feat(evaluation): memoir readiness, judge/replay updates, eval web playground

Add memoir_readiness_service and router tests; extend judge schemas/services, replay_service, and conversation rubric; align story route agent, payload, prompts, and story_pipeline_sync; update agent logging, config, and DI. Document internal-eval; add replayDraft util and PlaygroundPage changes in app-eval-web.

api/tests/test_story_route_payload.py

@@ -127,6 +127,21 @@ def test_total_budget_downgrades_tail_rows(monkeypatch):
     assert any("preview" in row and "body_for_route" not in row for row in data)
 
 
+def test_opening_snippet_when_no_summary_but_body():
+    s = _story(
+        id="1",
+        summary="短",
+        canonical_markdown="我在山东潍坊长大，小时候常和伙伴在河边玩。"
+        * 2,
+    )
+    settings = Settings()
+    rows = build_route_candidate_rows(
+        [s], {"1": {"char_count": 80, "version_count": 1}}, settings
+    )
+    assert "opening_snippet" in rows[0]
+    assert "潍坊" in rows[0]["opening_snippet"]
+
+
 def test_json_includes_core_fields():
     s = _story(
         id="x1",