test(M00): add checkpoint perceptual comparison
Work-Package: M00-QAR-VISUAL-DIFF-001 Agent: sindo-main-codex Tests: synthetic visual diff, M00 dry-run, coordination and documentation gates Fidelity: automates paired metrics; approved 3.3.5a captures and human approval remain required
This commit is contained in:
@@ -0,0 +1,209 @@
|
||||
extends SceneTree
|
||||
|
||||
## Compares paired PNG checkpoint directories without storing proprietary reference images.
|
||||
## Usage: godot --headless --path . --script res://src/tools/compare_render_checkpoints.gd --
|
||||
## --reference <directory> --candidate <directory> [--output <report.json>]
|
||||
## [--pixel-threshold 0.04] [--mean-threshold 0.015] [--changed-ratio-threshold 0.01]
|
||||
## Use --self-test for a synthetic regression check that writes only under user://.
|
||||
|
||||
const REPORT_SCHEMA_VERSION := 1
|
||||
const DEFAULT_PIXEL_THRESHOLD := 0.04
|
||||
const DEFAULT_MEAN_THRESHOLD := 0.015
|
||||
const DEFAULT_CHANGED_RATIO_THRESHOLD := 0.01
|
||||
|
||||
|
||||
func _initialize() -> void:
|
||||
var arguments := _parse_arguments(OS.get_cmdline_user_args())
|
||||
if arguments.has("error"):
|
||||
push_error("RENDER_CHECKPOINT_DIFF: %s" % arguments.error)
|
||||
quit(2)
|
||||
return
|
||||
if arguments.get("self_test", false):
|
||||
quit(_run_self_test())
|
||||
return
|
||||
|
||||
var reference_directory := String(arguments.get("reference", ""))
|
||||
var candidate_directory := String(arguments.get("candidate", ""))
|
||||
if reference_directory.is_empty() or candidate_directory.is_empty():
|
||||
push_error("RENDER_CHECKPOINT_DIFF: --reference and --candidate are required")
|
||||
quit(2)
|
||||
return
|
||||
|
||||
var report := _compare_directories(reference_directory, candidate_directory, arguments)
|
||||
var output_path := String(arguments.get("output", ""))
|
||||
if not output_path.is_empty() and not _write_report(output_path, report):
|
||||
quit(2)
|
||||
return
|
||||
print("RENDER_CHECKPOINT_DIFF %s compared=%d failed=%d missing=%d" % [
|
||||
"PASS" if report.passed else "FAIL",
|
||||
report.compared_count,
|
||||
report.failed_count,
|
||||
report.missing_count,
|
||||
])
|
||||
quit(0 if report.passed else 1)
|
||||
|
||||
|
||||
func _parse_arguments(raw_arguments: PackedStringArray) -> Dictionary:
|
||||
var parsed := {
|
||||
"pixel_threshold": DEFAULT_PIXEL_THRESHOLD,
|
||||
"mean_threshold": DEFAULT_MEAN_THRESHOLD,
|
||||
"changed_ratio_threshold": DEFAULT_CHANGED_RATIO_THRESHOLD,
|
||||
}
|
||||
var index := 0
|
||||
while index < raw_arguments.size():
|
||||
var argument := raw_arguments[index]
|
||||
if argument == "--self-test":
|
||||
parsed.self_test = true
|
||||
index += 1
|
||||
continue
|
||||
if argument not in ["--reference", "--candidate", "--output", "--pixel-threshold", "--mean-threshold", "--changed-ratio-threshold"]:
|
||||
return {"error": "unknown argument: %s" % argument}
|
||||
if index + 1 >= raw_arguments.size():
|
||||
return {"error": "missing value for %s" % argument}
|
||||
var key := argument.trim_prefix("--").replace("-", "_")
|
||||
var value := raw_arguments[index + 1]
|
||||
if key.ends_with("threshold"):
|
||||
if not value.is_valid_float():
|
||||
return {"error": "%s requires a number" % argument}
|
||||
parsed[key] = float(value)
|
||||
else:
|
||||
parsed[key] = value
|
||||
index += 2
|
||||
return parsed
|
||||
|
||||
|
||||
func _compare_directories(reference_directory: String, candidate_directory: String, options: Dictionary) -> Dictionary:
|
||||
var reference_files := _png_file_names(reference_directory)
|
||||
var results: Array[Dictionary] = []
|
||||
var failed_count := 0
|
||||
var missing_count := 0
|
||||
for file_name in reference_files:
|
||||
var reference_path := reference_directory.path_join(file_name)
|
||||
var candidate_path := candidate_directory.path_join(file_name)
|
||||
