fix(lessons): build the rule-candidate query with trigger_title (#4631)

CI run 707 failed test_the_trigger_separator_is_spelled_in_exactly_one_place:
rule_candidates joined the lesson's claim and trigger with an inline " — ",
a second spelling of embeddings.TRIGGER_SEP (#3207). It now calls
trigger_title — the same join a rule's own document title is built with,
which was the point of the query shape in the first place.

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

src/scribe/services/lesson_rules.py

@@ -399,7 +399,7 @@ async def rule_candidates(
     """The rules a lesson most resembles, for the writer to judge against.
 
     Searched with the lesson's claim and its trigger — the same two halves a
-    rule's own document leads with (`{title} — {trigger}`), so like is
+    rule's own document leads with (`trigger_title`), so like is
     compared with like; the insight is the story and would dilute the vector.
     Scoped as any project read is: global rules plus the lesson's project's
     own. The bar is the explicit rule search's, since this is an explicit
@@ -409,10 +409,11 @@ async def rule_candidates(
     caller can say "candidates unavailable" rather than "nothing resembles".
     """
     from scribe.services.embeddings import (
-        DEFAULT_SIMILARITY_THRESHOLD, semantic_search_rules,
+        DEFAULT_SIMILARITY_THRESHOLD, semantic_search_rules, trigger_title,
     )
 
-    query = " — ".join(p for p in ((what or "").strip(), (when_to_apply or "").strip()) if p)
+    # The rule document's own title join, so like is compared with like.
+    query = trigger_title(what, when_to_apply)
     report: dict = {}
     found = await semantic_search_rules(
         user_id, query, limit=CANDIDATE_LIMIT,