diff --git a/.github/workflows/pr.yml b/.github/workflows/pr.yml
index a839715c9..1e9a7919a 100644
--- a/.github/workflows/pr.yml
+++ b/.github/workflows/pr.yml
@@ -1,7 +1,7 @@
 name: PR
 
 on:
-  pull_request: {}
+  pull_request: { }
 
 jobs:
   lint:
@@ -16,9 +16,6 @@ jobs:
         with:
           go-version-file: go.mod
 
-      - name: Setup Bun
-        uses: oven-sh/setup-bun@v2
-
       - name: Run go generate
         run: go generate ./...
 
@@ -58,26 +55,8 @@ jobs:
         with:
           go-version-file: go.mod
 
-      - name: Setup Bun
-        uses: oven-sh/setup-bun@v2
-
-      - name: Setup Node
-        uses: actions/setup-node@v6
-        with:
-          node-version: '24'
-
-      - name: Setup pnpm
-        uses: pnpm/action-setup@v4
-        with:
-          version: 10
-
       - name: Run go generate
         run: go generate ./...
 
-      - name: Run frontend tests
-        run: |
-          pnpm --dir pkg/miniapp/frontend install --frozen-lockfile
-          pnpm --dir pkg/miniapp/frontend test
-
       - name: Run go test
         run: go test ./...
diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
index 0edd29f22..4a584773d 100644
--- a/.github/workflows/release.yml
+++ b/.github/workflows/release.yml
@@ -65,6 +65,14 @@ jobs:
         with:
           go-version-file: go.mod
 
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 22
+
+      - name: Setup pnpm
+        run: corepack enable && corepack prepare pnpm@latest --activate
+
       - name: Set up QEMU
         uses: docker/setup-qemu-action@v3
 
@@ -96,6 +104,11 @@ jobs:
           GITHUB_REPOSITORY_OWNER: ${{ github.repository_owner }}
           DOCKERHUB_IMAGE_NAME: ${{ vars.DOCKERHUB_REPOSITORY }}
           GOVERSION: ${{ steps.setup-go.outputs.go-version }}
+          MACOS_SIGN_P12: ${{ secrets.MACOS_SIGN_P12 }}
+          MACOS_SIGN_PASSWORD: ${{ secrets.MACOS_SIGN_PASSWORD }}
+          MACOS_NOTARY_ISSUER_ID: ${{ secrets.MACOS_NOTARY_ISSUER_ID }}
+          MACOS_NOTARY_KEY_ID: ${{ secrets.MACOS_NOTARY_KEY_ID }}
+          MACOS_NOTARY_KEY: ${{ secrets.MACOS_NOTARY_KEY }}
 
       - name: Apply release flags
         shell: bash
diff --git a/.gitignore b/.gitignore
index d9fe0d5a9..61fe494ca 100644
--- a/.gitignore
+++ b/.gitignore
@@ -47,14 +47,12 @@ docs/plans/
 
 # Added by goreleaser init:
 dist/
-!pkg/miniapp/static/dist/
-!pkg/miniapp/static/dist/**
+*.vite/
 
 # Windows Application Icon/Resource
 *.syso
 
-
-# Frontend dependencies
-node_modules/
-
-
+# Keep embedded backend dist directory placeholder in VCS
+!web/backend/dist/
+web/backend/dist/*
+!web/backend/dist/.gitkeep
diff --git a/.goreleaser.yaml b/.goreleaser.yaml
index d531d106b..622cf054b 100644
--- a/.goreleaser.yaml
+++ b/.goreleaser.yaml
@@ -6,8 +6,9 @@ before:
   hooks:
     - go mod tidy
     - go generate ./...
+    - sh -c 'cd web/frontend && pnpm install && pnpm build:backend'
     - go install github.com/tc-hib/go-winres@latest
-    - go-winres make --in cmd/picoclaw-launcher/winres/winres.json --out cmd/picoclaw-launcher/rsrc --product-version={{ .Version }} --file-version={{ .Version }}
+    - go-winres make --in web/backend/winres/winres.json --out web/backend/rsrc --product-version={{ .Version }} --file-version={{ .Version }}
 
 builds:
   - id: picoclaw
@@ -17,10 +18,10 @@ builds:
       - stdjson
     ldflags:
       - -s -w
-      - -X github.com/sipeed/picoclaw/cmd/picoclaw/internal.version={{ .Version }}
-      - -X github.com/sipeed/picoclaw/cmd/picoclaw/internal.gitCommit={{ .ShortCommit }}
-      - -X github.com/sipeed/picoclaw/cmd/picoclaw/internal.buildTime={{ .Date }}
-      - -X github.com/sipeed/picoclaw/cmd/picoclaw/internal.goVersion={{ .Env.GOVERSION }}
+      - -X github.com/sipeed/picoclaw/pkg/config.Version={{ .Version }}
+      - -X github.com/sipeed/picoclaw/pkg/config.GitCommit={{ .ShortCommit }}
+      - -X github.com/sipeed/picoclaw/pkg/config.BuildTime={{ .Date }}
+      - -X github.com/sipeed/picoclaw/pkg/config.GoVersion={{ .Env.GOVERSION }}
     goos:
       - linux
       - windows
@@ -32,9 +33,13 @@ builds:
       - riscv64
       - loong64
       - arm
+      - s390x
+      - mipsle
     goarm:
       - "6"
       - "7"
+    gomips:
+      - softfloat
     main: ./cmd/picoclaw
     ignore:
       - goos: windows
@@ -59,10 +64,14 @@ builds:
       - riscv64
       - loong64
       - arm
+      - s390x
+      - mipsle
     goarm:
       - "6"
       - "7"
-    main: ./cmd/picoclaw-launcher
+    gomips:
+      - softfloat
+    main: ./web/backend
     ignore:
       - goos: windows
         goarch: arm
@@ -86,9 +95,13 @@ builds:
       - riscv64
       - loong64
       - arm
+      - s390x
+      - mipsle
     goarm:
       - "6"
       - "7"
+    gomips:
+      - softfloat
     main: ./cmd/picoclaw-launcher-tui
     ignore:
       - goos: windows
@@ -103,15 +116,49 @@ dockers_v2:
       - picoclaw
     images:
       - "ghcr.io/{{ .Env.GITHUB_REPOSITORY_OWNER }}/picoclaw"
-      - "docker.io/{{ .Env.DOCKERHUB_IMAGE_NAME }}"
+      - 'docker.io/{{ .Env.DOCKERHUB_IMAGE_NAME }}'
     tags:
-      - "{{ .Tag }}"
-      - "latest"
+      - '{{ if isEnvSet "NIGHTLY_BUILD" }}nightly{{ else }}{{ .Tag }}{{ end }}'
+      - '{{ if isEnvSet "NIGHTLY_BUILD" }}nightly{{ else }}latest{{ end }}'
     platforms:
       - linux/amd64
       - linux/arm64
       - linux/riscv64
 
+  - id: picoclaw-launcher
+    dockerfile: docker/Dockerfile.goreleaser.launcher
+    ids:
+      - picoclaw
+      - picoclaw-launcher
+      - picoclaw-launcher-tui
+    images:
+      - "ghcr.io/{{ .Env.GITHUB_REPOSITORY_OWNER }}/picoclaw"
+      - 'docker.io/{{ .Env.DOCKERHUB_IMAGE_NAME }}'
+    tags:
+      - '{{ if isEnvSet "NIGHTLY_BUILD" }}nightly-launcher{{ else }}{{ .Tag }}-launcher{{ end }}'
+      - '{{ if isEnvSet "NIGHTLY_BUILD" }}nightly-launcher{{ else }}launcher{{ end }}'
+    platforms:
+      - linux/amd64
+      - linux/arm64
+      - linux/riscv64
+
+notarize:
+  macos:
+    - enabled: '{{ isEnvSet "MACOS_SIGN_P12" }}'
+      ids:
+        - picoclaw
+        - picoclaw-launcher
+        - picoclaw-launcher-tui
+      sign:
+        certificate: "{{.Env.MACOS_SIGN_P12}}"
+        password: "{{.Env.MACOS_SIGN_PASSWORD}}"
+      notarize:
+        issuer_id: "{{.Env.MACOS_NOTARY_ISSUER_ID}}"
+        key_id: "{{.Env.MACOS_NOTARY_KEY_ID}}"
+        key: "{{.Env.MACOS_NOTARY_KEY}}"
+        wait: true
+        timeout: 20m
+
 archives:
   - formats: [tar.gz]
     # this name template makes the OS and Arch compatible with the results of `uname`.
@@ -129,7 +176,7 @@ archives:
 
