feat: modernize PSO and add convergence research

Migrate the package and examples to the tensor-native PyTorch implementation, add benchmark evidence, and add the guarded post-training convergence protocol with TensorBoard progress monitoring and hash-verified recovery.

Constraint: Preserve one-shot official-test sealing and auditable research artifacts

Rejected: Commit local .omc runs and downloaded datasets | multi-gigabyte runtime state is machine-local

Confidence: high

Scope-risk: broad

Not-tested: Production CUDA run on pieroot-server

pso/__init__.py

@@ -1,22 +1,29 @@
-import tensorflow as tf
-import os
-from .optimizer import Optimizer as optimizer
-from .particle import Particle as particle
-
-__version__ = "1.0.5.1"
-
-print("pso2keras version : " + __version__)
-
-gpus = tf.config.experimental.list_physical_devices("GPU")
-if gpus:
-    try:
-        tf.config.experimental.set_memory_growth(gpus[0], True)
-    except RuntimeError as r:
-        print(r)
-
-os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"
+from ._version import __version__
+from .optimizer import Optimizer
+from .particle import Particle
+from .plugins import (
+    BasePlugin,
+    InitializationPlugin,
+    EvaluationPlugin,
+    MovementPlugin,
+    ConvergencePlugin,
+    RefinementPlugin,
+    PluginMetadata,
+    SwarmState,
+    available_plugins,
+)
 
 __all__ = [
-    "optimizer",
-    "particle",
+    "Optimizer",
+    "Particle",
+    "__version__",
+    "BasePlugin",
+    "InitializationPlugin",
+    "EvaluationPlugin",
+    "MovementPlugin",
+    "ConvergencePlugin",
+    "RefinementPlugin",
+    "PluginMetadata",
+    "SwarmState",
+    "available_plugins",
 ]