if not FileAccess.file_exists(candidate_path):
|
||||
results.append({"name": file_name, "status": "missing_candidate"})
|
||||
missing_count += 1
|
||||
continue
|
||||
var comparison := _compare_images(reference_path, candidate_path, options)
|
||||
comparison.name = file_name
|
||||
results.append(comparison)
|
||||
if comparison.status != "passed":
|
||||
failed_count += 1
|
||||
var no_reference_images := reference_files.is_empty()
|
||||
return {
|
||||
"schema_version": REPORT_SCHEMA_VERSION,
|
||||
"passed": not no_reference_images and failed_count == 0 and missing_count == 0,
|
||||
"reference_directory": reference_directory,
|
||||
"candidate_directory": candidate_directory,
|
||||
"pixel_threshold": options.pixel_threshold,
|
||||
"mean_threshold": options.mean_threshold,
|
||||
"changed_ratio_threshold": options.changed_ratio_threshold,
|
||||
"compared_count": results.size() - missing_count,
|
||||
"failed_count": failed_count,
|
||||
"missing_count": missing_count,
|
||||
"no_reference_images": no_reference_images,
|
||||
"results": results,
|
||||
}
|
||||
|
||||
|
||||
func _compare_images(reference_path: String, candidate_path: String, options: Dictionary) -> Dictionary:
|
||||
var reference_image := Image.load_from_file(reference_path)
|
||||
var candidate_image := Image.load_from_file(candidate_path)
|
||||
if reference_image == null or candidate_image == null or reference_image.is_empty() or candidate_image.is_empty():
|
||||
return {"status": "load_error"}
|
||||
if reference_image.get_size() != candidate_image.get_size():
|
||||
return {
|
||||
"status": "size_mismatch",
|
||||
"reference_size": [reference_image.get_width(), reference_image.get_height()],
|
||||
"candidate_size": [candidate_image.get_width(), candidate_image.get_height()],
|
||||
}
|
||||
|
||||
var error_sum := 0.0
|
||||
var changed_pixel_count := 0
|
||||
var pixel_count := reference_image.get_width() * reference_image.get_height()
|
||||
for y in reference_image.get_height():
|
||||
for x in reference_image.get_width():
|
||||
var perceptual_error := _perceptual_color_error(reference_image.get_pixel(x, y), candidate_image.get_pixel(x, y))
|
||||
error_sum += perceptual_error
|
||||
if perceptual_error > float(options.pixel_threshold):
|
||||
changed_pixel_count += 1
|
||||
var mean_perceptual_error := error_sum / float(pixel_count)
|
||||
var changed_pixel_ratio := float(changed_pixel_count) / float(pixel_count)
|
||||
var passed := mean_perceptual_error <= float(options.mean_threshold) and changed_pixel_ratio <= float(options.changed_ratio_threshold)
|
||||
return {
|
||||
"status": "passed" if passed else "threshold_exceeded",
|
||||
"width": reference_image.get_width(),
|
||||
"height": reference_image.get_height(),
|
||||
"mean_perceptual_error": mean_perceptual_error,
|
||||
"changed_pixel_ratio": changed_pixel_ratio,
|
||||
}
|
||||
|
||||
|
||||
func _perceptual_color_error(reference_color: Color, candidate_color: Color) -> float:
|
||||
var reference_linear := reference_color.srgb_to_linear()
|
||||
var candidate_linear := candidate_color.srgb_to_linear()
|
||||
var red_delta := absf(reference_linear.r - candidate_linear.r)
|
||||
var green_delta := absf(reference_linear.g - candidate_linear.g)
|
||||
var blue_delta := absf(reference_linear.b - candidate_linear.b)
|
||||
var alpha_delta := absf(reference_linear.a - candidate_linear.a)
|
||||
return 0.2126 * red_delta + 0.7152 * green_delta + 0.0722 * blue_delta + 0.25 * alpha_delta
|
||||
|
||||
|
||||
func _png_file_names(directory_path: String) -> Array[String]:
|
||||
var directory := DirAccess.open(directory_path)
|
||||
if directory == null:
|
||||
return []
|
||||
var file_names: Array[String] = []
|
||||
for file_name in directory.get_files():
|
||||
if file_name.to_lower().ends_with(".png"):
|
||||
file_names.append(file_name)
|
||||
file_names.sort()
|
||||
return file_names
|
||||
|
||||
