Delegate wearer boundary semantics to review

easycom_event_taxonomy.py

@@ -0,0 +1,44 @@
+"""Closed vocabularies shared by EasyCom event pre-label and review tools."""
+
+from __future__ import annotations
+
+
+EXCLUDE_REASONS = {
+    "OUT_OF_SCOPE_NORMAL_COMPLETION",
+    "OUT_OF_SCOPE_WITHIN_TURN_CONTINUATION",
+    "OUT_OF_SCOPE_POST_COMPLETION_ACTIVITY",
+    "OUT_OF_SCOPE_NON_EVENT",
+    "INSUFFICIENT_EVIDENCE",
+    "DATA_ANNOTATION_ERROR",
+    "DATA_RECORDING_BOUNDARY",
+    "DATA_MISSING_CONTEXT",
+    "DATA_NON_SPEECH_ARTIFACT",
+    "DATA_TIMESTAMP_CORRUPTION",
+}
+
+# Accepted only when loading or editing old review records. New DeepSeek and UI
+# outputs use the prefixed taxonomy above so scope and data-quality counts are
+# never silently combined.
+LEGACY_EXCLUDE_REASONS = {
+    "ANNOTATION_ERROR",
+    "RECORDING_BOUNDARY",
+    "MISSING_CONTEXT",
+    "NON_SPEECH_ARTIFACT",
+    "TIMESTAMP_CORRUPTION",
+    "UNRESOLVABLE",
+}
+
+
+def exclude_reason_group(reason: str | None) -> str | None:
+    """Map a leaf reason to a stable aggregation group."""
+    if reason is None:
+        return None
+    if reason.startswith("OUT_OF_SCOPE_"):
+        return "OUT_OF_SCOPE"
+    if reason == "INSUFFICIENT_EVIDENCE":
+        return "INSUFFICIENT_EVIDENCE"
+    if reason.startswith("DATA_"):
+        return "DATA_QUALITY"
+    if reason in LEGACY_EXCLUDE_REASONS:
+        return "LEGACY_UNSPECIFIED"
+    return "UNKNOWN"