perf(retrieval): one embedding per query per plugin request (milestone 456 step 1, #4903)

A single plugin request fans one query out to several ranked arms. The
operator message is searched by auto_inject, its reuse and lesson slots,
prompt_rule, the preference slot and rule_via_lesson, and each arm called
get_embedding on its own: up to six model calls for one vector.

- embeddings.query_embedding_memo(): a request-scoped ContextVar memo that
  get_embedding consults. Outside a scope the default is None, so every
  other caller is unchanged. A failed embedding is not remembered.
- memoized_query_embeddings decorates /retrieve, /tool-rules and
  /prior-art.
- get_embeddings (document chunks) is untouched.

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

src/scribe/routes/plugin.py

@@ -18,6 +18,7 @@ from scribe.services import repo_bindings as repo_bindings_svc
 from scribe.services import report_check as report_check_svc
 from scribe.services import shape_check as shape_check_svc
 from scribe.services import task_claims as task_claims_svc
+from scribe.services.embeddings import memoized_query_embeddings
 from scribe.services.settings import get_admin_setting, set_setting
 
 plugin_bp = Blueprint("plugin", __name__, url_prefix="/api/plugin")
@@ -88,6 +89,7 @@ async def session_context():
 
 @plugin_bp.get("/retrieve")
 @login_required
+@memoized_query_embeddings
 async def autoinject_retrieve():
     """Title-first knowledge auto-inject for the plugin's UserPromptSubmit hook.
 
@@ -163,6 +165,7 @@ async def autoinject_retrieve():
 
 @plugin_bp.get("/tool-rules")
 @login_required
+@memoized_query_embeddings
 async def pre_tool_rules():
     """Standing rules for the plugin's PreToolUse hook on ACTIONS (#3476).
 
@@ -240,6 +243,7 @@ async def pre_tool_rules():
 
 @plugin_bp.get("/prior-art")
 @login_required
+@memoized_query_embeddings
 async def write_path_prior_art():
     """Prior-art hint for the plugin's PreToolUse hook on Write/Edit.