feat(api): 回忆录管线简化、路由延迟池与相关加固

- Phase1/2：移除 MemoirOrchestrator.run 与 process_memoir_segments 别名；文档改为 process_memoir_phase1。
- 槽位校验集中到 stage_constants（filter_stage_slots），批处理与顺序路径及 state_service 写库一致。
- StoryRoute：no_llm/parse_error/invalid_target 保守 new_story；短篇护栏不覆盖这些 fallback。
- Phase2 低置信单路径可选延迟（StoryPipelineResult.deferred）：不写 Chapter/Story，Segment 记录 defer 元数据，冷却内不重复消费；上限后停自动重试，Phase1 同类目新段唤醒池内段。
- Alembic 0017：segments 表 narrative_defer_* 列。
- ProfileAgent：经 LlmGateway/注入 Provider 统一聊天与 JSON，新增测试。
- ImagePromptOrchestrator：LLM 初始化失败可依配置降级或硬失败；补充策略测试。
- 配套单测与 README/本地开发文档表述更新。

Co-authored-by: Cursor <cursoragent@cursor.com>

api/alembic/versions/0017_segment_narrative_defer.py

@@ -0,0 +1,75 @@
+"""segments：Phase2 低置信路由延迟元数据
+
+Revision ID: 0017_segment_narrative_defer
+Revises: 0016_memory_pipeline_status
+"""
+
+from typing import Sequence, Union
+
+import sqlalchemy as sa
+
+from alembic import op
+
+revision: str = "0017_segment_narrative_defer"
+down_revision: Union[str, None] = "0016_memory_pipeline_status"
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def _column_names(table_name: str) -> set[str]:
+    bind = op.get_bind()
+    inspector = sa.inspect(bind)
+    return {column["name"] for column in inspector.get_columns(table_name)}
+
+
+def upgrade() -> None:
+    columns = _column_names("segments")
+    if "narrative_deferred_until" not in columns:
+        op.add_column(
+            "segments",
+            sa.Column(
+                "narrative_deferred_until",
+                sa.DateTime(timezone=True),
+                nullable=True,
+            ),
+        )
+    if "narrative_defer_count" not in columns:
+        op.add_column(
+            "segments",
+            sa.Column(
+                "narrative_defer_count",
+                sa.Integer(),
+                nullable=False,
+                server_default=sa.text("0"),
+            ),
+        )
+    if "narrative_defer_reason" not in columns:
+        op.add_column(
+            "segments",
+            sa.Column(
+                "narrative_defer_reason",
+                sa.String(),
+                nullable=True,
+            ),
+        )
+    if "narrative_last_attempt_at" not in columns:
+        op.add_column(
+            "segments",
+            sa.Column(
+                "narrative_last_attempt_at",
+                sa.DateTime(timezone=True),
+                nullable=True,
+            ),
+        )
+
+
+def downgrade() -> None:
+    columns = _column_names("segments")
+    for column in (
+        "narrative_last_attempt_at",
+        "narrative_defer_reason",
+        "narrative_defer_count",
+        "narrative_deferred_until",
+    ):
+        if column in columns:
+            op.drop_column("segments", column)