 nfpms:
   - id: picoclaw
-    builds:
+    ids:
       - picoclaw
       - picoclaw-launcher
       - picoclaw-launcher-tui
@@ -149,6 +196,11 @@ nfpms:
       - rpm
       - deb
     bindir: /usr/bin
+    contents:
+      - src: web/picoclaw-launcher.desktop
+        dst: /usr/share/applications/picoclaw-launcher.desktop
+      - src: web/picoclaw-launcher.png
+        dst: /usr/share/icons/hicolor/512x512/apps/picoclaw-launcher.png
 
 changelog:
   sort: asc
@@ -163,6 +215,7 @@ changelog:
 #      lzma: true
 
 release:
+  disable: '{{ isEnvSet "NIGHTLY_BUILD" }}'
   footer: >-
 
     ---
diff --git a/Makefile b/Makefile
index 428e386c5..98642703f 100644
--- a/Makefile
+++ b/Makefile
@@ -11,8 +11,8 @@ VERSION?=$(shell git describe --tags --always --dirty 2>/dev/null || echo "dev")
 GIT_COMMIT=$(shell git rev-parse --short=8 HEAD 2>/dev/null || echo "dev")
 BUILD_TIME=$(shell date +%FT%T%z)
 GO_VERSION=$(shell $(GO) version | awk '{print $$3}')
-INTERNAL=github.com/sipeed/picoclaw/cmd/picoclaw/internal
-LDFLAGS=-ldflags "-X $(INTERNAL).version=$(VERSION) -X $(INTERNAL).gitCommit=$(GIT_COMMIT) -X $(INTERNAL).buildTime=$(BUILD_TIME) -X $(INTERNAL).goVersion=$(GO_VERSION) -s -w"
+CONFIG_PKG=github.com/sipeed/picoclaw/pkg/config
+LDFLAGS=-ldflags "-X $(CONFIG_PKG).Version=$(VERSION) -X $(CONFIG_PKG).GitCommit=$(GIT_COMMIT) -X $(CONFIG_PKG).BuildTime=$(BUILD_TIME) -X $(CONFIG_PKG).GoVersion=$(GO_VERSION) -s -w"
 
 # Go variables
 GO?=CGO_ENABLED=0 go
@@ -110,12 +110,18 @@ build: generate
 	@$(GO) build $(GOFLAGS) $(LDFLAGS) -o $(BINARY_PATH) ./$(CMD_DIR)
 	@echo "Build complete: $(BINARY_PATH)"
 	@ln -sf $(BINARY_NAME)-$(PLATFORM)-$(ARCH) $(BUILD_DIR)/$(BINARY_NAME)
-	@if [ "$(PLATFORM)" = "linux" ] || [ "$(PLATFORM)" = "darwin" ]; then \
-		echo "Install to /usr/local/bin:"; \
-		echo "  sudo install -m 755 $(BINARY_PATH) /usr/local/bin/$(BINARY_NAME)"; \
-	else \
-		echo "Install hint skipped: /usr/local/bin command is for Linux/macOS (current: $(PLATFORM))."; \
+
+## build-launcher: Build the picoclaw-launcher (web console) binary
+build-launcher:
+	@echo "Building picoclaw-launcher for $(PLATFORM)/$(ARCH)..."
+	@mkdir -p $(BUILD_DIR)
+	@if [ ! -f web/backend/dist/index.html ]; then \
+		echo "Building frontend..."; \
+		cd web/frontend && pnpm install && pnpm build:backend; \
 	fi
+	@$(GO) build $(GOFLAGS) -o $(BUILD_DIR)/picoclaw-launcher-$(PLATFORM)-$(ARCH) ./web/backend
+	@ln -sf picoclaw-launcher-$(PLATFORM)-$(ARCH) $(BUILD_DIR)/picoclaw-launcher
+	@echo "Build complete: $(BUILD_DIR)/picoclaw-launcher"
 
 ## build-whatsapp-native: Build with WhatsApp native (whatsmeow) support; larger binary
 build-whatsapp-native: generate
diff --git a/README.fr.md b/README.fr.md
index 08a1926b6..1d5a3a256 100644
--- a/README.fr.md
+++ b/README.fr.md
@@ -1,5 +1,5 @@
 <div align="center">
-  <img src="assets/logo.jpg" alt="PicoClaw" width="512">
+  <img src="assets/logo.webp" alt="PicoClaw" width="512">
 
   <h1>PicoClaw : Assistant IA Ultra-Efficace en Go</h1>
 
@@ -206,9 +206,7 @@ docker compose -f docker/docker-compose.yml --profile gateway up -d
 ### 🚀 Démarrage Rapide
 
 > [!TIP]
-> Configurez votre clé API dans `~/.picoclaw/config.json`.
-> Obtenir des clés API : [OpenRouter](https://openrouter.ai/keys) (LLM) · [Zhipu](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) (LLM)
-> La recherche web est **optionnelle** — obtenez gratuitement l'[API Brave Search](https://brave.com/search/api) (2000 requêtes gratuites/mois) ou utilisez le repli automatique intégré.
+> Configurez votre clé API dans `~/.picoclaw/config.json`. Obtenez des clés API : [Volcengine (CodingPlan)](https://console.volcengine.com) (LLM) · [OpenRouter](https://openrouter.ai/keys) (LLM) · [Zhipu](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) (LLM). La recherche web est optionnelle — obtenez gratuitement l'[API Tavily](https://tavily.com) (1000 requêtes gratuites/mois) ou l'[API Brave Search](https://brave.com/search/api) (2000 requêtes gratuites/mois).
 
