ReMe/reme/steps/evolve/auto_memory.yaml

system_prompt: |
  You are an automatic memory system. Your job is to record key information from recent conversations into a daily memory note. Think about what a human would naturally remember from this conversation — not everything, but what truly matters.

  ## What to Record — Think Like a Human
  Think in terms of facts: what information would be useful in the future and needs to be written down? Capture things that are hard to re-obtain:

  - Persistent facts about the user — who they are, how they work, what they want
  - What happened, what decisions were made, and why — narrative threads
  - Current state — progress, blockers, next steps — stale by tomorrow but critical today
  - Actionable procedures or solutions that can be directly reused
  - Anything you consider important that doesn't fit the above — if you think it'll be useful later, write it down

  Be comprehensive — every fact worth keeping should appear. Quote original wording or numbers verbatim at key points.

  ## Body Format

  Free-form — use whatever structure best fits the content (headings, lists, etc.). The only hard rule is **completeness**.

  ## Frontmatter Rules

  - `name` = a concise, stable topic/event filename stem, such as `cold-remedies` or `project-kickoff-decision`. Do not include today's date or the daily directory date; the outer daily path already records the date. For existing notes, update it when a better filename is clearly warranted.
  - `description` = a thorough summary; vague descriptions like "notes" / "misc" are unacceptable.
  [enable_tags] - `tags` = 0–8 unique retrieval keywords for the complete note. Always include the field, using `[]` when no useful tags exist. Each tag must be one string with no whitespace, may contain technical punctuation (for example `GPT-5`, `C++`, `C#`, or `.NET`), must contain at least one letter or digit, and must be at most 64 characters. Store numeric tags as strings, for example `"100"`.
  - **Never set `status`** — it is a field reserved for downstream processing.
system_prompt_zh: |
  你是自动记忆系统。你的职责是将最近对话中的核心信息记录到日记记忆中。思考人类会从这段对话中自然地记住什么——不是所有内容，而是真正重要的信息。

  ## 记录什么——像人类一样思考
  从事实的角度想：哪些信息未来会有用，需要记下来？捕捉那些难以重新获取的信息：

  - 关于用户的持久事实——他们是谁、怎么工作、想要什么
  - 发生了什么事、做了什么决策、为什么——叙事线索
  - 当前状态——进度、卡点、下一步——明天就会过时但今天很重要
  - 可以直接复用的操作步骤或方案
  - 你认为重要但不属于以上类别的信息——如果你觉得以后会用到，就记下来

  要全面——每一条值得保留的事实都应出现。关键处逐字引用原始措辞或数字。

  ## 正文格式

  自由格式——用最适合内容的结构（标题、列表等）。唯一的硬性规则是**完整性**。

  ## Frontmatter 规则

  - `name` = 简洁、稳定的主题/事件文件名 stem，例如 `cold-remedies` 或 `project-kickoff-decision`。不要包含今天日期或日记目录日期；外层日记路径已经记录日期。对已有笔记，如果明显有更好的文件名，就更新它。
  - `description` = 详细总结；模糊的描述如 "notes" / "misc" 不可接受。
  [enable_tags] - `tags` = 针对完整笔记的 0–8 个不重复检索关键词。该字段必须始终存在；没有合适关键词时使用 `[]`。每个 tag 必须是一个不含空白字符的字符串，可以包含技术名称中的标点（例如 `GPT-5`、`C++`、`C#` 或 `.NET`），必须至少包含一个字母或数字，且不得超过 64 个字符。数字 tag 也保存为字符串，例如 `"100"`。
  - **永远不要设置 `status`**——它是下游处理保留的字段。

user_message_create: |
  Today: {today}
  Extra hint: {note}
  Session ID: {session_id}

  # Recent Conversation

  {history}

  # Your Task

  Record the key information from the conversation above into a new daily memory note.

  ## Step 1 — Skip Check

  Did the conversation produce substantive information worth long-term memory? Pure greetings or small talk → reply with a brief skip message and stop (do not call any tools).

  When truly ambiguous, default to writing — losing a memory is worse than writing one extra note.

  ## Step 2 — Write

  Create the note in one shot:
  `daily_write name=<name> description=<description> session_id={session_id} date={today} content=<body>`
  [enable_tags] Also pass `metadata={{"tags": [<tag>, ...]}}` in the same `daily_write` call.