|
||||
func _write_report(output_path: String, report: Dictionary) -> bool:
|
||||
var absolute_path := ProjectSettings.globalize_path(output_path)
|
||||
var error := DirAccess.make_dir_recursive_absolute(absolute_path.get_base_dir())
|
||||
if error != OK:
|
||||
push_error("RENDER_CHECKPOINT_DIFF: cannot create report directory: %s" % error_string(error))
|
||||
return false
|
||||
var report_file := FileAccess.open(absolute_path, FileAccess.WRITE)
|
||||
if report_file == null:
|
||||
push_error("RENDER_CHECKPOINT_DIFF: cannot write report: %s" % output_path)
|
||||
return false
|
||||
report_file.store_string(JSON.stringify(report, " "))
|
||||
return true
|
||||
|
||||
|
||||
func _run_self_test() -> int:
|
||||
var root := "user://render_checkpoint_diff_self_test"
|
||||
var reference_directory := root.path_join("reference")
|
||||
var identical_directory := root.path_join("identical")
|
||||
var changed_directory := root.path_join("changed")
|
||||
for directory_path in [reference_directory, identical_directory, changed_directory]:
|
||||
DirAccess.make_dir_recursive_absolute(ProjectSettings.globalize_path(directory_path))
|
||||
var reference_image := Image.create(2, 2, false, Image.FORMAT_RGBA8)
|
||||
reference_image.fill(Color(0.25, 0.5, 0.75, 1.0))
|
||||
var changed_image := reference_image.duplicate()
|
||||
changed_image.set_pixel(0, 0, Color.WHITE)
|
||||
for pair in [
|
||||
[reference_directory, reference_image],
|
||||
[identical_directory, reference_image],
|
||||
[changed_directory, changed_image],
|
||||
]:
|
||||
var save_error: Error = pair[1].save_png(String(pair[0]).path_join("synthetic.png"))
|
||||
if save_error != OK:
|
||||
push_error("RENDER_CHECKPOINT_DIFF SELF_TEST: cannot save fixture")
|
||||
return 1
|
||||
var options := {
|
||||
"pixel_threshold": DEFAULT_PIXEL_THRESHOLD,
|
||||
"mean_threshold": DEFAULT_MEAN_THRESHOLD,
|
||||
"changed_ratio_threshold": DEFAULT_CHANGED_RATIO_THRESHOLD,
|
||||
}
|
||||
var identical_report := _compare_directories(reference_directory, identical_directory, options)
|
||||
var changed_report := _compare_directories(reference_directory, changed_directory, options)
|
||||
if not identical_report.passed or changed_report.passed:
|
||||
push_error("RENDER_CHECKPOINT_DIFF SELF_TEST: expected identical pass and changed failure")
|
||||
return 1
|
||||
print("RENDER_CHECKPOINT_DIFF SELF_TEST PASS")
|
||||
return 0
|
||||
@@ -14,7 +14,10 @@
|
||||
"max_hitch_ms_max_regression_percent": 10.0,
|
||||
"load_time_ms_max_regression_percent": 10.0,
|
||||
"memory_bytes_max_regression_percent": 10.0,
|
||||
"visual_diff": "perceptual comparison required; exact PNG hashes are evidence, not an animated-scene pass criterion"
|
||||
"visual_mean_perceptual_error_max": 0.015,
|
||||
"visual_changed_pixel_ratio_max": 0.01,
|
||||
"visual_pixel_error_threshold": 0.04,
|
||||
"visual_diff": "automated thresholds require human approval; exact PNG hashes are evidence, not an animated-scene pass criterion"
|
||||
},
|
||||
"required_coverage": [
|
||||
"terrain",
|
||||
|
||||
@@ -42,6 +42,11 @@ func _initialize() -> void:
|
||||
var required := String(required_variant)
|
||||
_expect(covered.has(required), "missing checkpoint coverage: %s" % required, failures)
|
||||
|
||||
var comparison_budgets: Dictionary = manifest.get("comparison_budgets", {})
|
||||
for threshold_name in ["visual_mean_perceptual_error_max", "visual_changed_pixel_ratio_max", "visual_pixel_error_threshold"]:
|
||||
var threshold := float(comparison_budgets.get(threshold_name, -1.0))
|
||||
_expect(threshold >= 0.0 and threshold <= 1.0, "%s must be between 0 and 1" % threshold_name, failures)
|
||||
|
||||
var contract: Dictionary = manifest.get("cache_contract", {})
|
||||
var actual_versions := {
|
||||
"baked_terrain": STREAMING_LOADER.REQUIRED_BAKED_TILE_FORMAT_VERSION,
|
||||
|
||||
Reference in New Issue
Block a user