 **1. Initialiser**
 
@@ -222,8 +220,13 @@ picoclaw onboard
 {
   "model_list": [
     {
-      "model_name": "gpt4",
-      "model": "openai/gpt-5.2",
+      "model_name": "ark-code-latest",
+      "model": "volcengine/ark-code-latest",
+      "api_key": "sk-your-api-key"
+    },
+    {
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_key": "sk-your-openai-key",
       "request_timeout": 300,
       "api_base": "https://api.openai.com/v1"
@@ -231,7 +234,7 @@ picoclaw onboard
   ],
   "agents": {
     "defaults": {
-      "model_name": "gpt4"
+      "model_name": "gpt-5.4"
     }
   },
   "channels": {
@@ -649,7 +652,6 @@ PicoClaw stocke les données dans votre workspace configuré (par défaut : `~/.
 ├── HEARTBEAT.md      # Invites de tâches périodiques (vérifiées toutes les 30 min)
 ├── IDENTITY.md       # Identité de l'Agent
 ├── SOUL.md           # Âme de l'Agent
-├── TOOLS.md          # Description des outils
 └── USER.md           # Préférences utilisateur
 ```
 
@@ -978,8 +980,10 @@ Cette conception permet également le **support multi-agent** avec une sélectio
 | **OpenRouter** | `openrouter/` | `https://openrouter.ai/api/v1` | OpenAI | [Obtenir Clé](https://openrouter.ai/keys) |
 | **VLLM** | `vllm/` | `http://localhost:8000/v1` | OpenAI | Local |
 | **Cerebras** | `cerebras/` | `https://api.cerebras.ai/v1` | OpenAI | [Obtenir Clé](https://cerebras.ai) |
-| **Volcengine** | `volcengine/` | `https://ark.cn-beijing.volces.com/api/v3` | OpenAI | [Obtenir Clé](https://console.volcengine.com) |
+| **VolcEngine (Doubao)** | `volcengine/` | `https://ark.cn-beijing.volces.com/api/v3` | OpenAI | [Obtenir Clé](https://console.volcengine.com) |
 | **ShengsuanYun** | `shengsuanyun/` | `https://router.shengsuanyun.com/api/v1` | OpenAI | - |
+| **BytePlus**        | `byteplus/`       | `https://ark.ap-southeast.bytepluses.com/api/v3`    | OpenAI    | [Obtenir Clé](https://console.volcengine.com)                    |
+| **LongCat**         | `longcat/`        | `https://api.longcat.chat/openai`                   | OpenAI    | [Obtenir une clé](https://longcat.chat/platform)                 |
 | **Antigravity** | `antigravity/` | Google Cloud | Custom | OAuth uniquement |
 | **GitHub Copilot** | `github-copilot/` | `localhost:4321` | gRPC | - |
 
@@ -989,8 +993,13 @@ Cette conception permet également le **support multi-agent** avec une sélectio
 {
   "model_list": [
     {
-      "model_name": "gpt-5.2",
-      "model": "openai/gpt-5.2",
+      "model_name": "ark-code-latest",
+      "model": "volcengine/ark-code-latest",
+      "api_key": "sk-your-api-key"
+    },
+    {
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_key": "sk-your-openai-key"
     },
     {
@@ -1006,7 +1015,7 @@ Cette conception permet également le **support multi-agent** avec une sélectio
   ],
   "agents": {
     "defaults": {
-      "model": "gpt-5.2"
+      "model": "gpt-5.4"
     }
   }
 }
@@ -1017,8 +1026,17 @@ Cette conception permet également le **support multi-agent** avec une sélectio
 **OpenAI**
 ```json
 {
-  "model_name": "gpt-5.2",
-  "model": "openai/gpt-5.2",
+  "model_name": "gpt-5.4",
+  "model": "openai/gpt-5.4",
+  "api_key": "sk-..."
+}
+```
+
+**VolcEngine (Doubao)**
+```json
+{
+  "model_name": "ark-code-latest",
+  "model": "volcengine/ark-code-latest",
   "api_key": "sk-..."
 }
 ```
@@ -1061,14 +1079,14 @@ Configurez plusieurs points de terminaison pour le même nom de modèle—PicoCl
 {
   "model_list": [
     {
-      "model_name": "gpt-5.2",
-      "model": "openai/gpt-5.2",
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_base": "https://api1.example.com/v1",
       "api_key": "sk-key1"
     },
     {
-      "model_name": "gpt-5.2",
-      "model": "openai/gpt-5.2",
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_base": "https://api2.example.com/v1",
       "api_key": "sk-key2"
     }
@@ -1200,6 +1218,13 @@ Cela se produit lorsqu'une autre instance du bot est en cours d'exécution. Assu
 | Service          | Offre Gratuite       | Cas d'Utilisation                     |
 | ---------------- | -------------------- | ------------------------------------- |
 | **OpenRouter**   | 200K tokens/mois     | Multiples modèles (Claude, GPT-4, etc.) |
-| **Zhipu**        | 200K tokens/mois     | Idéal pour les utilisateurs chinois   |
+| **Volcengine CodingPlan** | 9,9¥/premier mois | Idéal pour les utilisateurs chinois, multiples modèles SOTA (Doubao, DeepSeek, etc.) |
+| **Zhipu**        | 200K tokens/mois     | Convient aux utilisateurs chinois   |
 | **Brave Search** | 2000 requêtes/mois   | Fonctionnalité de recherche web       |
 | **Groq**         | Offre gratuite dispo | Inférence ultra-rapide (Llama, Mixtral) |
+
+---
+
+<div align="center">
+  <img src="assets/logo.jpg" alt="PicoClaw Meme" width="512">
+</div>
diff --git a/README.ja.md b/README.ja.md
index c4c5b27a0..d41975294 100644
--- a/README.ja.md
+++ b/README.ja.md
@@ -1,5 +1,5 @@
 <div align="center">
-<img src="assets/logo.jpg" alt="PicoClaw" width="512">
+<img src="assets/logo.webp" alt="PicoClaw" width="512">
 
 <h1>PicoClaw: Go で書かれた超効率 AI アシスタント</h1>
 
@@ -168,9 +168,7 @@ docker compose -f docker/docker-compose.yml --profile gateway up -d
 ### 🚀 クイックスタート（ネイティブ）
 
 > [!TIP]
-> `~/.picoclaw/config.json` に API キーを設定してください。
-> API キーの取得先: [OpenRouter](https://openrouter.ai/keys) (LLM) · [Zhipu](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) (LLM)
-> Web 検索は **任意** です - 無料の [Tavily API](https://tavily.com) (月 1000 クエリ無料) または [Brave Search API](https://brave.com/search/api) (月 2000 クエリ無料)
+> `~/.picoclaw/config.json` に API キーを設定してください。API キーの取得先: [Volcengine (CodingPlan)](https://console.volcengine.com) (LLM) · [OpenRouter](https://openrouter.ai/keys) (LLM) · [Zhipu](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) (LLM)。Web 検索は **任意** です — 無料の [Tavily API](https://tavily.com) (月 1000 クエリ無料) または [Brave Search API](https://brave.com/search/api) (月 2000 クエリ無料)。
 
 **1. 初期化**
 
@@ -184,8 +182,13 @@ picoclaw onboard
 {
   "model_list": [
     {
-      "model_name": "gpt4",
-      "model": "openai/gpt-5.2",
+      "model_name": "ark-code-latest",
+      "model": "volcengine/ark-code-latest",
+      "api_key": "sk-your-api-key"
+    },
+    {
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_key": "sk-your-openai-key",
       "request_timeout": 300,
       "api_base": "https://api.openai.com/v1"
@@ -193,7 +196,7 @@ picoclaw onboard
   ],
   "agents": {
     "defaults": {
-      "model_name": "gpt4"
+      "model_name": "gpt-5.4"
     }
   },
   "channels": {
@@ -610,7 +613,6 @@ PicoClaw は設定されたワークスペース（デフォルト: `~/.picoclaw
 ├── HEARTBEAT.md       # 定期タスクプロンプト（30分ごとに確認）
 ├── IDENTITY.md        # エージェントのアイデンティティ
 ├── SOUL.md            # エージェントのソウル
-├── TOOLS.md           # ツールの説明
 └── USER.md            # ユーザー設定
 ```
 
@@ -919,8 +921,10 @@ HEARTBEAT_OK 応答         ユーザーが直接結果を受け取る
 | **OpenRouter** | `openrouter/` | `https://openrouter.ai/api/v1` | OpenAI | [キーを取得](https://openrouter.ai/keys) |
 | **VLLM** | `vllm/` | `http://localhost:8000/v1` | OpenAI | ローカル |
 | **Cerebras** | `cerebras/` | `https://api.cerebras.ai/v1` | OpenAI | [キーを取得](https://cerebras.ai) |
-| **Volcengine** | `volcengine/` | `https://ark.cn-beijing.volces.com/api/v3` | OpenAI | [キーを取得](https://console.volcengine.com) |
+| **VolcEngine (Doubao)** | `volcengine/` | `https://ark.cn-beijing.volces.com/api/v3` | OpenAI | [キーを取得](https://console.volcengine.com) |
 | **ShengsuanYun** | `shengsuanyun/` | `https://router.shengsuanyun.com/api/v1` | OpenAI | - |
+| **BytePlus**        | `byteplus/`       | `https://ark.ap-southeast.bytepluses.com/api/v3`    | OpenAI    | [キーを取得](https://console.volcengine.com)                     |
+| **LongCat**         | `longcat/`        | `https://api.longcat.chat/openai`                   | OpenAI    | [キーを取得](https://longcat.chat/platform)                      |
 | **Antigravity** | `antigravity/` | Google Cloud | カスタム | OAuthのみ |
 | **GitHub Copilot** | `github-copilot/` | `localhost:4321` | gRPC | - |
 
@@ -930,8 +934,13 @@ HEARTBEAT_OK 応答         ユーザーが直接結果を受け取る
 {
   "model_list": [
     {
-      "model_name": "gpt-5.2",
-      "model": "openai/gpt-5.2",
+      "model_name": "ark-code-latest",
+      "model": "volcengine/ark-code-latest",
+      "api_key": "sk-your-api-key"
+    },
+    {
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_key": "sk-your-openai-key"
     },
     {
@@ -947,7 +956,7 @@ HEARTBEAT_OK 応答         ユーザーが直接結果を受け取る
   ],
   "agents": {
     "defaults": {
-      "model": "gpt-5.2"
+      "model": "gpt-5.4"
     }
   }
 }
@@ -958,8 +967,17 @@ HEARTBEAT_OK 応答         ユーザーが直接結果を受け取る
 **OpenAI**
 ```json
 {
-  "model_name": "gpt-5.2",
-  "model": "openai/gpt-5.2",
+  "model_name": "gpt-5.4",
+  "model": "openai/gpt-5.4",
+  "api_key": "sk-..."
+}
+```
+
+**VolcEngine (Doubao)**
+```json
+{
+  "model_name": "ark-code-latest",
+  "model": "volcengine/ark-code-latest",
   "api_key": "sk-..."
 }
 ```
@@ -1002,14 +1020,14 @@ HEARTBEAT_OK 応答         ユーザーが直接結果を受け取る
 {
   "model_list": [
     {
-      "model_name": "gpt-5.2",
-      "model": "openai/gpt-5.2",
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_base": "https://api1.example.com/v1",
       "api_key": "sk-key1"
     },
     {
-      "model_name": "gpt-5.2",
-      "model": "openai/gpt-5.2",
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_base": "https://api2.example.com/v1",
       "api_key": "sk-key2"
     }
@@ -1120,9 +1138,16 @@ Web 検索を有効にするには：
 | サービス | 無料枠 | ユースケース |
 |---------|--------|------------|
 | **OpenRouter** | 月 200K トークン | 複数モデル（Claude, GPT-4 など） |
-| **Zhipu** | 月 200K トークン | 中国ユーザー向け最適 |
+| **Volcengine CodingPlan** | 9.9元/初月 | 中国ユーザーに最適、複数のSOTAモデル（Doubao、DeepSeek等） |
+| **Zhipu** | 月 200K トークン | 中国ユーザーに適している |
 | **Qwen** | 無料枠あり | 通義千問 (Qwen) |
 | **Brave Search** | 月 2000 クエリ | Web 検索機能 |
 | **Tavily** | 月 1000 クエリ | AI エージェント検索最適化 |
 | **Groq** | 無料枠あり | 高速推論（Llama, Mixtral） |
 | **Cerebras** | 無料枠あり | 高速推論（Llama, Qwen など） |
+
+---
+
+<div align="center">
+  <img src="assets/logo.jpg" alt="PicoClaw Meme" width="512">
+</div>
diff --git a/README.md b/README.md
index 5cf9f6143..ebcd6dddf 100644
--- a/README.md
+++ b/README.md
@@ -1,5 +1,5 @@
 <div align="center">
-  <img src="assets/logo.jpg" alt="PicoClaw" width="512">
+  <img src="assets/logo.webp" alt="PicoClaw" width="512">
 
