create-openclaw-bot 5.13.8 → 5.14.0

package/README.md

@@ -7,7 +7,7 @@
 *Run one command → open the dashboard → your bot is live. Windows · macOS · Linux · VPS — Docker-powered, auto-installed for you.*
 
 <p align="center">
-  <a href="https://github.com/tuanminhhole/openclaw-setup/releases"><img src="https://img.shields.io/badge/RELEASE-v5.13.8-0EA5E9?style=for-the-badge" alt="Version 5.13.8" /></a>
+  <a href="https://github.com/tuanminhhole/openclaw-setup/releases"><img src="https://img.shields.io/badge/RELEASE-v5.14.0-0EA5E9?style=for-the-badge" alt="Version 5.14.0" /></a>
   <a href="https://github.com/tuanminhhole/openclaw-setup?tab=MIT-1-ov-file"><img src="https://img.shields.io/badge/LICENSE-MIT-success?style=for-the-badge" alt="MIT License" /></a>
   <a href="https://www.npmjs.com/package/create-openclaw-bot"><img src="https://img.shields.io/npm/v/create-openclaw-bot?style=for-the-badge&label=CLI&color=2563EB&logo=npm&logoColor=white" alt="NPM Version" /></a>
   <a href="https://github.com/tuanminhhole/openclaw-setup/stargazers"><img src="https://img.shields.io/github/stars/tuanminhhole/openclaw-setup?style=for-the-badge&color=eab308&logo=github&logoColor=white" alt="GitHub Stars" /></a>
@@ -37,11 +37,26 @@
 
 ---
 
-## 🆕 What's New in v5.13.8
+## 🆕 What's New in v5.14.0
+
+- 🛠️ **Bots build their own skills**: ask your bot for a reusable capability ("make me a skill for X") and it writes the skill and puts it to work in the same reply — no approval step, no config editing. The skill is saved to `skills/<name>/SKILL.md` in the bot's workspace and loads itself. **Existing bots pick this up automatically on update.**
+
+<details>
+<summary><b>Previous: What's new in v5.13.9</b></summary>
+
+- 🧠 **Always-on memory for every bot (learning-memory)**: a new context-engine plugin injects your curated `MEMORY.md` + `USER.md` into **every** turn — including group chats, which the default recall skips. Bots stop forgetting context and rules over time: no more chiming in when nobody called them, or re-asking things you already told them. Auto-installed for new bots + a 1-click card in the dashboard.
+- 🧹 **Retired TencentDB Agent Memory** in favor of the always-on engine above (no external service needed). Existing bots are auto-migrated on update — the old learning-memory *skill* and the TencentDB plugin are removed automatically.
+
+</details>
+
+<details>
+<summary><b>Previous: What's new in v5.13.4</b></summary>
 
 - ⚙️ **New Settings page**: pick your theme (light/dark toggle), language (VI/EN) and timezone right from the dashboard — available in both the sidebar and the mobile nav bar.
 - 🕒 **Schedules & cron run in the correct local time**: newly created bots carry an explicit timezone, so reminders/cron no longer drift a day off around midnight (a UTC-vs-local bug that could schedule into the past). Scheduling guidance was hardened end-to-end (local time + timezone, explicit delivery target, raw group id).
 
+</details>
+
 <details>
 <summary><b>Previous: What's new in v5.13.0</b></summary>
 
@@ -336,7 +351,7 @@ Companion repos to build a complete, self-running AI assistant:
 - [openclaw-n8n-facebook-poster](https://github.com/tuanminhhole/openclaw-n8n-facebook-poster) — Auto-post to Facebook via n8n
 
 **🧩 Skills**
-- [openclaw-skill-learning-memory](https://github.com/tuanminhhole/openclaw-skill-learning-memory) — Self-evolving long-term memory for agents
+- [openclaw-learning-memory](https://github.com/tuanminhhole/openclaw-learning-memory) — Always-on memory context engine (injects curated MEMORY.md + USER.md into every turn, incl. groups)
 - [openclaw-skill-infographic](https://github.com/tuanminhhole/openclaw-skill-infographic) — Infographic generation
 
 ---

package/README.vi.md

@@ -7,7 +7,7 @@
 *Chạy một lệnh → mở dashboard → bot lên sóng. Windows · macOS · Linux · VPS — chạy trên Docker, tự cài giúp bạn.*
 
 <p align="center">
-  <a href="https://github.com/tuanminhhole/openclaw-setup/releases"><img src="https://img.shields.io/badge/RELEASE-v5.13.8-0EA5E9?style=for-the-badge" alt="Version 5.13.8" /></a>
+  <a href="https://github.com/tuanminhhole/openclaw-setup/releases"><img src="https://img.shields.io/badge/RELEASE-v5.14.0-0EA5E9?style=for-the-badge" alt="Version 5.14.0" /></a>
   <a href="https://github.com/tuanminhhole/openclaw-setup?tab=MIT-1-ov-file"><img src="https://img.shields.io/badge/LICENSE-MIT-success?style=for-the-badge" alt="MIT License" /></a>
   <a href="https://www.npmjs.com/package/create-openclaw-bot"><img src="https://img.shields.io/npm/v/create-openclaw-bot?style=for-the-badge&label=CLI&color=2563EB&logo=npm&logoColor=white" alt="NPM Version" /></a>
   <a href="https://github.com/tuanminhhole/openclaw-setup/stargazers"><img src="https://img.shields.io/github/stars/tuanminhhole/openclaw-setup?style=for-the-badge&color=eab308&logo=github&logoColor=white" alt="GitHub Stars" /></a>
@@ -37,11 +37,26 @@
 
