feat(eval): server-side replay/phase1 timing + memoir phase1 batch chunking

- Replay and memoir-submit responses include started/finished UTC and elapsed_ms;
  Phase1 poll exposes Redis-backed submit time and elapsed_ms_since_submit.
- Phase1 batch LLM splits segments by memoir_phase1_batch_llm_chunk_size with
  bisect fallback per chunk; Playground shows server timings.

Made-with: Cursor

api/app/agents/memoir/orchestrator.py

@@ -12,7 +12,7 @@ from typing import Any, Callable, Dict, List, Set, Tuple
 
 from app.agents.memoir.batch_phase1_prep import (
     STAGE_ALLOWED_SLOTS,
-    run_batch_phase1_prep,
+    run_batch_phase1_prep_chunked,
 )
 from app.agents.memoir.classification_agent import (
     ClassificationAgent,
@@ -177,7 +177,12 @@ class MemoirOrchestrator:
         segment_skip_story_ids: Set[str] = set()
         segment_chapter_category: Dict[str, str] = {}
 
-        by_id = run_batch_phase1_prep(segments, state, classify_extract_llm)
+        by_id = run_batch_phase1_prep_chunked(
+            segments,
+            state,
+            classify_extract_llm,
+            chunk_size=int(settings.memoir_phase1_batch_llm_chunk_size),
+        )
 
         for segment in segments:
             text = segment.user_input_text or ""