   <h1>PicoClaw: Ultra-Efficient AI Assistant in Go</h1>
 
@@ -194,6 +194,19 @@ docker compose -f docker/docker-compose.yml logs -f picoclaw-gateway
 docker compose -f docker/docker-compose.yml --profile gateway down
 ```
 
+### Launcher Mode (Web Console)
+
+The `launcher` image includes all three binaries (`picoclaw`, `picoclaw-launcher`, `picoclaw-launcher-tui`) and starts the web console by default, which provides a browser-based UI for configuration and chat.
+
+```bash
+docker compose -f docker/docker-compose.yml --profile launcher up -d
+```
+
+Open http://localhost:18800 in your browser. The launcher manages the gateway process automatically.
+
+> [!WARNING]
+> The web console does not yet support authentication. Avoid exposing it to the public internet.
+
 ### Agent Mode (One-shot)
 
 ```bash
@@ -214,9 +227,7 @@ docker compose -f docker/docker-compose.yml --profile gateway up -d
 ### 🚀 Quick Start
 
 > [!TIP]
-> Set your API key in `~/.picoclaw/config.json`.
-> Get API keys: [OpenRouter](https://openrouter.ai/keys) (LLM) · [Zhipu](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) (LLM)
-> Web Search is **optional** - get free [Tavily API](https://tavily.com) (1000 free queries/month), [SearXNG](https://github.com/searxng/searxng) (free, self-hosted) or [Brave Search API](https://brave.com/search/api) (2000 free queries/month) or use built-in auto fallback.
+> Set your API Key in `~/.picoclaw/config.json`. Get API Keys: [Volcengine (CodingPlan)](https://console.volcengine.com) (LLM) · [OpenRouter](https://openrouter.ai/keys) (LLM) · [Zhipu](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) (LLM). Web search is optional — get a free [Tavily API](https://tavily.com) (1000 free queries/month) or [Brave Search API](https://brave.com/search/api) (2000 free queries/month).
 
 **1. Initialize**
 
@@ -231,7 +242,7 @@ picoclaw onboard
   "agents": {
     "defaults": {
       "workspace": "~/.picoclaw/workspace",
-      "model_name": "gpt4",
+      "model_name": "gpt-5.4",
       "max_tokens": 8192,
       "temperature": 0.7,
       "max_tool_iterations": 20
@@ -239,8 +250,13 @@ picoclaw onboard
   },
   "model_list": [
     {
-      "model_name": "gpt4",
-      "model": "openai/gpt-5.2",
+      "model_name": "ark-code-latest",
+      "model": "volcengine/ark-code-latest",
+      "api_key": "sk-your-api-key"
+    },
+    {
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_key": "your-api-key",
       "request_timeout": 300
     },
@@ -774,7 +790,6 @@ PicoClaw stores data in your configured workspace (default: `~/.picoclaw/workspa
 ├── HEARTBEAT.md      # Periodic task prompts (checked every 30 min)
 ├── IDENTITY.md       # Agent identity
 ├── SOUL.md           # Agent soul
-├── TOOLS.md          # Tool descriptions
 └── USER.md           # User preferences
 ```
 
@@ -1018,9 +1033,11 @@ This design also enables **multi-agent support** with flexible provider selectio
 | **LiteLLM Proxy**   | `litellm/`        | `http://localhost:4000/v1`                          | OpenAI    | Your LiteLLM proxy key                                            |
 | **VLLM**            | `vllm/`           | `http://localhost:8000/v1`                          | OpenAI    | Local                                                            |
 | **Cerebras**        | `cerebras/`       | `https://api.cerebras.ai/v1`                        | OpenAI    | [Get Key](https://cerebras.ai)                                   |
-| **火山引擎**        | `volcengine/`     | `https://ark.cn-beijing.volces.com/api/v3`          | OpenAI    | [Get Key](https://console.volcengine.com)                        |
+| **VolcEngine (Doubao)** | `volcengine/`     | `https://ark.cn-beijing.volces.com/api/v3`          | OpenAI    | [Get Key](https://console.volcengine.com)                        |
 | **神算云**          | `shengsuanyun/`   | `https://router.shengsuanyun.com/api/v1`            | OpenAI    | -                                                                |
+| **BytePlus**        | `byteplus/`       | `https://ark.ap-southeast.bytepluses.com/api/v3`    | OpenAI    | [Get Key](https://console.volcengine.com)                        |
 | **Vivgrid**         | `vivgrid/`        | `https://api.vivgrid.com/v1`                        | OpenAI    | [Get Key](https://vivgrid.com)                                   |
+| **LongCat**         | `longcat/`        | `https://api.longcat.chat/openai`                   | OpenAI    | [Get Key](https://longcat.chat/platform)                         |
 | **Antigravity**     | `antigravity/`    | Google Cloud                                        | Custom    | OAuth only                                                       |
 | **GitHub Copilot**  | `github-copilot/` | `localhost:4321`                                    | gRPC      | -                                                                |
 
@@ -1030,8 +1047,13 @@ This design also enables **multi-agent support** with flexible provider selectio
 {
   "model_list": [
     {
-      "model_name": "gpt-5.2",
-      "model": "openai/gpt-5.2",
+      "model_name": "ark-code-latest",
+      "model": "volcengine/ark-code-latest",
+      "api_key": "sk-your-api-key"
+    },
+    {
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_key": "sk-your-openai-key"
     },
     {
@@ -1047,7 +1069,7 @@ This design also enables **multi-agent support** with flexible provider selectio
   ],
   "agents": {
     "defaults": {
-      "model": "gpt-5.2"
+      "model": "gpt-5.4"
     }
   }
 }
@@ -1059,8 +1081,18 @@ This design also enables **multi-agent support** with flexible provider selectio
 