 ---
 
-## 🆕 Có gì mới trong v5.13.8
+## 🆕 Có gì mới trong v5.14.0
+
+- 🛠️ **Bot tự tạo skill cho chính nó**: nhờ bot làm một kỹ năng dùng lại ("tạo cho anh skill X") là nó viết xong và dùng được ngay trong cùng câu trả lời — không còn bước chờ duyệt, không phải sửa cấu hình. Skill lưu vào `skills/<tên>/SKILL.md` trong workspace của bot và tự nạp. **Bot cũ tự nhận khi cập nhật.**
+
+<details>
+<summary><b>Trước đó: Có gì mới trong v5.13.9</b></summary>
+
+- 🧠 **Trí nhớ always-on cho mọi bot (learning-memory)**: plugin context-engine mới nạp `MEMORY.md` + `USER.md` đã chắt lọc vào **MỌI lượt** — kể cả trong nhóm (điều recall mặc định bỏ qua). Bot hết quên ngữ cảnh/quy tắc theo thời gian: không còn "nói leo" khi không ai gọi, không hỏi lại điều bạn đã dặn. Tự cài cho bot mới + có card 1-chạm trên dashboard.
+- 🧹 **Bỏ TencentDB Agent Memory**, thay bằng engine always-on ở trên (không cần dịch vụ ngoài). Bot cũ tự migrate khi cập nhật — *skill* learning-memory cũ và plugin TencentDB được gỡ tự động.
+
+</details>
+
+<details>
+<summary><b>Trước đó: Có gì mới trong v5.13.4</b></summary>
 
 - ⚙️ **Trang Cài đặt mới**: chọn giao diện (nút gạt Sáng/Tối), ngôn ngữ (VI/EN) và múi giờ ngay trong dashboard — có ở cả sidebar lẫn thanh điều hướng mobile.
 - 🕒 **Lịch & cron chạy đúng giờ địa phương**: bot tạo mới nhận múi giờ rõ ràng, nên nhắc hẹn/cron không còn lệch 1 ngày quanh nửa đêm (lỗi UTC-vs-local có thể đặt lịch vào quá khứ). Đã siết hướng dẫn lập lịch toàn diện (giờ local + múi giờ, nơi gửi rõ ràng, ID nhóm dạng thô).
 
+</details>
+
 <details>
 <summary><b>Trước đó: Có gì mới trong v5.13.0</b></summary>
 
@@ -336,7 +351,7 @@ Các repo đi kèm để bạn dựng một trợ lý AI "tự vận hành" hoà
 - [openclaw-n8n-facebook-poster](https://github.com/tuanminhhole/openclaw-n8n-facebook-poster) — Tự động đăng Facebook qua n8n
 
 **🧩 Skill**
-- [openclaw-skill-learning-memory](https://github.com/tuanminhhole/openclaw-skill-learning-memory) — Bộ nhớ dài hạn tự tiến hoá cho agent
+- [openclaw-learning-memory](https://github.com/tuanminhhole/openclaw-learning-memory) — Context engine trí nhớ always-on (nạp MEMORY.md + USER.md vào mọi lượt, kể cả nhóm)
 - [openclaw-skill-infographic](https://github.com/tuanminhhole/openclaw-skill-infographic) — Tạo infographic
 
 ---

package/dist/server/local-server.js

@@ -1032,14 +1032,16 @@ function ensureZaloModPluginConfig(entry, cfg) {
     const gwPort = Number(cfg.gateway?.port) || state.gatewayPort || 18789;
     entry.config.dashboardPort = gwPort + 1;
   }
-  // Auto-assign botName from first agent name
-  if (!entry.config.botName) {
-    const agentName = cfg.agents?.list?.[0]?.name;
-    if (agentName) entry.config.botName = agentName;
-  }
-  // Auto-assign zaloDisplayNames from botName
-  if ((!entry.config.zaloDisplayNames || entry.config.zaloDisplayNames.length === 0) && entry.config.botName) {
-    entry.config.zaloDisplayNames = [entry.config.botName];
+  // Seed the default bot's identity under bots.default (per-bot shape). zalo-mod
+  // treats bots.<profile> as the canonical source — do NOT write legacy top-level
+  // botName/zaloDisplayNames (they get stripped by the plugin's normalizer anyway).
+  const firstAgentName = cfg.agents?.list?.[0]?.name;
+  if (firstAgentName) {
+    entry.config.bots = entry.config.bots || {};
+    const def = entry.config.bots.default = entry.config.bots.default || {};
+    if (!def.botName) def.botName = firstAgentName;
+    if (!Array.isArray(def.zaloDisplayNames) || def.zaloDisplayNames.length === 0) def.zaloDisplayNames = [firstAgentName];
+    if (!def.slashPrefix) def.slashPrefix = String(firstAgentName).toLowerCase().replace(/[^a-z0-9-]/g, '') || 'bot';
   }
 }
 
