chore: prepare repository for publishing

AGENTS.md

@@ -13,6 +13,7 @@ Use runtime-provided startup context first.
 That context may already include:
 
 - `AGENTS.md`, `SOUL.md`, and `USER.md`
+- `SESSION-STATE.md` when local active memory exists
 - recent daily memory such as `memory/YYYY-MM-DD.md`
 - `MEMORY.md` when this is the main session
 
@@ -22,15 +23,68 @@ Do not manually reread startup files unless:
 2. The provided context is missing something you need
 3. You need a deeper follow-up read beyond the provided startup context
 
+## Local Task Ownership
+
+- 本项目的任务系统以当前目录下的 [GOALS.md](/home/long/project/llm-intelligence/GOALS.md) 和 [TASKS.md](/home/long/project/llm-intelligence/TASKS.md) 为准。
+- 禁止把 `llm-intelligence` 的任务状态写回 `~/.openclaw/workspace/TASKS.md` 或其他全局任务文件。
+- review / cron / verifier 默认只读项目状态；只有在确实完成了项目内任务且验证通过后，才允许更新**本项目** `TASKS.md`。
+- 如果需要改任务文件，先重新读取最新内容；不要基于旧快照直接 `edit(oldText/newText)`。
+- 对 `TASKS.md`、`GOALS.md`、`OPENCLAW_EXECUTION.md` 这类大文档：
+  - 第一次 `edit` 失败后，必须先 `read` 最新全文
+  - 只允许对最小锚点重试一次
+  - 再失败就改为整段或整文件 `write`
+
 ## Memory
 
 You wake up fresh each session. These files are your continuity:
 
-- **Daily notes:** `memory/YYYY-MM-DD.md` (create `memory/` if needed) — raw logs of what happened
-- **Long-term:** `MEMORY.md` — your curated memories, like a human's long-term memory
+- **Active state:** `SESSION-STATE.md` — current project task state / WAL
+- **Daily notes:** `memory/YYYY-MM-DD.md` (create `memory/` if needed) — batched project archive, not per-message live logs
+- **Long-term:** `MEMORY.md` — curated project knowledge
+- **Ground truth for task status:** `TASKS.md`
+- **Ground truth for goal scope:** `GOALS.md`
 
 Capture what matters. Decisions, context, things to remember. Skip the secrets unless asked to keep them.
 
+### Project Memory Routing
+
+- High-frequency task changes go to `SESSION-STATE.md`
+- End-of-block summaries and project-local compaction recovery notes go to `memory/YYYY-MM-DD.md`
+- Stable project knowledge, recurring decisions, and long-lived risks go to `MEMORY.md`
+- Task completion and status changes belong in `TASKS.md`, not `MEMORY.md`
+- Goal / phase boundary changes belong in `GOALS.md`
+
+### Project Daily Memory Protocol
+
+- Do **not** treat `memory/YYYY-MM-DD.md` as the live working buffer.
+- Use it as a low-frequency archive file with timestamped sections appended at EOF.
+- If today's file does not exist, create it first with a stable header and a single `## Entries` section.
+- Because OpenClaw has `read` / `edit` / `write` but no `append`, prefer:
+  1. Read the current file
+  2. Preserve old content
+  3. Add one new timestamped section under `## Entries`
+  4. Use `write` for the full-file rewrite
+- Avoid `edit` for log-style files unless the anchor is tiny, unique, and freshly read.
+- Recommended section title format:
+  - `## HH:MM - <actor> - <topic>`
+- Allowed `<actor>` values:
+  - `main`
+  - `cron`
+  - `review`
+  - `verifier`
+  - `worker`
+- Section body should stay compact and use these headings only:
+  - `### Context`
+  - `### Evidence`
+  - `### Outcome`
+  - `### Next`
+- Role-specific rules:
+  - `cron` only records schedule result, failure reason, and whether follow-up is needed
+  - `review` only records findings, risk judgment, and recommended action
+  - `verifier` only records commands, evidence, and pass/fail
+  - `main` records user decisions, task switches, and milestone conclusions
+- Do not paste large raw logs into daily memory. Store only concise summaries plus file paths / commands.
+
 ### 🧠 MEMORY.md - Your Long-Term Memory
 
 - **ONLY load in main session** (direct chats with your human)
@@ -45,7 +99,7 @@ Capture what matters. Decisions, context, things to remember. Skip the secrets u
 
 - **Memory is limited** — if you want to remember something, WRITE IT TO A FILE
 - "Mental notes" don't survive session restarts. Files do.
-- When someone says "remember this" → update `memory/YYYY-MM-DD.md` or relevant file
+- When someone says "remember this" → update `SESSION-STATE.md` first, then route it to the right long-term file
 - When you learn a lesson → update AGENTS.md, TOOLS.md, or the relevant skill
 - When you make a mistake → document it so future-you doesn't repeat it
 - **Text > Brain** 📝