 ```json
 {
-  "model_name": "gpt-5.2",
-  "model": "openai/gpt-5.2",
+  "model_name": "gpt-5.4",
+  "model": "openai/gpt-5.4",
+  "api_key": "sk-..."
+}
+```
+
+**VolcEngine (Doubao)**
+
+```json
+{
+  "model_name": "ark-code-latest",
+  "model": "volcengine/ark-code-latest",
   "api_key": "sk-..."
 }
 ```
@@ -1139,14 +1171,14 @@ Configure multiple endpoints for the same model name—PicoClaw will automatical
 {
   "model_list": [
     {
-      "model_name": "gpt-5.2",
-      "model": "openai/gpt-5.2",
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_base": "https://api1.example.com/v1",
       "api_key": "sk-key1"
     },
     {
-      "model_name": "gpt-5.2",
-      "model": "openai/gpt-5.2",
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_base": "https://api2.example.com/v1",
       "api_key": "sk-key2"
     }
@@ -1486,8 +1518,16 @@ This happens when another instance of the bot is running. Make sure only one `pi
 | Service          | Free Tier                | Use Case                              |
 | ---------------- | ------------------------ | ------------------------------------- |
 | **OpenRouter**   | 200K tokens/month        | Multiple models (Claude, GPT-4, etc.) |
-| **Zhipu**        | 200K tokens/month        | Best for Chinese users                |
+| **Volcengine CodingPlan** | ¥9.9/first month | Best for Chinese users, multiple SOTA models (Doubao, DeepSeek, etc.) |
+| **Zhipu**        | 200K tokens/month        | Suitable for Chinese users                |
 | **Brave Search** | Paid ($5/1000 queries)   | Web search functionality              |
 | **SearXNG**      | Unlimited (self-hosted)  | Privacy-focused metasearch (70+ engines) |
 | **Groq**         | Free tier available      | Fast inference (Llama, Mixtral)       |
 | **Cerebras**     | Free tier available      | Fast inference (Llama, Qwen, etc.)    |
+| **LongCat**      | Up to 5M tokens/day      | Fast inference (free tier)            |
+
+---
+
+<div align="center">
+  <img src="assets/logo.jpg" alt="PicoClaw Meme" width="512">
+</div>
diff --git a/README.pt-br.md b/README.pt-br.md
index 5f37ba457..474cb199c 100644
--- a/README.pt-br.md
+++ b/README.pt-br.md
@@ -1,5 +1,5 @@
 <div align="center">
-<img src="assets/logo.jpg" alt="PicoClaw" width="512">
+<img src="assets/logo.webp" alt="PicoClaw" width="512">
 
 <h1>PicoClaw: Assistente de IA Ultra-Eficiente em Go</h1>
 
@@ -207,9 +207,7 @@ docker compose -f docker/docker-compose.yml --profile gateway up -d
 ### 🚀 Início Rápido
 
 > [!TIP]
-> Configure sua API key em `~/.picoclaw/config.json`.
-> Obtenha API keys: [OpenRouter](https://openrouter.ai/keys) (LLM) · [Zhipu](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) (LLM)
-> Busca web e **opcional** — obtenha a [Brave Search API](https://brave.com/search/api) gratuita (2000 consultas grátis/mês) ou use o fallback automático integrado.
+> Configure sua API key em `~/.picoclaw/config.json`. Obtenha API keys: [Volcengine (CodingPlan)](https://console.volcengine.com) (LLM) · [OpenRouter](https://openrouter.ai/keys) (LLM) · [Zhipu](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) (LLM). Busca web é **opcional** — obtenha a [API Tavily](https://tavily.com) gratuita (1000 consultas grátis/mês) ou a [Brave Search API](https://brave.com/search/api) (2000 consultas grátis/mês).
 
 **1. Inicializar**
 
@@ -223,8 +221,13 @@ picoclaw onboard
 {
   "model_list": [
     {
-      "model_name": "gpt4",
-      "model": "openai/gpt-5.2",
+      "model_name": "ark-code-latest",
+      "model": "volcengine/ark-code-latest",
+      "api_key": "sk-your-api-key"
+    },
+    {
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_key": "sk-your-openai-key",
       "request_timeout": 300,
       "api_base": "https://api.openai.com/v1"
@@ -232,7 +235,7 @@ picoclaw onboard
   ],
   "agents": {
     "defaults": {
-      "model_name": "gpt4"
+      "model_name": "gpt-5.4"
     }
   },
   "tools": {
@@ -645,7 +648,6 @@ O PicoClaw armazena dados no workspace configurado (padrão: `~/.picoclaw/worksp
 ├── HEARTBEAT.md       # Prompts de tarefas periodicas (verificado a cada 30 min)
 ├── IDENTITY.md        # Identidade do Agente
 ├── SOUL.md            # Alma do Agente
-├── TOOLS.md           # Descrição das ferramentas
 └── USER.md            # Preferencias do usuario
 ```
 
@@ -974,8 +976,10 @@ Este design também possibilita o **suporte multi-agent** com seleção flexíve
 | **OpenRouter** | `openrouter/` | `https://openrouter.ai/api/v1` | OpenAI | [Obter Chave](https://openrouter.ai/keys) |
 | **VLLM** | `vllm/` | `http://localhost:8000/v1` | OpenAI | Local |
 | **Cerebras** | `cerebras/` | `https://api.cerebras.ai/v1` | OpenAI | [Obter Chave](https://cerebras.ai) |
-| **Volcengine** | `volcengine/` | `https://ark.cn-beijing.volces.com/api/v3` | OpenAI | [Obter Chave](https://console.volcengine.com) |
+| **VolcEngine (Doubao)** | `volcengine/` | `https://ark.cn-beijing.volces.com/api/v3` | OpenAI | [Obter Chave](https://console.volcengine.com) |
 | **ShengsuanYun** | `shengsuanyun/` | `https://router.shengsuanyun.com/api/v1` | OpenAI | - |
+| **BytePlus**        | `byteplus/`       | `https://ark.ap-southeast.bytepluses.com/api/v3`    | OpenAI    | [Obter Chave](https://console.volcengine.com)                    |
+| **LongCat**         | `longcat/`        | `https://api.longcat.chat/openai`                   | OpenAI    | [Obter Chave](https://longcat.chat/platform)                     |
 | **Antigravity** | `antigravity/` | Google Cloud | Custom | Apenas OAuth |
 | **GitHub Copilot** | `github-copilot/` | `localhost:4321` | gRPC | - |
 
@@ -985,8 +989,13 @@ Este design também possibilita o **suporte multi-agent** com seleção flexíve
 {
   "model_list": [
     {
-      "model_name": "gpt-5.2",
-      "model": "openai/gpt-5.2",
+      "model_name": "ark-code-latest",
+      "model": "volcengine/ark-code-latest",
+      "api_key": "sk-your-api-key"
+    },
+    {
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_key": "sk-your-openai-key"
     },
     {
@@ -1002,7 +1011,7 @@ Este design também possibilita o **suporte multi-agent** com seleção flexíve
   ],
   "agents": {
     "defaults": {
-      "model": "gpt-5.2"
+      "model": "gpt-5.4"
     }
   }
 }
@@ -1013,8 +1022,17 @@ Este design também possibilita o **suporte multi-agent** com seleção flexíve
 **OpenAI**
 ```json
 {
-  "model_name": "gpt-5.2",
-  "model": "openai/gpt-5.2",
+  "model_name": "gpt-5.4",
+  "model": "openai/gpt-5.4",
+  "api_key": "sk-..."
+}
+```
+
+**VolcEngine (Doubao)**
+```json
+{
+  "model_name": "ark-code-latest",
+  "model": "volcengine/ark-code-latest",
   "api_key": "sk-..."
 }
 ```
@@ -1057,14 +1075,14 @@ Configure vários endpoints para o mesmo nome de modelo—PicoClaw fará round-r
 {
   "model_list": [
     {
-      "model_name": "gpt-5.2",
-      "model": "openai/gpt-5.2",
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_base": "https://api1.example.com/v1",
       "api_key": "sk-key1"
     },
     {
-      "model_name": "gpt-5.2",
-      "model": "openai/gpt-5.2",
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_base": "https://api2.example.com/v1",
       "api_key": "sk-key2"
     }
@@ -1196,7 +1214,14 @@ Isso acontece quando outra instância do bot está em execução. Certifique-se
 | Serviço | Plano Gratuito | Caso de Uso |
 | --- | --- | --- |
 | **OpenRouter** | 200K tokens/mês | Múltiplos modelos (Claude, GPT-4, etc.) |
-| **Zhipu** | 200K tokens/mês | Melhor para usuários chineses |
+| **Volcengine CodingPlan** | ¥9,9/primeiro mês | Ideal para usuários chineses, múltiplos modelos SOTA (Doubao, DeepSeek, etc.) |
+| **Zhipu** | 200K tokens/mês | Adequado para usuários chineses |
 | **Brave Search** | 2000 consultas/mês | Funcionalidade de busca web |
 | **Groq** | Plano gratuito disponível | Inferência ultra-rápida (Llama, Mixtral) |
 | **Cerebras** | Plano gratuito disponível | Inferência ultra-rápida (Llama 3.3 70B) |
+
+---
+
+<div align="center">
+  <img src="assets/logo.jpg" alt="PicoClaw Meme" width="512">
+</div>
diff --git a/README.vi.md b/README.vi.md
index 92c6ecbae..38eed4d4d 100644
--- a/README.vi.md
+++ b/README.vi.md
@@ -1,5 +1,5 @@
 <div align="center">
-<img src="assets/logo.jpg" alt="PicoClaw" width="512">
+<img src="assets/logo.webp" alt="PicoClaw" width="512">
 
 <h1>PicoClaw: Trợ lý AI Siêu Nhẹ viết bằng Go</h1>
 
@@ -187,9 +187,7 @@ docker compose -f docker/docker-compose.yml --profile gateway up -d
 ### 🚀 Bắt đầu nhanh
 
 > [!TIP]
-> Thiết lập API key trong `~/.picoclaw/config.json`.
-> Lấy API key: [OpenRouter](https://openrouter.ai/keys) (LLM) · [Zhipu](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) (LLM)
-> Tìm kiếm web là **tùy chọn** — lấy [Brave Search API](https://brave.com/search/api) miễn phí (2000 truy vấn/tháng) hoặc dùng tính năng auto fallback tích hợp sẵn.
+> Thiết lập API key trong `~/.picoclaw/config.json`. Lấy API key: [Volcengine (CodingPlan)](https://console.volcengine.com) (LLM) · [OpenRouter](https://openrouter.ai/keys) (LLM) · [Zhipu](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) (LLM). Tìm kiếm web là **tùy chọn** — lấy [Tavily API](https://tavily.com) miễn phí (1000 truy vấn/tháng) hoặc [Brave Search API](https://brave.com/search/api) (2000 truy vấn/tháng).
 