@@ -3126,8 +3128,8 @@ async function applyFeatureToggle(projectDir, agentId, kind, id, enabled) {
   // from <workspace>/skills, so each bot's copy is independent. Toggling here affects ONLY the
   // active bot's workspace folder. The global skills.entries[id].enabled flag is kept true
   // while ANY bot still has the folder (openclaw needs it true to load the skill at all).
-  if (kind === 'skill' && (id === 'image-gen' || id === 'learning-memory')) {
-    const slugMap = { 'image-gen': 'infographic-generator', 'learning-memory': 'learning-memory' };
+  if (kind === 'skill' && id === 'image-gen') {
+    const slugMap = { 'image-gen': 'infographic-generator' };
     const slug = slugMap[id];
     const rel = workspaceRelForAgent(agent, cfg, projectDir) || `workspace-${agent.id}`;
     const folder = join(projectDir, '.openclaw', rel, 'skills', slug);
@@ -3284,7 +3286,9 @@ async function applyFeatureToggle(projectDir, agentId, kind, id, enabled) {
 // Most plugins are ClawHub packages (installed as `clawhub:<id>`). A few ship as plain npm
 // packages and need their real package spec instead. Map id → install spec here.
 const PLUGIN_NPM_SPEC = {
-  'memory-tencentdb': '@tencentdb-agent-memory/memory-tencentdb',
+  // learning-memory ships on ClawHub as `openclaw-learning-memory` (manifest id is
+  // `learning-memory`, used as the config key). Install by the full package spec.
+  'learning-memory': 'clawhub:openclaw-learning-memory',
 };
 const pluginInstallSpec = (id) => PLUGIN_NPM_SPEC[id] || `clawhub:${id}`;
 
@@ -3292,7 +3296,6 @@ async function installFeature(projectDir, agentId, kind, id) {
   if (kind === 'skill') {
     const skillSlugMap = {
       'image-gen': 'infographic-generator',
-      'learning-memory': 'learning-memory',
     };
     const slug = skillSlugMap[id] || id;
 
@@ -3379,6 +3382,11 @@ async function installFeature(projectDir, agentId, kind, id) {
         sendLog('[zalo-connect] Restarting container to apply...');
         await run('docker', ['restart', getBotContainerName(projectDir)], { shell: false }).catch(() => {});
       }
+      // Drop cached container extension versions so the card reflects the just-installed
+      // version immediately (extver cache lives until explicitly cleared, like the
+      // general install path below does).
+      probeCacheClear(`extver:${projectDir}`);
+      probeCacheClear(`runtime:${projectDir}`);
       return { ok: true, id: 'zalo-connect' };
     }
     const installSpec = pluginInstallSpec(id);
@@ -3675,14 +3683,13 @@ async function getFeatureFlags(projectDir, agentId = '') {
   // THIS agent's workspace (not the global skills.entries flag, which would leak across bots).
   const imageGenOn = isSkillFolderExists(projectDir, aid, 'infographic-generator', cfg);
   const webSearchOn = isEnabled(['duckduckgo']);
-  const learningMemoryOn = isSkillFolderExists(projectDir, aid, 'learning-memory', cfg);
   const aliases = {
     browser: ['openclaw-browser-automation', 'browser-automation'],
     zalo: ['openclaw-zalo-mod', 'zalo-mod'],
     crawler: ['openclaw-facebook-crawler', 'openclaw-n8n-facebook-crawler', 'n8n-facebook-crawler'],
     poster: ['openclaw-n8n-facebook-poster', 'openclaw-facebook-poster', 'facebook-poster'],
     fbMessenger: ['openclaw-fb-messenger', 'fb-messenger'],
-    tencentMemory: ['memory-tencentdb'],
+    learningMemory: ['learning-memory', 'openclaw-learning-memory'],
     zaloConnect: ['zalo-connect', 'openclaw-zalo-connect'],
   };
   const flags = {
@@ -3690,13 +3697,12 @@ async function getFeatureFlags(projectDir, agentId = '') {
     'skill:cron': cronOn,
     'skill:image-gen': imageGenOn,
     'skill:web-search': webSearchOn,
-    'skill:learning-memory': learningMemoryOn,
     'plugin:openclaw-browser-automation': isEnabled(aliases.browser),
     'plugin:openclaw-zalo-mod': isEnabled(aliases.zalo),
     'plugin:openclaw-facebook-crawler': isEnabled(aliases.crawler),
     'plugin:openclaw-n8n-facebook-poster': isEnabled(aliases.poster),
     'plugin:openclaw-fb-messenger': isEnabled(aliases.fbMessenger),
-    'plugin:memory-tencentdb': isEnabled(aliases.tencentMemory),
+    'plugin:learning-memory': isEnabled(aliases.learningMemory),
     'plugin:zalo-connect': isEnabled(aliases.zaloConnect),
   };
   const extensionsDir = join(projectDir || '', '.openclaw', 'extensions');
@@ -3706,7 +3712,6 @@ async function getFeatureFlags(projectDir, agentId = '') {
     extensionDirExists(aliases) || isInstalledByRecord(aliases);
   const installed = {
     'skill:image-gen': isSkillFolderExists(projectDir, aid, 'infographic-generator', cfg),
-    'skill:learning-memory': isSkillFolderExists(projectDir, aid, 'learning-memory', cfg),
     'plugin:openclaw-browser-automation': isActuallyInstalled(aliases.browser),
     'plugin:openclaw-zalo-mod': isActuallyInstalled(aliases.zalo),
     'plugin:openclaw-facebook-crawler': isActuallyInstalled(aliases.crawler),
@@ -3715,31 +3720,34 @@ async function getFeatureFlags(projectDir, agentId = '') {
     // proof of install — require a real extension dir or an install record instead.
     'plugin:openclaw-fb-messenger': extensionDirExists(aliases.fbMessenger)
       || aliases.fbMessenger.some((a) => installedKeys.has(a) || Array.from(installedSpecs).some((spec) => spec.includes(a))),
-    'plugin:memory-tencentdb': isActuallyInstalled(aliases.tencentMemory),
+    'plugin:learning-memory': isActuallyInstalled(aliases.learningMemory),
     'plugin:zalo-connect': isActuallyInstalled(aliases.zaloConnect),
   };
   const versions = {
     'skill:image-gen': await getInstalledSkillVersion(projectDir, aid, 'infographic-generator', cfg),
-    'skill:learning-memory': await getInstalledSkillVersion(projectDir, aid, 'learning-memory', cfg),
     'plugin:openclaw-browser-automation': await getInstalledPluginVersion(projectDir, aliases.browser),
     'plugin:openclaw-zalo-mod': await getInstalledPluginVersion(projectDir, aliases.zalo),
     'plugin:openclaw-facebook-crawler': await getInstalledPluginVersion(projectDir, aliases.crawler),
     'plugin:openclaw-n8n-facebook-poster': await getInstalledPluginVersion(projectDir, aliases.poster),
     'plugin:openclaw-fb-messenger': await getInstalledPluginVersion(projectDir, aliases.fbMessenger),
-    'plugin:memory-tencentdb': await getInstalledPluginVersion(projectDir, aliases.tencentMemory),
+    'plugin:learning-memory': await getInstalledPluginVersion(projectDir, aliases.learningMemory),
     'plugin:zalo-connect': await getInstalledPluginVersion(projectDir, aliases.zaloConnect),
   };
-  // Docker: fill any plugin version still empty from the container's extensions volume
-  // (e.g. bundled/clawhub plugins like zalo-mod that aren't on the host). One docker exec.
+  // Docker: the container's extensions volume is the SOURCE OF TRUTH for installed
+  // plugin versions — clawhub/plugin installs run inside the container, so a host copy
+  // (bind-mounted .openclaw or a stale installs.json) can lag behind after an update.
+  // When the container reports a version, it OVERRIDES the host value (not just fills
+  // empties) so the card shows the actually-installed version, not a stale one. Native
+  // installs return {} here, so host values are kept.
   const containerExtVersions = await getContainerExtensionVersions(projectDir);
   if (Object.keys(containerExtVersions).length) {
-    const fillVer = (key, names) => { if (!versions[key]) { for (const n of names) { if (containerExtVersions[n]) { versions[key] = containerExtVersions[n]; break; } } } };
+    const fillVer = (key, names) => { for (const n of names) { if (containerExtVersions[n]) { versions[key] = containerExtVersions[n]; break; } } };
     fillVer('plugin:openclaw-browser-automation', aliases.browser);
     fillVer('plugin:openclaw-zalo-mod', aliases.zalo);
     fillVer('plugin:openclaw-facebook-crawler', aliases.crawler);
     fillVer('plugin:openclaw-n8n-facebook-poster', aliases.poster);
     fillVer('plugin:openclaw-fb-messenger', aliases.fbMessenger);
-    fillVer('plugin:memory-tencentdb', aliases.tencentMemory);
+    fillVer('plugin:learning-memory', aliases.learningMemory);
     fillVer('plugin:zalo-connect', aliases.zaloConnect);
   }
   const zaloBackend = fresh.channels?.['zalo-connect']?.enabled ? 'zalo-connect' : '';

