Clarify average-vs-single-post ambiguity in campaign stage bullets

Mckinley flagged the July/August stage bullets as confusing. Two
separate problems: July's bullet conflated Carousel's 4-post average
with the 14/07-28/07-30/07 trilogy as if they were the same finding,
when the trilogy is mostly a Video story (only 30/07 was Carousel).
And "Carousel's single best post of the campaign (50.8%)" in August's
bullet left it ambiguous whether 50.8% was an average or one post's
score (it's one post, 04/08 - August only had a single Carousel that
month, nothing to average).

Rewrote both to be explicit: July's now separates the format-average
finding from the narrative-arc finding into two sentences, and spells
out the trilogy's actual formats (Video, Video, Carousel). August's
now says directly "the single Carousel this month (04/08) was the
campaign's single best post."

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

monthly_report_notes.py

@@ -414,12 +414,14 @@ NOTES = {
             ],
             "trilogy_intro": "Three stages, three different kinds of answer:",
             "trilogy_posts": [
-                "July — Find the Voice: Carousel's best average format (4 posts, "
-                "6.0%-45.0%), plus the 14/07-28/07-30/07 personal-voice trilogy",
+                "July — Find the Voice: Carousel averaged best across its 4 "
+                "posts this month (range 6.0%-45.0%). Separately, the 14/07-"
+                "28/07-30/07 trilogy (Video, Video, Carousel) worked as a "
+                "sequential narrative arc, independent of format.",
                 "August — Find the Audience: a clear demographic answer "
                 "(Academia/Research, Germany, Researcher/Scientist), the "
-                "6-post TXServices launch arc, and Carousel's single best post "
-                "of the campaign (50.8%)",
+                "6-post TXServices launch arc, and the single Carousel this "
+                "month (04/08) was the campaign's single best post at 50.8%",
                 "September — Find the Trigger: one real trigger found (08/09's "
                 "pain-point post, beating even the month's own Carousel, 10.0%), "
                 "but not repeated — growth and engagement both decelerated",