feat(dream): add memory dream cli and docs

- New memory/deep-dream.mdx (zh/en/ja): memory flow, distillation rules, dream diary, manual trigger, safety mechanisms
- Simplify long-term memory page, link to deep-dream for details
- New cli/memory-knowledge.mdx (zh/en/ja): memory and knowledge commands
- Move knowledge commands from general.mdx to memory-knowledge.mdx
- Register new pages in docs.json navigation for all languages
- Add /memory dream to cli/index.mdx command tables

agent/memory/summarizer.py

@@ -42,7 +42,7 @@ DREAM_SYSTEM_PROMPT = """你是一个记忆整理助手，负责定期整理用
 1. **当前长期记忆** — MEMORY.md 的全部现有内容
 2. **今日日记** — 当天的日常记录
 
-MEMORY.md 会注入每次对话的系统提示词中，因此必须保持精炼。
+MEMORY.md 会注入每次对话的系统提示词中，因此必须保持精炼，只存放有价值和值得记忆的内容。
 
 **重要：只能基于提供的材料进行整理，严禁编造、推测或添加材料中不存在的信息。**
 
@@ -52,12 +52,12 @@ MEMORY.md 会注入每次对话的系统提示词中，因此必须保持精炼
 
 在现有记忆基础上进行整理和提炼，输出完整的更新后内容：
 - **合并提炼**：将含义相近的多条合并为一条高密度表述，而非简单罗列
-- **新增萃取**：从今日日记中提取值得永久记住的新信息（偏好、决策、人物、经验）
+- **新增萃取**：从今日日记中提取值得永久记住的新信息（偏好、决策、人物、规则、经验）
 - **冲突更新**：当新信息与旧条目矛盾时，以新信息为准，替换旧条目
 - **清理无效**：删除临时性记录、空白条目、格式残留等
 - **删除冗余**：已被更精炼表述涵盖的旧条目应删除，避免信息重复
 - 每条一行，用 "- " 开头，不带日期前缀
-- 目标：控制在 30 条以内，每条尽量一句话概括
+- 目标：控制在 50 条以内，每条尽量一句话概括
 
 ### Part 2: 梦境日记（[DREAM]）
 
@@ -300,15 +300,13 @@ class MemoryFlushManager:
 
     # ---- Deep Dream (memory distillation) ----
 
-    def deep_dream(self, user_id: Optional[str] = None, lookback_days: int = 1) -> bool:
+    def deep_dream(self, user_id: Optional[str] = None, lookback_days: int = 1, force: bool = False) -> bool:
         """
         Distill recent daily memories into MEMORY.md and generate a dream diary.
 
-        Process:
-        1. Read current MEMORY.md + recent N days of daily files
-        2. LLM produces updated MEMORY.md (deduped/pruned) + dream diary narrative
-        3. Overwrite MEMORY.md with the distilled version
-        4. Write dream diary to memory/dreams/YYYY-MM-DD.md
+        Args:
+            lookback_days: How many days of daily files to read (default 1 for scheduled, 3 for manual)
+            force: Skip input-hash dedup check (used by manual /memory dream trigger)
         """
         if not self.llm_model:
             logger.warning("[DeepDream] No LLM model available, skipping")
@@ -327,7 +325,7 @@ class MemoryFlushManager:
         # Dedup: skip if input materials haven't changed since last dream
         import hashlib
         input_hash = hashlib.md5((memory_content + daily_content).encode("utf-8")).hexdigest()
-        if input_hash == self._last_dream_input_hash:
+        if not force and input_hash == self._last_dream_input_hash:
             logger.debug("[DeepDream] Input unchanged since last dream, skipping")
             return False
         self._last_dream_input_hash = input_hash
@@ -377,16 +375,10 @@ class MemoryFlushManager:
             logger.warning("[DeepDream] No [MEMORY] section in LLM output, skipping overwrite")
             return False
 
-        # Overwrite MEMORY.md (with shrinkage protection)
+        # Overwrite MEMORY.md
         try:
             main_file = self.get_main_memory_file(user_id)
             old_size = len(memory_content)
-            if old_size > 200 and len(new_memory) < old_size * 0.3:
-                logger.warning(
-                    f"[DeepDream] Distilled MEMORY.md is too small "
-                    f"({old_size} → {len(new_memory)} chars, <30%), aborting to prevent data loss"
-                )
-                return False
             main_file.write_text(new_memory + "\n", encoding="utf-8")
             logger.info(
                 f"[DeepDream] Updated MEMORY.md "