package/dist/setup/shared/bot-config-gen.js

@@ -114,10 +114,34 @@
           // nửa đêm và đặt cron/lịch vào quá khứ. Lấy tz người dùng chọn ở UI Cài đặt (mặc định VN).
           userTimezone,
           compaction: { mode: 'safeguard' },
-          // Trim stale tool results before Anthropic's prompt-cache TTL expires so the
-          // re-cache write stays small → lower token cost on long sessions, zero downside.
-          // The stable system prompt (AGENTS.md/SOUL.md…) stays cached above the boundary.
-          contextPruning: { mode: 'cache-ttl', ttl: '5m' },
+          // Trim stale tool results from context before each LLM call. Lowers token
+          // cost on long sessions AND keeps a heavy multi-step turn (deep research +
+          // file/PDF gen) from piling up tool output that overflows the model window
+          // mid tool-loop. These bots run on 9router (no Anthropic prompt cache), so a
+          // short 2m TTL lets pruning engage sooner inside a long turn — no cache
+          // downside. The stable system prompt (AGENTS.md/SOUL.md…) is never pruned.
+          contextPruning: { mode: 'cache-ttl', ttl: '2m' },
+          // Compress vision inputs — these bots are image-heavy (infographics, PDF
+          // charts, screenshots). "efficient" keeps vision-token cost down so an
+          // image-rich turn is far less likely to blow past the context window.
+          imageQuality: 'efficient',
+          // Downscale image payloads when sanitizing transcript/tool-result content
+          // (OpenClaw default is 1200px). Verified failure mode: the bot generated 4K
+          // infographics for a PDF and then read them back with the image tool — each
+          // read landed a ~100KB base64 blob in the transcript, and the overflow
+          // precheck counts that base64 as plain text (~14k tokens per image). Eight of
+          // them in one turn = 214k estimated tokens against a 180k budget → abort with
+          // "nothing to compact". 1024px keeps charts/screenshots legible to vision
+          // while roughly halving the payload.
+          imageMaxDimensionPx: 1024,
+          // Cap each persisted tool result. The model-context auto default is huge
+          // (64k chars/result at 200k tokens), so one heavy turn (e.g. deep research
+          // with 40+ web fetches) can pile up 200k+ tokens of tool output in a SINGLE
+          // unsplittable turn — which then can't be compacted ("nothing to compact")
+          // and poisons the session until a manual reset. 12k chars (~3k tokens) per
+          // result keeps per-source content substantial while making that runaway
+          // impossible. Applies to persisted results + overflow recovery.
+          contextLimits: { toolResultMaxChars: 12000 },
           // Agent-TURN budget (seconds). 120 was too short for multi-step cloud turns (OCR +
           // file gen + tool calls). 900 = OpenClaw's own native default and the practical max
           // we use. This is the turn budget — a DIFFERENT layer from 9router's per-request
@@ -240,8 +264,17 @@
     const skillEntries = buildSkillsEntries(skills, selectedSkills);
     // NOTE: the "zalo-actions" skill was removed — its guidance now lives in the `zalo-connect`
     // tool description itself (fork ≥ v3.0.2), so no per-bot skill entry is needed anymore.
+    //
+    // Skill Workshop `approvalPolicy: "auto"` lets the assistant author its own
+    // workspace skills end-to-end when the user asks ("tạo skill X"): create the
+    // proposal AND apply it in one turn, without a separate operator approval.
+    // Apply is still scanner-gated + workspace-scoped + rollback-tracked, so this
+    // stays safe. Workspace SKILL.md files auto-load via the skills watcher — no
+    // per-skill openclaw.json entry is needed. `autonomous.enabled` stays false so
+    // the bot only creates skills on explicit request, never spontaneously.
+    cfg.skills = { workshop: { approvalPolicy: 'auto' } };
     if (Object.keys(skillEntries).length > 0) {
-      cfg.skills = { entries: skillEntries };
+      cfg.skills.entries = skillEntries;
     }
 