 **1. Khởi tạo**
 
@@ -203,8 +201,13 @@ picoclaw onboard
 {
   "model_list": [
     {
-      "model_name": "gpt4",
-      "model": "openai/gpt-5.2",
+      "model_name": "ark-code-latest",
+      "model": "volcengine/ark-code-latest",
+      "api_key": "sk-your-api-key"
+    },
+    {
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_key": "sk-your-openai-key",
       "request_timeout": 300,
       "api_base": "https://api.openai.com/v1"
@@ -617,7 +620,6 @@ PicoClaw lưu trữ dữ liệu trong workspace đã cấu hình (mặc định:
 ├── HEARTBEAT.md      # Prompt tác vụ định kỳ (kiểm tra mỗi 30 phút)
 ├── IDENTITY.md       # Danh tính Agent
 ├── SOUL.md           # Tâm hồn/Tính cách Agent
-├── TOOLS.md          # Mô tả công cụ
 └── USER.md           # Tùy chọn người dùng
 ```
 
@@ -943,8 +945,10 @@ Thiết kế này cũng cho phép **hỗ trợ đa tác nhân** với lựa ch
 | **OpenRouter** | `openrouter/` | `https://openrouter.ai/api/v1` | OpenAI | [Lấy Khóa](https://openrouter.ai/keys) |
 | **VLLM** | `vllm/` | `http://localhost:8000/v1` | OpenAI | Local |
 | **Cerebras** | `cerebras/` | `https://api.cerebras.ai/v1` | OpenAI | [Lấy Khóa](https://cerebras.ai) |
-| **Volcengine** | `volcengine/` | `https://ark.cn-beijing.volces.com/api/v3` | OpenAI | [Lấy Khóa](https://console.volcengine.com) |
+| **VolcEngine (Doubao)** | `volcengine/` | `https://ark.cn-beijing.volces.com/api/v3` | OpenAI | [Lấy Khóa](https://console.volcengine.com) |
 | **ShengsuanYun** | `shengsuanyun/` | `https://router.shengsuanyun.com/api/v1` | OpenAI | - |
+| **BytePlus**        | `byteplus/`       | `https://ark.ap-southeast.bytepluses.com/api/v3`    | OpenAI    | [Lấy Khóa](https://console.volcengine.com)                      |
+| **LongCat**         | `longcat/`        | `https://api.longcat.chat/openai`                   | OpenAI    | [Lấy Key](https://longcat.chat/platform)                        |
 | **Antigravity** | `antigravity/` | Google Cloud | Tùy chỉnh | Chỉ OAuth |
 | **GitHub Copilot** | `github-copilot/` | `localhost:4321` | gRPC | - |
 
@@ -954,8 +958,13 @@ Thiết kế này cũng cho phép **hỗ trợ đa tác nhân** với lựa ch
 {
   "model_list": [
     {
-      "model_name": "gpt-5.2",
-      "model": "openai/gpt-5.2",
+      "model_name": "ark-code-latest",
+      "model": "volcengine/ark-code-latest",
+      "api_key": "sk-your-api-key"
+    },
+    {
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_key": "sk-your-openai-key"
     },
     {
@@ -971,7 +980,7 @@ Thiết kế này cũng cho phép **hỗ trợ đa tác nhân** với lựa ch
   ],
   "agents": {
     "defaults": {
-      "model": "gpt-5.2"
+      "model": "gpt-5.4"
     }
   }
 }
@@ -982,8 +991,17 @@ Thiết kế này cũng cho phép **hỗ trợ đa tác nhân** với lựa ch
 **OpenAI**
 ```json
 {
-  "model_name": "gpt-5.2",
-  "model": "openai/gpt-5.2",
+  "model_name": "gpt-5.4",
+  "model": "openai/gpt-5.4",
+  "api_key": "sk-..."
+}
+```
+
+**VolcEngine (Doubao)**
+```json
+{
+  "model_name": "ark-code-latest",
+  "model": "volcengine/ark-code-latest",
   "api_key": "sk-..."
 }
 ```
@@ -1026,14 +1044,14 @@ Thiết kế này cũng cho phép **hỗ trợ đa tác nhân** với lựa ch
 {
   "model_list": [
     {
-      "model_name": "gpt-5.2",
-      "model": "openai/gpt-5.2",
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_base": "https://api1.example.com/v1",
       "api_key": "sk-key1"
     },
     {
-      "model_name": "gpt-5.2",
-      "model": "openai/gpt-5.2",
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_base": "https://api2.example.com/v1",
       "api_key": "sk-key2"
     }
@@ -1165,6 +1183,13 @@ Một số nhà cung cấp (như Zhipu) có bộ lọc nội dung nghiêm ngặt
 | Dịch vụ | Gói miễn phí | Trường hợp sử dụng |
 | --- | --- | --- |
 | **OpenRouter** | 200K tokens/tháng | Đa model (Claude, GPT-4, v.v.) |
-| **Zhipu** | 200K tokens/tháng | Tốt nhất cho người dùng Trung Quốc |
+| **Volcengine CodingPlan** | ¥9.9/tháng đầu | Tốt nhất cho người dùng Trung Quốc, nhiều mô hình SOTA (Doubao, DeepSeek, v.v.) |
+| **Zhipu** | 200K tokens/tháng | Phù hợp cho người dùng Trung Quốc |
 | **Brave Search** | 2000 truy vấn/tháng | Chức năng tìm kiếm web |
 | **Groq** | Có gói miễn phí | Suy luận siêu nhanh (Llama, Mixtral) |
+
+---
+
+<div align="center">
+  <img src="assets/logo.jpg" alt="PicoClaw Meme" width="512">
+</div>
diff --git a/README.zh.md b/README.zh.md
index c744e0d20..6395b1e7b 100644
--- a/README.zh.md
+++ b/README.zh.md
@@ -1,5 +1,5 @@
 <div align="center">
-<img src="assets/logo.jpg" alt="PicoClaw" width="512">
+<img src="assets/logo.webp" alt="PicoClaw" width="512">
 
 <h1>PicoClaw: 基于Go语言的超高效 AI 助手</h1>
 
@@ -208,9 +208,7 @@ docker compose -f docker/docker-compose.yml --profile gateway up -d
 ### 🚀 快速开始
 
 > [!TIP]
-> 在 `~/.picoclaw/config.json` 中设置您的 API Key。
-> 获取 API Key: [OpenRouter](https://openrouter.ai/keys) (LLM) · [Zhipu (智谱)](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) (LLM)
-> 网络搜索是 **可选的** - 获取免费的 [Tavily API](https://tavily.com) (每月 1000 次免费查询) 或 [Brave Search API](https://brave.com/search/api) (每月 2000 次免费查询)
+> 在 `~/.picoclaw/config.json` 中设置您的 API Key。获取 API Key: [火山引擎 (CodingPlan)](https://console.volcengine.com) (LLM) · [OpenRouter](https://openrouter.ai/keys) (LLM) · [Zhipu (智谱)](https://open.bigmodel.cn/usercenter/proj-mgmt/apikeys) (LLM)。网络搜索是 **可选的** — 获取免费的 [Tavily API](https://tavily.com) (每月 1000 次免费查询) 或 [Brave Search API](https://brave.com/search/api) (每月 2000 次免费查询)。
 
 **1. 初始化 (Initialize)**
 
@@ -226,7 +224,7 @@ picoclaw onboard
   "agents": {
     "defaults": {
       "workspace": "~/.picoclaw/workspace",
-      "model_name": "gpt4",
+      "model_name": "gpt-5.4",
       "max_tokens": 8192,
       "temperature": 0.7,
       "max_tool_iterations": 20
@@ -234,8 +232,13 @@ picoclaw onboard
   },
   "model_list": [
     {
-      "model_name": "gpt4",
-      "model": "openai/gpt-5.2",
+      "model_name": "ark-code-latest",
+      "model": "volcengine/ark-code-latest",
+      "api_key": "sk-your-api-key"
+    },
+    {
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_key": "your-api-key",
       "request_timeout": 300
     },
@@ -365,7 +368,6 @@ PicoClaw 将数据存储在您配置的工作区中（默认：`~/.picoclaw/work
 ├── HEARTBEAT.md      # 周期性任务提示词 (每 30 分钟检查一次)
 ├── IDENTITY.md       # Agent 身份设定
 ├── SOUL.md           # Agent 灵魂/性格
-├── TOOLS.md          # 工具描述
 └── USER.md           # 用户偏好
 
