fix(retrieval): the newest two rows are not the newest row of each dial (#4104)

`current_settings` read a surface's history with one query and `limit(2)`, then
keyed the rows by dial. That is only the same thing while both dials have moved
equally often — and they do not. Floors get walked; budgets rarely move. Three
floor changes and one budget change returns two floor rows, and the budget
change vanishes.

Under #4102 that cost a missing reason. Since #4104 it is worse: the dial then
reports `source: "shipped"` — still on the value Scribe shipped — for a number
somebody deliberately tuned. A wrong calibration answer, in the direction a
reader has no cause to double-check.

One query per dial, `limit(1)` each.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01821k5B3Ysecp9fNYs92Kuy

src/scribe/services/retrieval_tuning.py

@@ -153,18 +153,30 @@ async def current_settings(user_id: int) -> list[dict]:
     async with async_session() as session:
         for name in surface_names():
             s = get_surface(name)
-            rows = (
-                await session.execute(
-                    select(RetrievalTuningEvent)
-                    .where(
-                        RetrievalTuningEvent.surface == name,
-                        RetrievalTuningEvent.user_id == user_id,
+            # ONE QUERY PER DIAL, not one `limit(len(DIALS))` over both.
+            # "The newest two rows" is not "the newest row of each kind": a
+            # surface whose floor was moved three times and whose budget was
+            # moved once returns two floor rows, and the budget change
+            # disappears. That was a missing reason when this only fed
+            # `last_change`; since #4104 it is also a WRONG calibration answer —
+            # a tuned dial reporting as "still on the shipped default", which is
+            # the one state a reader would not think to check.
+            last = {}
+            for dial in DIALS:
+                row = (
+                    await session.execute(
+                        select(RetrievalTuningEvent)
+                        .where(
+                            RetrievalTuningEvent.surface == name,
+                            RetrievalTuningEvent.user_id == user_id,
+                            RetrievalTuningEvent.dial == dial,
+                        )
+                        .order_by(RetrievalTuningEvent.created_at.desc())
+                        .limit(1)
                     )
-                    .order_by(RetrievalTuningEvent.created_at.desc())
-                    .limit(len(DIALS))
-                )
-            ).scalars().all()
-            last = {r.dial: r for r in rows}
+                ).scalars().first()
+                if row is not None:
+                    last[dial] = row
             out.append({
                 "surface": name,
                 "floor": await floor_for(user_id, name),