     // ── plugins (memory-core dreaming + openclaw-zalo-mod) ────────────────────────────
@@ -371,6 +404,12 @@
 
     const allow = ['memory-core'];
 
+    // Always-on memory: the learning-memory context engine injects the curated
+    // MEMORY.md + USER.md into every turn (including group sessions, which the default
+    // recall excludes). Enabled for every bot; the plugin is installed at creation time.
+    entries['learning-memory'] = { enabled: true };
+    allow.push('learning-memory');
+
     // Zalo Personal → zalo-connect channel plugin (pinned install happens in the
     // entrypoint / creation flow). openclaw-zalo-mod stays a separate opt-in plugin.
     if (isZaloPersonal(channelKey)) {
@@ -395,6 +434,8 @@
 
     const plugins = { entries };
     plugins.allow = allow;
+    // Select learning-memory as the active context engine (always-on memory).
+    plugins.slots = { contextEngine: 'learning-memory' };
     if (allow.length) plugins.bundledDiscovery = 'compat';
 
     return { plugins };

package/dist/setup/shared/docker-gen.js

@@ -256,6 +256,28 @@ if(touched){console.log('[patch-9router] Applied Codex compatibility patch.');}e
     const backupConfigScript = `const fs=require('fs'),path=require('path'),p=path.join(process.cwd(),'.openclaw','openclaw.json'),b=p.replace('openclaw.json','.openclaw-config-backup.json');if(fs.existsSync(p)){fs.copyFileSync(p,b);}`;
 
