feat(retrieval): a review pass judges whether injected lines related — menus_to_review, judge_menu and a judged readout (#4772)

An open rate cannot say whether a menu line related: every line carries its
matched passage (#4364), so "not opened" covers unrelated, enough as shown,
and already in context. #4772 "Injected notes are never judged".

- retrieval_judgments (0115): a reviewer verdict per line of a logged call,
  on_point / adjacent / unrelated, with its reason, rank, budget side and
  whether the agent opened it within the hour.
- menus_to_review re-runs a random sample of unjudged auto_inject calls with
  the arm's own parameters, past its budget, passage on every line.
  judge_menu records verdicts, re-deriving rank from a fresh re-run.
- retrieval_telemetry gains a judged block (by rank, within/beyond budget,
  on_point_unopened). surfaced_never_pulled stops blaming titles.
- missed-retrieval guidance names the review before a budget move.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

src/scribe/services/backup.py

@@ -159,6 +159,10 @@ _NOT_INCLUDED = [
     "app_logs", "notifications",
     "invitation_tokens", "password_reset_tokens", "user_profiles",
     "retrieval_logs",
+    # Verdicts on retrieval_logs rows (#4772), so they go where their subject
+    # goes: a restore that carried a judgment of a call it did not carry would
+    # leave a verdict on nothing. A sample, re-takeable by the review pass.
+    "retrieval_judgments",
     # Sensitive credentials, same reasoning as api_keys: a backup that carries
     # forge tokens is a token-exfiltration file. Users re-add connections
     # after a restore; the per-project pin (projects.forge_connection_id) is