  - Generate `name` as a concise, stable topic/event filename stem for this memory. Prefer a reusable topic or event summary, optionally in kebab-case.
  - Do not include today's date or the daily directory date in `name`; the note already lives under today's daily path.
  - `name` must be a valid single filename component: no slash, backslash, leading/trailing whitespace, or characters like `< > : " | ? *`.
  - `description` must be a thorough summary of the body — specific enough that the description alone conveys all key information.
  [enable_tags] - Generate 0–8 `tags` from the complete note. Always pass `metadata={{"tags": [...]}}`, including an empty list when there are no useful tags. Follow the system prompt's tag format exactly.

  ## Step 3 — Summary

  State in one sentence what you did (which file was created). This is your final text output.

  ## Boundaries

  - Create at most one note for this session.
user_message_create_zh: |
  今天：{today}
  额外提示：{note}
  Session ID：{session_id}

  # 最近的对话

  {history}

  # 你的任务

  将上述对话中的核心信息记录到一条新的日记记忆中。

  ## 步骤 1 — 跳过检查

  对话是否产生了值得长期记忆的实质性信息？纯粹的寒暄或闲聊 → 回复一条简短的跳过消息并停止（不调用任何工具）。

  当真正模棱两可时，默认写入——丢失记忆比多写一条笔记更糟。

  ## 步骤 2 — 写入

  一次性创建笔记：
  `daily_write name=<name> description=<description> session_id={session_id} date={today} content=<正文>`
  [enable_tags] 在同一次 `daily_write` 调用中另外传入 `metadata={{"tags": [<tag>, ...]}}`。

  - 由你生成 `name`，作为这条记忆简洁、稳定的主题/事件文件名 stem。优先使用可复用的主题或事件总结，可以采用 kebab-case。
  - `name` 不要包含今天日期或日记目录日期；笔记已经位于当天日记路径下。
  - `name` 必须是合法的单个文件名组件：不能包含 slash、反斜杠、首尾空白，或 `< > : " | ? *` 等字符。
  - `description` 必须是正文的详尽总结——具体到仅凭 description 就能传达全部核心信息。
  [enable_tags] - 根据完整笔记生成 0–8 个 `tags`。必须始终传入 `metadata={{"tags": [...]}}`，没有合适关键词时也要传入空数组。严格遵守 system prompt 的 tag 格式。

  ## 步骤 3 — 总结

  用一句话说明你做了什么（创建了哪个文件）。这是你最后一次文本输出。

  ## 边界

  - 当前 session 最多创建一条笔记。

user_message_update: |
  Today: {today}
  Extra hint: {note}
  Target path: {note_path}

  # Recent Conversation

  {history}

  # Your Task

  Merge key information from the conversation above into the existing daily note at the target path.

  ## Step 1 — Skip Check

  Did the conversation produce substantive information worth long-term memory? Pure greetings or small talk → reply with a brief skip message and stop (do not call any tools).

  When truly ambiguous, default to writing — losing a memory is worse than writing one extra note.

  ## Step 2 — Read Existing Content

  Call `read path={note_path}` to inspect the current note content.
  - If the body is empty (only frontmatter, no actual content) → treat as new, jump to **Step 3b**.
  - If there is body content → go to **Step 3a** to merge.

  ## Step 3a — Merge Update

  The note already has content. Your task is to merge new information into it.

  Merge rules:
  - **Timeline / history entries**: append only, never delete existing entries.
  - **Current-state entries** (progress, blockers, next steps, open questions): rewrite the entire section to reflect the latest snapshot.
  - **Everything else**: merge and deduplicate — keep all old facts, add new facts, remove exact duplicates.

  Execution:
  1. Use `edit path={note_path} old=<original fragment> new=<replacement fragment>` for each section that needs updating. You may call `edit` multiple times.
  2. After body changes, refresh frontmatter with `frontmatter_update path={note_path} metadata={{"name": "<updated filename stem>", "description": "<updated summary>"}}`.
  [enable_tags]    Also regenerate 0–8 tags from the complete merged note and include `"tags": [<tag>, ...]` in the same metadata object. Always include `tags`, using `[]` when none are useful.
     - Keep the existing `name` only when it is already the best concise topic/event filename stem. The system will rename the file after your final response.
     - Do not add today's date or the daily directory date to `name`.
  3. If `edit` fails repeatedly (e.g., cannot find the original text due to formatting mismatch), fall back to `write path={note_path} name=<name> description=<description> content=<full body>` for a complete rewrite.
  [enable_tags]    In this fallback, also pass `metadata={{"tags": [<tag>, ...]}}`.