     const restoreConfigScript = `const fs=require('fs'),os=require('os'),path=require('path'),p=path.join(process.cwd(),'.openclaw','openclaw.json'),b=p.replace('openclaw.json','.openclaw-config-backup.json');if(fs.existsSync(p)&&fs.existsSync(b)){const c=JSON.parse(fs.readFileSync(p,'utf8'));const bk=JSON.parse(fs.readFileSync(b,'utf8'));const keep=['agents','channels','bindings','commands','models','browser','skills','plugins','tools'];for(const k of keep){if(bk[k]&&!c[k])c[k]=bk[k];}const gp=Number(process.env.OPENCLAW_GATEWAY_PORT||process.env.OPENCLAW_PORT)||c.gateway?.port||bk.gateway?.port||18789;const a=new Set(['http://localhost:'+gp,'http://127.0.0.1:'+gp,'http://0.0.0.0:'+gp]);for(const entries of Object.values(os.networkInterfaces()||{})){for(const entry of entries||[]){if(!entry||entry.internal||entry.family!=='IPv4'||!entry.address)continue;a.add('http://'+entry.address+':'+gp);}}c.tools=Object.assign({},c.tools,{profile:'full',exec:{host:'gateway',security:'full',ask:'off'}});c.gateway=Object.assign({},c.gateway,{port:gp,bind:'custom',customBindHost:'0.0.0.0',mode:c.gateway?.mode||bk.gateway?.mode||'local',controlUi:Object.assign({},c.gateway?.controlUi,{allowedOrigins:Array.from(a).filter(Boolean)})});fs.writeFileSync(p,JSON.stringify(c,null,2));fs.unlinkSync(b);}`;
+    // One-shot migration for projects created by an older setup: the learning-memory
+    // SKILL and the memory-tencentdb plugin are deprecated (replaced by the learning-memory
+    // context-engine plugin). Drop their config entries so they stop loading; the skill
+    // folders + tencentdb install are removed by the shell steps that follow.
+    const deprecatedCleanupScript = `const fs=require('fs'),path=require('path');const p=path.join(process.cwd(),'.openclaw','openclaw.json');if(fs.existsSync(p)){const c=JSON.parse(fs.readFileSync(p,'utf8'));let ch=false;if(c.plugins&&c.plugins.entries&&c.plugins.entries['memory-tencentdb']){delete c.plugins.entries['memory-tencentdb'];ch=true;}if(c.plugins&&Array.isArray(c.plugins.allow)){const n=c.plugins.allow.filter(x=>x!=='memory-tencentdb'&&x!=='@tencentdb-agent-memory/memory-tencentdb');if(n.length!==c.plugins.allow.length){c.plugins.allow=n;ch=true;}}if(c.skills&&c.skills.entries&&c.skills.entries['learning-memory']){delete c.skills.entries['learning-memory'];ch=true;}if(ch)fs.writeFileSync(p,JSON.stringify(c,null,2));}`;
+    // One-shot upgrade for projects created by an older setup (their openclaw.json was
+    // generated before these defaults existed, and bot-config-gen only runs when a bot is
+    // created/regenerated — so a plain rebuild would never pick them up):
+    //   • skills.workshop.approvalPolicy:'auto' → the assistant can author a workspace
+    //     skill end-to-end on request instead of stopping at "proposal awaiting approval".
+    //   • imageMaxDimensionPx / imageQuality / contextLimits.toolResultMaxChars → keep one
+    //     heavy turn (deep research, 4K chart read-back) from overflowing the context
+    //     window mid tool-loop, which cannot be compacted and poisons the session.
+    // Each key is only filled in when absent, so an operator's own tuning is never clobbered.
+    const contextDefaultsScript = `const fs=require('fs'),path=require('path');const p=path.join(process.cwd(),'.openclaw','openclaw.json');if(fs.existsSync(p)){const c=JSON.parse(fs.readFileSync(p,'utf8'));let ch=false;c.skills=c.skills||{};c.skills.workshop=c.skills.workshop||{};if(!c.skills.workshop.approvalPolicy){c.skills.workshop.approvalPolicy='auto';ch=true;}const d=(c.agents&&c.agents.defaults)?c.agents.defaults:null;if(d){if(d.imageMaxDimensionPx===undefined){d.imageMaxDimensionPx=1024;ch=true;}if(d.imageQuality===undefined){d.imageQuality='efficient';ch=true;}d.contextLimits=d.contextLimits||{};if(d.contextLimits.toolResultMaxChars===undefined){d.contextLimits.toolResultMaxChars=12000;ch=true;}}if(ch)fs.writeFileSync(p,JSON.stringify(c,null,2));}`;
+    // Companion backfill for the same older projects: their TOOLS.md was generated before the
+    // skill-authoring / long-turn guidance existed, and workspace files are only written when a
+    // bot is created — so a rebuild alone leaves the assistant stopping at "proposal awaiting
+    // approval" even once approvalPolicy is 'auto'. (TOOLS.md is listed in AGENTS.md as required
+    // reading, so guidance lands there rather than in the main manual.) Appends the block once
+    // per workspace, keyed off the `skill_workshop` marker, never rewriting a file that has it.
+    const agentsGuidanceScript = `const fs=require('fs'),path=require('path');const vi=['','## 🛠️ Tự tạo skill & việc dài','','**Tự tạo skill:** Khi user nhờ tạo một kỹ năng/quy trình dùng lại (vd _"tạo skill X"_), bạn TỰ làm từ đầu đến cuối — dùng tool **skill_workshop**: tạo proposal RỒI **apply luôn trong cùng lượt** (môi trường này bật approvalPolicy auto, không cần chờ ai duyệt). Skill ghi vào skills/<tên>/SKILL.md và **tự nạp** qua watcher — KHÔNG cần sửa openclaw.json. Đừng dừng ở _"đã tạo proposal, chờ duyệt"_. KHÔNG nhúng bí mật vào skill — đọc từ biến môi trường lúc chạy.','','**Việc dài, nhiều bước (research sâu, dựng báo cáo/PDF):** ảnh/chart bạn vừa tạo thì **đừng đọc lại** bằng tool ảnh (chèn thẳng file vào tài liệu; kiểm bằng file tồn tại / build thành công) — đọc lại ảnh lớn ngốn ngữ cảnh gấp nhiều lần bạn tưởng. Tạo hình cạnh dài khoảng 1280px, đừng 4K trừ khi user yêu cầu. Research nhiều nguồn thì dùng **sessions_spawn** mỗi nhánh một subagent, bảo chúng **ghi dữ liệu thô ra file** và **chỉ trả tóm tắt ngắn kèm đường dẫn**; bạn tổng hợp từ file.',''].join('\\n');const en=['','## 🛠️ Authoring skills & long work','','**Authoring skills:** When the user asks for a reusable capability (e.g. _"make a skill for X"_), do it end-to-end — use the **skill_workshop** tool: create the proposal AND **apply it in the same turn** (this environment sets approvalPolicy auto, so no separate approval is needed). The skill lands in skills/<name>/SKILL.md and **auto-loads** via the watcher — no openclaw.json edit required. Do not stop at _"proposal created, awaiting approval"_. Never hardcode secrets into a skill — read them from environment variables at runtime.','','**Long multi-step work (deep research, building reports/PDFs):** do not read back an image or chart you just made (drop the file straight in; verify via file exists / build succeeded) — re-reading a large image costs far more context than it looks. Render at about 1280px on the long edge, skip 4K unless asked. For multi-source research, use **sessions_spawn** with one subagent per branch, have them **write raw findings to files** and **return only a short summary plus paths**; synthesize from the files.',''].join('\\n');const root=path.join(process.cwd(),'.openclaw');let dirs=[];try{dirs=fs.readdirSync(root).filter(n=>n.indexOf('workspace')===0);}catch(e){}for(const d of dirs){const f=path.join(root,d,'TOOLS.md');try{if(!fs.existsSync(f))continue;const cur=fs.readFileSync(f,'utf8');if(cur.indexOf('skill_workshop')!==-1)continue;const isVi=/Kỹ năng|Ghi chú|Xử lý lỗi|môi trường/.test(cur);fs.appendFileSync(f,(cur.endsWith('\\n')?'':'\\n')+(isVi?vi:en));}catch(e){}}`;
     const securityCompatScript = `const fs=require('fs'),path=require('path');const scopes=['operator.admin','operator.pairing','operator.approvals'];function uniq(a){return Array.from(new Set([...(Array.isArray(a)?a:[]),...scopes]));}function walk(v){if(!v||typeof v!=='object')return;if(Array.isArray(v)){v.forEach(walk);return;}if(Array.isArray(v.scopes)||Array.isArray(v.approvedScopes)){v.scopes=uniq(v.scopes);v.approvedScopes=uniq(v.approvedScopes);}Object.values(v).forEach(walk);}const home=process.env.OPENCLAW_HOME||path.join(process.cwd(),'.openclaw');const state=process.env.OPENCLAW_STATE_DIR||home;const cfgPath=path.join(process.cwd(),'.openclaw','openclaw.json');if(fs.existsSync(cfgPath)){const c=JSON.parse(fs.readFileSync(cfgPath,'utf8'));const p=c.models&&c.models.providers&&c.models.providers['9router'];if(p){p.request=Object.assign({},p.request,{allowPrivateNetwork:true});}fs.writeFileSync(cfgPath,JSON.stringify(c,null,2));}for(const root of Array.from(new Set([home,state]))){const f=path.join(root,'devices','paired.json');if(fs.existsSync(f)){const d=JSON.parse(fs.readFileSync(f,'utf8'));walk(d);fs.writeFileSync(f,JSON.stringify(d,null,2));}}`;
 
