diff --git a/awareness.el b/awareness.el
index 9eed32c..6c69745 100644
--- a/awareness.el
+++ b/awareness.el
@@ -54,6 +54,21 @@ fn ise_post(content: String) -> Void {
         let fail_raw: String = state_get("soul.ise_fail_count")
         let fail_n: Int = if str_eq(fail_raw, "") { 0 } else { str_to_int(fail_raw) }
         state_set("soul.ise_fail_count", int_to_str(fail_n + 1))
+        // el_from_float on a LITERAL is correct and is NOT the double-wrap bug
+        // (checked and dismissed 2026-08-02 self-review — recording the result
+        // so this call site is not "fixed" again by the next reader).
+        // The compiler treats el_from_float as the boxing intrinsic: both
+        // `el_from_float(0.3)` and a bare `0.3` emit exactly one
+        // el_from_float(0.3) in dist/awareness.c. Verified byte-identical
+        // codegen either way.
+        // The real bug fixed in server.el on 2026-08-01 was different: there
+        // the arguments came from json_get_float(), i.e. values ALREADY boxed
+        // as el_val_t. Wrapping THOSE a second time reinterprets the boxed
+        // bits as a raw double, fails engram_decode_score's range check, and
+        // silently clamps to defaults.
+        // The sweep criterion is therefore "el_from_float applied to an
+        // already-boxed expression", never "el_from_float applied to a
+        // literal". Grepping for the call name alone produces false positives.
         let discard: String = engram_node_full(
             content, "InternalStateEvent", "state-event",
             el_from_float(0.3), el_from_float(0.3), el_from_float(0.8),