB → 2.5KB (81% reduction)
- Test time: ~0.38s

Co-authored-by: Claude <assistant@anthropic.com>

- Schema generation test only runs when relevant files change
- Saves ~3 minutes per Python version (9+ minutes total) for most PRs
- Always runs on main branch to ensure consistency
- Reduces timeout from 15 to 10 minutes for regular tests

The schema generation test accounts for 35% of test suite time but is only
needed when schemas or generation code changes.

Co-Authored-By: Claude Opus 4.1 <noreply@anthropic.com>