     const runtimeParts = runtimeCommandParts.filter(Boolean);
@@ -323,6 +345,16 @@ if(touched){console.log('[patch-9router] Applied Codex compatibility patch.');}e
       const zaloConnectSpec = common.ZALO_CONNECT_PLUGIN_SPEC || 'clawhub:openclaw-zalo-connect';
       runtimeParts.push(`ensure_plugin zalo-connect "${zaloConnectSpec}"`);
     }
+    // Always-on memory context engine for every bot (see bot-config-gen: plugins.slots
+    // .contextEngine = "learning-memory"). ensure_plugin skips if already installed.
+    runtimeParts.push('ensure_plugin learning-memory "clawhub:openclaw-learning-memory"');
+    // Migrate off the deprecated learning-memory SKILL + memory-tencentdb plugin (older setups).
+    runtimeParts.push(`node - <<'NODE'\n${deprecatedCleanupScript}\nNODE`);
+    runtimeParts.push('find "$OPENCLAW_HOME" -maxdepth 4 -type d -path "*/skills/learning-memory" -exec rm -rf {} + 2>/dev/null || true');
+    runtimeParts.push('if [ -d "$OPENCLAW_HOME/extensions/memory-tencentdb" ] || openclaw plugins list 2>/dev/null | grep -q memory-tencentdb; then openclaw plugins uninstall memory-tencentdb --force 2>/dev/null || true; fi');
+    // Backfill skill-authoring + context defaults for configs from an older setup (see above).
+    runtimeParts.push(`node - <<'NODE'\n${contextDefaultsScript}\nNODE`);
+    runtimeParts.push(`node - <<'NODE'\n${agentsGuidanceScript}\nNODE`);
     runtimeParts.push('openclaw gateway run');
     const runtimeScript = ['#!/bin/sh', 'set -e', ...runtimeParts].join('\n');
     let browserInstall = '';

package/dist/setup/shared/workspace-gen.js

@@ -1231,6 +1231,14 @@ Skills dùng chung. Setup là của riêng bạn. Tách ra nghĩa là cập nh
 
 - Xem chi tiết hướng dẫn các kỹ năng được cài đặt tại thư mục [skills](./skills/).
 
+**🛠️ Tự tạo skill:** Khi user nhờ tạo một kỹ năng/quy trình dùng lại (vd _"tạo skill X"_), bạn TỰ làm được từ đầu đến cuối — dùng tool \`skill_workshop\`: tạo proposal RỒI **apply luôn trong cùng lượt** (môi trường này đã bật \`approvalPolicy: auto\` nên không cần chờ ai duyệt). Skill sẽ được ghi vào \`skills/<tên>/SKILL.md\` trong workspace và **tự nạp** qua watcher — KHÔNG cần sửa \`openclaw.json\`. Đừng dừng ở bước _"đã tạo proposal, chờ sếp duyệt rồi áp dụng"_: user bảo tạo nghĩa là tạo xong dùng được ngay. Tuyệt đối KHÔNG nhúng bí mật (mật khẩu/token/tài khoản) vào nội dung skill — đọc chúng từ biến môi trường lúc chạy.
+
+**🧠 Việc dài, nhiều bước (research sâu, dựng báo cáo/PDF):** cửa sổ ngữ cảnh là tài nguyên — một lượt nhồi quá nhiều sẽ vỡ giữa đường và KHÔNG nén lại được. Ba quy tắc:
+
+- **Ảnh/chart bạn vừa tạo thì đừng đọc lại** bằng tool ảnh để "xem cho chắc". Chèn thẳng file vào tài liệu; muốn kiểm thì xem file có tồn tại / build thành công. Đọc lại một ảnh lớn tốn ngữ cảnh gấp nhiều lần bạn tưởng.
+- **Tạo hình ở cỡ vừa đủ** (cạnh dài ~1280px là đẹp cho báo cáo). Đừng làm 4K trừ khi user yêu cầu rõ.
+- **Research nhiều nguồn thì chia việc:** \`sessions_spawn\` mỗi nhánh một subagent (mỗi con có cửa sổ riêng), bảo chúng **ghi dữ liệu thô ra file** trong workspace và **chỉ trả về tóm tắt ngắn kèm đường dẫn file**. Bạn tổng hợp từ file. Đừng tự mình kéo hàng chục trang web vào một lượt.
+
 ## 📁 File & Workspace
 
 - Bot có thể đọc/ghi file trong thư mục workspace: \`${workspacePath}\`
@@ -1282,6 +1290,14 @@ Skills are shared. Your setup is yours. Keeping them apart means you can update
 
 - See detailed guidelines of installed skills in the [skills](./skills/) directory.
 
