feat: add kernel completion verdict functions and response fields

Pure functions in types.py classify finish reasons, judge stream
completeness and outcome, and decide cacheability; TransportResult and
LLMResponse gain finish_reason and stream_end; snapshots accept
tool_calls null.

Red: tests/unit/test_completion_verdict.py failed at collection
(ImportError: _classify_finish et al. undefined) before this change.

src/polygateway/__init__.py

@@ -50,6 +50,7 @@ from polygateway.types import (
     OpenAIChatCompletion,
     ResponseMode,
     SourceConfig,
+    StreamEnd,
     TelemetryStatus,
     ThinkingObservation,
 )
@@ -73,6 +74,7 @@ __all__ = [
     "GovernanceBackendError",
     "LLMResponse",
     "ResponseMode",
+    "StreamEnd",
     "OpenAIChatCompletion",
     "ModelPrice",
     "OcrClient",