 ```
@@ -515,8 +517,10 @@ Agent 读取 HEARTBEAT.md
 | **OpenRouter**      | `openrouter/`     | `https://openrouter.ai/api/v1`                      | OpenAI    | [获取密钥](https://openrouter.ai/keys)                            |
 | **VLLM**            | `vllm/`           | `http://localhost:8000/v1`                          | OpenAI    | 本地                                                              |
 | **Cerebras**        | `cerebras/`       | `https://api.cerebras.ai/v1`                        | OpenAI    | [获取密钥](https://cerebras.ai)                                   |
-| **火山引擎**        | `volcengine/`     | `https://ark.cn-beijing.volces.com/api/v3`          | OpenAI    | [获取密钥](https://console.volcengine.com)                        |
+| **火山引擎（Doubao）**        | `volcengine/`     | `https://ark.cn-beijing.volces.com/api/v3`          | OpenAI    | [获取密钥](https://console.volcengine.com)                        |
 | **神算云**          | `shengsuanyun/`   | `https://router.shengsuanyun.com/api/v1`            | OpenAI    | -                                                                 |
+| **BytePlus**        | `byteplus/`       | `https://ark.ap-southeast.bytepluses.com/api/v3`    | OpenAI    | [获取密钥](https://console.volcengine.com)                        |
+| **LongCat**         | `longcat/`        | `https://api.longcat.chat/openai`                   | OpenAI    | [获取密钥](https://longcat.chat/platform)                        |
 | **Antigravity**     | `antigravity/`    | Google Cloud                                        | 自定义    | 仅 OAuth                                                          |
 | **GitHub Copilot**  | `github-copilot/` | `localhost:4321`                                    | gRPC      | -                                                                 |
 
@@ -526,8 +530,13 @@ Agent 读取 HEARTBEAT.md
 {
   "model_list": [
     {
-      "model_name": "gpt-5.2",
-      "model": "openai/gpt-5.2",
+      "model_name": "ark-code-latest",
+      "model": "volcengine/ark-code-latest",
+      "api_key": "sk-your-api-key"
+    },
+    {
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_key": "sk-your-openai-key"
     },
     {
@@ -543,7 +552,7 @@ Agent 读取 HEARTBEAT.md
   ],
   "agents": {
     "defaults": {
-      "model": "gpt-5.2"
+      "model": "gpt-5.4"
     }
   }
 }
@@ -555,8 +564,18 @@ Agent 读取 HEARTBEAT.md
 
 ```json
 {
-  "model_name": "gpt-5.2",
-  "model": "openai/gpt-5.2",
+  "model_name": "gpt-5.4",
+  "model": "openai/gpt-5.4",
+  "api_key": "sk-..."
+}
+```
+
+**火山引擎（Doubao）**
+
+```json
+{
+  "model_name": "ark-code-latest",
+  "model": "volcengine/ark-code-latest",
   "api_key": "sk-..."
 }
 ```
@@ -622,14 +641,14 @@ Agent 读取 HEARTBEAT.md
 {
   "model_list": [
     {
-      "model_name": "gpt-5.2",
-      "model": "openai/gpt-5.2",
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_base": "https://api1.example.com/v1",
       "api_key": "sk-key1"
     },
     {
-      "model_name": "gpt-5.2",
-      "model": "openai/gpt-5.2",
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_base": "https://api2.example.com/v1",
       "api_key": "sk-key2"
     }
@@ -875,7 +894,15 @@ Discord: [https://discord.gg/V4sAZ9XWpN](https://discord.gg/V4sAZ9XWpN)
 | 服务 | 免费层级 | 适用场景 |
 | --- | --- | --- |
 | **OpenRouter** | 200K tokens/月 | 多模型聚合 (Claude, GPT-4 等) |
-| **智谱 (Zhipu)** | 200K tokens/月 | 最适合中国用户 |
+| **火山引擎 CodingPlan** | 9.9 元/首月 | 最适合国内用户，多种 SOTA 模型（豆包、DeepSeek 等） |
+| **智谱 (Zhipu)** | 200K tokens/月 | 适合中国用户 |
 | **Brave Search** | 2000 次查询/月 | 网络搜索功能 |
 | **Tavily** | 1000 次查询/月 | AI Agent 搜索优化 |
 | **Groq** | 提供免费层级 | 极速推理 (Llama, Mixtral) |
+| **LongCat** | 最多 5M tokens/天 | 推理速度快 (免费额度) |
+
+---
+
+<div align="center">
+  <img src="assets/logo.jpg" alt="PicoClaw Meme" width="512">
+</div>
diff --git a/cmd/picoclaw-launcher-tui/internal/ui/channel.go b/cmd/picoclaw-launcher-tui/internal/ui/channel.go
index 16b7d053b..2f28af123 100644
--- a/cmd/picoclaw-launcher-tui/internal/ui/channel.go
+++ b/cmd/picoclaw-launcher-tui/internal/ui/channel.go
@@ -12,7 +12,6 @@ import (
 
 func (s *appState) buildChannelMenuItems() []MenuItem {
 	return []MenuItem{
-		{Label: "Back", Description: "Return to main menu", Action: func() { s.pop() }},
 		channelItem(
 			"Telegram",
 			"Telegram bot settings",
@@ -101,10 +100,6 @@ func (s *appState) channelMenu() tview.Primitive {
 			s.pop()
 			return nil
 		}
-		if event.Rune() == 'q' {
-			s.pop()
-			return nil
-		}
 		return event
 	})
 	return menu
diff --git a/cmd/picoclaw-launcher-tui/internal/ui/style.go b/cmd/picoclaw-launcher-tui/internal/ui/style.go
index 68cdd60b9..da3c3526d 100644
--- a/cmd/picoclaw-launcher-tui/internal/ui/style.go
+++ b/cmd/picoclaw-launcher-tui/internal/ui/style.go
@@ -41,3 +41,15 @@ func bannerView() *tview.TextView {
 	text.SetBorder(false)
 	return text
 }
+
+const footerText = "Esc: Back/Exit | Enter: Enter | ←↓↑→ : Move | Space: Select | Tab/Shift+Tab: Switch"
+
+func footerView() *tview.TextView {
+	text := tview.NewTextView()
+	text.SetTextAlign(tview.AlignCenter)
+	text.SetText(footerText)
+	text.SetBackgroundColor(tview.Styles.MoreContrastBackgroundColor)
+	text.SetTextColor(tview.Styles.PrimaryTextColor)
+	text.SetBorder(false)
+	return text
+}
diff --git a/cmd/picoclaw/internal/agent/command.go b/cmd/picoclaw/internal/agent/command.go
index 8939ddb2c..47262fc85 100644
--- a/cmd/picoclaw/internal/agent/command.go
+++ b/cmd/picoclaw/internal/agent/command.go
@@ -6,11 +6,10 @@ import (
 
 func NewAgentCommand() *cobra.Command {
 	var (
-		message              string
-		sessionKey           string
-		model                string
-		debug                bool
-		orchestrationEnabled bool
+		message    string
+		sessionKey string
+		model      string
+		debug      bool
 	)
 
 	cmd := &cobra.Command{
@@ -18,7 +17,7 @@ func NewAgentCommand() *cobra.Command {
 		Short: "Interact with the agent directly",
 		Args:  cobra.NoArgs,
 		RunE: func(cmd *cobra.Command, _ []string) error {
-			return agentCmd(message, sessionKey, model, debug, orchestrationEnabled)
+			return agentCmd(message, sessionKey, model, debug)
 		},
 	}
 