+**🛠️ Authoring skills:** When the user asks you to build a reusable capability (e.g. _"make a skill for X"_), you can do it end-to-end — use the \`skill_workshop\` tool: create the proposal AND **apply it in the same turn** (this environment sets \`approvalPolicy: auto\`, so no separate approval is needed). The skill lands in \`skills/<name>/SKILL.md\` in the workspace and **auto-loads** via the watcher — no \`openclaw.json\` edit required. Don't stop at _"proposal created, awaiting approval"_: if they asked you to build it, finish it so it works right away. Never hardcode secrets (passwords/tokens/accounts) into a skill's contents — read them from environment variables at runtime.
+
+**🧠 Long multi-step work (deep research, building reports/PDFs):** the context window is a budget — cram too much into one turn and it blows up mid-flight, with nothing left to compact. Three rules:
+
+- **Don't read back an image or chart you just made** to "double-check" it. Drop the file straight into the document; verify by checking the file exists or that the build succeeded. Re-reading a large image costs far more context than it looks.
+- **Render images at a sane size** (~1280px on the long edge looks great in a report). Skip 4K unless the user explicitly asks.
+- **Split multi-source research:** \`sessions_spawn\` one subagent per branch (each gets its own window), have them **write raw findings to files** in the workspace and **return only a short summary plus the file paths**. You synthesize from the files. Don't pull dozens of web pages into a single turn yourself.
+
 ## 📁 File & Workspace
 
 - Bot can read/write files in workspace: \`${workspacePath}\`

package/dist/web/app.js

@@ -1061,11 +1061,10 @@ function botSkillsPanel() {
     { id: 'cron', title: 'Cron', desc: 'Native scheduler (SQLite) — cron guide in TOOLS.md' },
     { id: 'image-gen', title: 'Tạo ảnh Infographic', desc: 'Tạo ảnh infographic, poster tự động qua 9Router' },
     { id: 'web-search', title: 'Web Search', desc: 'Tìm kiếm web thời gian thực (DuckDuckGo)' },
-    { id: 'learning-memory', title: 'Siêu Trí Nhớ Dài Hạn (learning-memory)', desc: 'Tự động ghi nhớ bài học vào MEMORY.md, tự đóng gói và tiến hóa kỹ năng mới vào skills/' },
   ];
   const plugins = [
     { id: 'zalo-connect', title: 'OpenClaw Zalo Connect', desc: t('Kênh Zalo cá nhân (zca-js) — BẮT BUỘC cho bot Zalo. Tự cài khi tạo bot Zalo đầu tiên; bấm Cập nhật để lên bản mới nhất.', 'Personal Zalo channel (zca-js) — REQUIRED for Zalo bots. Auto-installed with your first Zalo bot; click Update for the latest version.'), channels: ['zalo-personal'] },
-    { id: 'memory-tencentdb', title: 'TencentDB Agent Memory', desc: 'Bộ nhớ phân tầng L0–L3 + nén ngữ cảnh: nhớ tốt session dài, tiết kiệm ~61% token (local SQLite, không cần API)' },
+    { id: 'learning-memory', title: 'Siêu Trí Nhớ Dài Hạn (learning-memory)', desc: t('Bộ nhớ always-on: nạp MEMORY.md + USER.md đã chắt lọc vào MỌI lượt — kể cả trong nhóm — nên bot không quên ngữ cảnh/quy tắc. Tự cài khi tạo bot.', 'Always-on memory: injects a curated MEMORY.md + USER.md into every turn — including group chats — so the bot stops forgetting context and rules. Auto-installed on bot creation.') },
     { id: 'openclaw-browser-automation', title: 'openclaw-browser-automation', desc: 'Smart Search + Browser (headless & Chrome thật)' },
     { id: 'openclaw-zalo-mod', title: 'openclaw-zalo-mod', desc: 'Zalo group helpers', channels: ['zalo-personal'], openWebPort: 18790, openWebPath: '/dashboard' },
     { id: 'openclaw-fb-messenger', title: 'openclaw-fb-messenger', desc: t('Kênh Facebook Messenger — webhook + Graph API (bắt buộc cho bot Messenger)', 'Facebook Messenger channel — webhook + Graph API (required for Messenger bots)'), channels: ['fb-messenger'] },
@@ -1085,7 +1084,7 @@ function botSkillsPanel() {
     const key = `${group}:${item.id}`;
     const loading = !!state.featureLoading[key];
     const locked = !!state.featureLocked?.[key];
-    const requiresInstall = group === 'plugin' || (group === 'skill' && (item.id === 'image-gen' || item.id === 'learning-memory'));
+    const requiresInstall = group === 'plugin' || (group === 'skill' && item.id === 'image-gen');
     const isInstalled = !requiresInstall || !!state.featureInstalled?.[key] || locked;
     
     const version = requiresInstall && isInstalled ? (state.featureVersions?.[key] || '') : '';

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "create-openclaw-bot",
-  "version": "5.13.8",
+  "version": "5.14.0",
   "description": "Interactive CLI installer for OpenClaw Bot",
   "main": "dist/cli.js",
   "bin": {