feat(telemetry): tell a ranker decline from a repeat before the observation window opens (#3497)

Making the rule arms log every call exposed a second ambiguity in the same
row. `result_count == 0` is two unrelated events wearing one number:

  - the ranker found nothing above the bar — the only evidence a threshold is
    set too high; and
  - the ranker found only what this session had already been shown — which
    says nothing whatever about the bar.

A long session excludes its way into the second, so the arm reads worse the
longer it runs correctly. Rows written now carry the ambiguity permanently,
which is why this lands before any watch period rather than after.

`retrieval_logs.suppressed_count` (0095, nullable) holds what the caller
dropped as already-shown. Both rule arms report it; they filter in Python and
always know. The note arms pass exclusions INTO semantic_search_notes and
never see what was dropped, so they store NULL.

THE NULL IS LOAD-BEARING. It means "not measured here", and the readout
renders it as `suppression: null` rather than a zeroed dict. Defaulting to 0
would let an unmeasured surface read as a perfectly clean one — the same
substitution of an artifact for a measurement that #3311 made. No backfill,
for the same reason: existing rows genuinely do not know.

`retrieval_telemetry`'s `sources` gains `suppression` with `measured_calls`,
`calls_with_suppression` and `zero_because_already_shown`; subtract the last
from `zero_result_calls` for the true ranker declines. The MCP tool docstring
says to read the two together and warns against reading the null as a zero.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_011cPyzNnegXHr5iRMzzy5KJ

src/scribe/services/plugin_context.py

@@ -1253,6 +1253,11 @@ async def build_write_path_hint(
             threshold=cfg["rule_threshold"], limit=RULEHINT_LIMIT,
             project_id=project_id,
             is_task=None, results=fresh, duration_ms=rule_ms,
+            # What the ranker found and this session had already been told.
+            # Without it a zero row cannot say whether the bar was too high or
+            # the reader was simply ahead of it — and only the first is a
+            # reason to move the threshold.
+            suppressed=len(hits) - len(fresh),
         )
         if fresh:
             # `rule_ids` is `fresh`, i.e. AFTER exclude_rule_ids. A rule the
@@ -1352,6 +1357,10 @@ async def build_tool_rule_hint(
             threshold=cfg["rule_threshold"], limit=RULEHINT_LIMIT,
             project_id=project_id,
             is_task=None, results=fresh, duration_ms=duration_ms,
+            # See the sibling arm. It matters more here: this arm fires on every
+            # Bash call, so a long session excludes its way to an all-zero row
+            # and the threshold looks wrong when nothing about it is.
+            suppressed=len(hits) - len(fresh),
         )
         if not fresh:
             return out

src/scribe/services/retrieval_telemetry.py

@@ -55,12 +55,18 @@ def _build_payload(
     is_task: bool | None,
     results: list[tuple[float, Note]],
     duration_ms: float | None,
+    suppressed: int | None = None,
 ) -> dict:
     """Reduce a retrieval call to a flat, JSON-safe RetrievalLog payload.
 
     Pure and synchronous (no DB, no event loop) so it is unit-testable and safe
     to run inline before scheduling the write. `results` is the
     `(score, Note)` list from semantic_search_notes, already highest-first.
+
+    `suppressed` is how many scored hits the caller dropped because the session
+    had already been shown them, and it stays None for callers that cannot
+    know. See the column's comment: None means "not measured here", which is a
+    different fact from 0 and must never render as one.
     """
     items = [
         {"id": int(note.id), "score": round(float(score), 5), "rank": rank}
@@ -76,6 +82,7 @@ def _build_payload(
         "project_id": project_id,
         "is_task": is_task,
         "result_count": len(items),
+        "suppressed_count": (None if suppressed is None else int(suppressed)),
         "top_score": (scores[0] if scores else None),
         "min_score": (scores[-1] if scores else None),
         "result_ids": items,
@@ -115,6 +122,7 @@ def record_retrieval(
     is_task: bool | None,
     results: list[tuple[float, Any]],
     duration_ms: float | None = None,
+    suppressed: int | None = None,
 ) -> None:
     """Fire-and-forget: record one retrieval call.
 
@@ -140,6 +148,7 @@ def record_retrieval(
             is_task=is_task,
             results=results,
             duration_ms=duration_ms,
+            suppressed=suppressed,
         )
     except Exception:
         logger.debug("retrieval telemetry payload build failed", exc_info=True)
@@ -166,7 +175,8 @@ def record_retrieval(
 
 def _bucket(rows: list) -> dict:
     """A score readout a human can act on, from one aggregate row."""
-    calls, zero, cleared, p10, p50, p90, lo, hi, avg_n, dur = rows
+    (calls, zero, cleared, p10, p50, p90, lo, hi, avg_n, dur,
+     measured, supp_calls, supp_zero) = rows
     return {
         "calls": int(calls or 0),
         # A call that returned nothing is not a low-scoring call — it is a
@@ -178,6 +188,22 @@ def _bucket(rows: list) -> dict:
         # bar on almost every call is either well-tuned or too loose, and the
         # score spread below says which.
         "cleared_threshold": int(cleared or 0),
+        # Of the zeros above, which were the RANKER declining and which were
+        # the reader having seen it already? `zero_result_calls` cannot say,
+        # and only the first kind is evidence about the threshold.
+        #
+        # None — not a zeroed dict — when no row in the window reported it. A
+        # surface that filters inside the search genuinely does not know, and
+        # rendering that as `{"calls": 0}` would state a measurement nobody
+        # made. That substitution is the whole of #3311.
+        "suppression": (
+            None if not int(measured or 0) else {
+                "measured_calls": int(measured or 0),
+                "calls_with_suppression": int(supp_calls or 0),
+                # Subtract from zero_result_calls for the true ranker declines.
+                "zero_because_already_shown": int(supp_zero or 0),
+            }
+        ),
         "top_score": {
             "p10": _round(p10), "p50": _round(p50), "p90": _round(p90),
             "min": _round(lo), "max": _round(hi),
@@ -240,6 +266,14 @@ async def retrieval_summary(user_id: int | None, *, days: int = 30) -> dict:
         else_=0,
     )
     zero = case((RetrievalLog.result_count == 0, 1), else_=0)
+    # Three sums rather than one, because "not measured" and "measured as zero"
+    # are different answers and a single counter cannot hold both.
+    measured = case((RetrievalLog.suppressed_count.isnot(None), 1), else_=0)
+    supp_calls = case((RetrievalLog.suppressed_count > 0, 1), else_=0)
+    supp_zero = case(
+        ((RetrievalLog.result_count == 0) & (RetrievalLog.suppressed_count > 0), 1),
+        else_=0,
+    )
 
     def pct(p: float):
         return func.percentile_cont(p).within_group(RetrievalLog.top_score.asc())
@@ -266,6 +300,9 @@ async def retrieval_summary(user_id: int | None, *, days: int = 30) -> dict:
                         func.percentile_cont(0.9).within_group(
                             RetrievalLog.duration_ms.asc()
                         ),
+                        func.sum(measured).label("measured"),
+                        func.sum(supp_calls).label("supp_calls"),
+                        func.sum(supp_zero).label("supp_zero"),
                     )
                     .where(
                         RetrievalLog.created_at >= since,