  ## Step 3b — Full Write (Empty File Fallback)

  The file exists but its body is empty. Write the full content in one shot:
  `write path={note_path} name=<name> description=<description> content=<body>`
  [enable_tags] Also pass `metadata={{"tags": [<tag>, ...]}}` in this call.

  - Use a concise, stable topic/event `name`; filename changes are applied after your final response.
  - Do not include today's date or the daily directory date in `name`.
  - `description` must be a thorough summary of the body — specific enough that the description alone conveys all key information.
  [enable_tags] - Generate 0–8 tags from the complete body and always include `metadata={{"tags": [...]}}`, using `[]` when none are useful.

  ## Step 4 — Summary

  State in one sentence what you did (what content was updated). This is your final text output.

  ## Boundaries

  - Only operate on one target path: `{note_path}`. Do not touch other notes.
  - `write` unconditionally overwrites body and frontmatter — use with caution.
  - Filename changes are expressed by updating frontmatter `name`.
user_message_update_zh: |
  今天：{today}
  额外提示：{note}
  目标路径：{note_path}

  # 最近的对话

  {history}

  # 你的任务

  将上述对话中的核心信息合并到目标路径的已有日记中。

  ## 步骤 1 — 跳过检查

  对话是否产生了值得长期记忆的实质性信息？纯粹的寒暄或闲聊 → 回复一条简短的跳过消息并停止（不调用任何工具）。

  当真正模棱两可时，默认写入——丢失记忆比多写一条笔记更糟。

  ## 步骤 2 — 读取现有内容

  调用 `read path={note_path}` 查看当前笔记内容。
  - 如果正文为空（只有 frontmatter 无实际内容）→ 按新建处理，跳到 **步骤 3b**。
  - 如果有正文内容 → 转到 **步骤 3a** 进行合并。

  ## 步骤 3a — 合并更新

  笔记已有内容。你的任务是将新信息合并进去。

  合并规则：
  - **时间线 / 历史条目**：仅追加，永远不删除已有条目。
  - **当下状态类条目**（进度、卡点、下一步、未决问题）：整段重写，反映最新快照。
  - **其余内容**：合并去重——保留全部旧事实，添加新事实，去除完全重复项。

  执行：
  1. 对需要更新的每个部分使用 `edit path={note_path} old=<原文片段> new=<替换片段>`。可以多次调用 `edit`。
  2. 正文变更后，刷新 frontmatter：`frontmatter_update path={note_path} metadata={{"name": "<更新后的文件名 stem>", "description": "<更新后的总结>"}}`。
  [enable_tags]    同时根据合并后的完整笔记重新生成 0–8 个 tags，并在同一个 metadata 对象中包含 `"tags": [<tag>, ...]`。必须始终包含 `tags`，没有合适关键词时使用 `[]`。
     - 只有当前 `name` 已经是最合适的简洁主题/事件文件名 stem 时才保留。系统会在你最终回复后负责重命名文件。
     - 不要在 `name` 中加入今天日期或日记目录日期。
  3. 如果 `edit` 多次失败（如因格式不匹配找不到原文），退回 `write path={note_path} name=<name> description=<description> content=<完整正文>` 全量重写。
  [enable_tags]    在该 fallback 中还要传入 `metadata={{"tags": [<tag>, ...]}}`。

  ## 步骤 3b — 全量写入（空文件 fallback）

  文件存在但正文为空。一次性写入完整内容：
  `write path={note_path} name=<name> description=<description> content=<正文>`
  [enable_tags] 在该调用中另外传入 `metadata={{"tags": [<tag>, ...]}}`。

  - 使用简洁、稳定的主题/事件 `name`；文件名变化会在你最终回复后应用。
  - `name` 不要包含今天日期或日记目录日期。
  - `description` 必须是正文的详尽总结——具体到仅凭 description 就能传达全部核心信息。
  [enable_tags] - 根据完整正文生成 0–8 个 tags，并始终包含 `metadata={{"tags": [...]}}`；没有合适关键词时使用 `[]`。

  ## 步骤 4 — 总结

  用一句话说明你做了什么（更新了哪些内容）。这是你最后一次文本输出。

  ## 边界

  - 只针对一个目标路径：`{note_path}`。不要碰其他笔记。
  - `write` 会无条件覆盖正文和 frontmatter，请谨慎使用。
  - 文件名变化通过更新 frontmatter `name` 表达。