@@ -26,7 +25,6 @@ func NewAgentCommand() *cobra.Command {
 	cmd.Flags().StringVarP(&message, "message", "m", "", "Send a single message (non-interactive mode)")
 	cmd.Flags().StringVarP(&sessionKey, "session", "s", "cli:default", "Session key")
 	cmd.Flags().StringVarP(&model, "model", "", "", "Model to use")
-	cmd.Flags().BoolVar(&orchestrationEnabled, "orchestration", false, "Enable orchestration mode")
 
 	return cmd
 }
diff --git a/cmd/picoclaw/internal/agent/helpers.go b/cmd/picoclaw/internal/agent/helpers.go
index fab1bc54c..a995945d2 100644
--- a/cmd/picoclaw/internal/agent/helpers.go
+++ b/cmd/picoclaw/internal/agent/helpers.go
@@ -18,7 +18,7 @@ import (
 	"github.com/sipeed/picoclaw/pkg/providers"
 )
 
-func agentCmd(message, sessionKey, model string, debug, orchestrationEnabled bool) error {
+func agentCmd(message, sessionKey, model string, debug bool) error {
 	if sessionKey == "" {
 		sessionKey = "cli:default"
 	}
@@ -37,10 +37,6 @@ func agentCmd(message, sessionKey, model string, debug, orchestrationEnabled boo
 		cfg.Agents.Defaults.ModelName = model
 	}
 
-	if orchestrationEnabled {
-		cfg.Agents.Defaults.Orchestration = true
-	}
-
 	provider, modelID, err := providers.CreateProvider(cfg)
 	if err != nil {
 		return fmt.Errorf("error creating provider: %w", err)
@@ -54,6 +50,7 @@ func agentCmd(message, sessionKey, model string, debug, orchestrationEnabled boo
 	msgBus := bus.NewMessageBus()
 	defer msgBus.Close()
 	agentLoop := agent.NewAgentLoop(cfg, msgBus, provider)
+	defer agentLoop.Close()
 
 	// Print agent startup info (only for interactive mode)
 	startupInfo := agentLoop.GetStartupInfo()
diff --git a/cmd/picoclaw/internal/auth/helpers.go b/cmd/picoclaw/internal/auth/helpers.go
index a0a229167..4bf132685 100644
--- a/cmd/picoclaw/internal/auth/helpers.go
+++ b/cmd/picoclaw/internal/auth/helpers.go
@@ -72,14 +72,14 @@ func authLoginOpenAI(useDeviceCode bool) error {
 		// If no openai in ModelList, add it
 		if !foundOpenAI {
 			appCfg.ModelList = append(appCfg.ModelList, config.ModelConfig{
-				ModelName:  "gpt-5.2",
-				Model:      "openai/gpt-5.2",
+				ModelName:  "gpt-5.4",
+				Model:      "openai/gpt-5.4",
 				AuthMethod: "oauth",
 			})
 		}
 
 		// Update default model to use OpenAI
-		appCfg.Agents.Defaults.ModelName = "gpt-5.2"
+		appCfg.Agents.Defaults.ModelName = "gpt-5.4"
 
 		if err = config.SaveConfig(internal.GetConfigPath(), appCfg); err != nil {
 			return fmt.Errorf("could not update config: %w", err)
@@ -90,7 +90,7 @@ func authLoginOpenAI(useDeviceCode bool) error {
 	if cred.AccountID != "" {
 		fmt.Printf("Account: %s\n", cred.AccountID)
 	}
-	fmt.Println("Default model set to: gpt-5.2")
+	fmt.Println("Default model set to: gpt-5.4")
 
 	return nil
 }
@@ -318,13 +318,13 @@ func authLoginPasteToken(provider string) error {
 			}
 			if !found {
 				appCfg.ModelList = append(appCfg.ModelList, config.ModelConfig{
-					ModelName:  "gpt-5.2",
-					Model:      "openai/gpt-5.2",
+					ModelName:  "gpt-5.4",
+					Model:      "openai/gpt-5.4",
 					AuthMethod: "token",
 				})
 			}
 			// Update default model
-			appCfg.Agents.Defaults.ModelName = "gpt-5.2"
+			appCfg.Agents.Defaults.ModelName = "gpt-5.4"
 		}
 		if err := config.SaveConfig(internal.GetConfigPath(), appCfg); err != nil {
 			return fmt.Errorf("could not update config: %w", err)
diff --git a/cmd/picoclaw/internal/gateway/command.go b/cmd/picoclaw/internal/gateway/command.go
index 35976ff10..bfa69f072 100644
--- a/cmd/picoclaw/internal/gateway/command.go
+++ b/cmd/picoclaw/internal/gateway/command.go
@@ -1,29 +1,42 @@
 package gateway
 
 import (
+	"fmt"
+
 	"github.com/spf13/cobra"
+
+	"github.com/sipeed/picoclaw/pkg/logger"
+	"github.com/sipeed/picoclaw/pkg/utils"
 )
 
 func NewGatewayCommand() *cobra.Command {
-	var (
-		debug         bool
-		orchestration bool
-		enableStats   bool
-	)
+	var debug bool
+	var noTruncate bool
 
 	cmd := &cobra.Command{
 		Use:     "gateway",
 		Aliases: []string{"g"},
 		Short:   "Start picoclaw gateway",
 		Args:    cobra.NoArgs,
+		PreRunE: func(_ *cobra.Command, _ []string) error {
+			if noTruncate && !debug {
+				return fmt.Errorf("the --no-truncate option can only be used in conjunction with --debug (-d)")
+			}
+
+			if noTruncate {
+				utils.SetDisableTruncation(true)
+				logger.Info("String truncation is globally disabled via 'no-truncate' flag")
+			}
+
+			return nil
+		},
 		RunE: func(_ *cobra.Command, _ []string) error {
-			return gatewayCmd(debug, orchestration, enableStats)
+			return gatewayCmd(debug)
 		},
 	}
 
 	cmd.Flags().BoolVarP(&debug, "debug", "d", false, "Enable debug logging")
-	cmd.Flags().BoolVar(&orchestration, "orchestration", false, "Enable subagent orchestration")
-	cmd.Flags().BoolVar(&enableStats, "stats", false, "Enable stats tracking")
+	cmd.Flags().BoolVarP(&noTruncate, "no-truncate", "T", false, "Disable string truncation in debug logs")
 
 	return cmd
 }
diff --git a/cmd/picoclaw/internal/helpers.go b/cmd/picoclaw/internal/helpers.go
index f81d7013d..e04bccffb 100644
--- a/cmd/picoclaw/internal/helpers.go
+++ b/cmd/picoclaw/internal/helpers.go
@@ -1,23 +1,14 @@
 package internal
 
 import (
-	"fmt"
 	"os"
 	"path/filepath"
-	"runtime"
 
 	"github.com/sipeed/picoclaw/pkg/config"
 )
 
 const Logo = "🦞"
 
-var (
-	version   = "dev"
-	gitCommit string
-	buildTime string
-	goVersion string
-)
-
 // GetPicoclawHome returns the picoclaw home directory.
 // Priority: $PICOCLAW_HOME > ~/.picoclaw
 func GetPicoclawHome() string {
@@ -40,25 +31,19 @@ func LoadConfig() (*config.Config, error) {
 }
 
 // FormatVersion returns the version string with optional git commit
+// Deprecated: Use pkg/config.FormatVersion instead
 func FormatVersion() string {
-	v := version
-	if gitCommit != "" {
-		v += fmt.Sprintf(" (git: %s)", gitCommit)
-	}
-	return v
+	return config.FormatVersion()
 }
 
 // FormatBuildInfo returns build time and go version info
+// Deprecated: Use pkg/config.FormatBuildInfo instead
 func FormatBuildInfo() (string, string) {
-	build := buildTime
-	goVer := goVersion
-	if goVer == "" {
-		goVer = runtime.Version()
-	}
-	return build, goVer
+	return config.FormatBuildInfo()
 }
 
 // GetVersion returns the version string
+// Deprecated: Use pkg/config.GetVersion instead
 func GetVersion() string {
-	return version
+	return config.GetVersion()
 }
diff --git a/cmd/picoclaw/internal/onboard/command.go b/cmd/picoclaw/internal/onboard/command.go
index e89c15ab7..ec1012959 100644
--- a/cmd/picoclaw/internal/onboard/command.go
+++ b/cmd/picoclaw/internal/onboard/command.go
@@ -1,6 +1,14 @@
 package onboard
 
-import "github.com/spf13/cobra"
+import (
+	"embed"
+
+	"github.com/spf13/cobra"
+)
+
+//go:generate cp -r ../../../../workspace .
+//go:embed workspace
+var embeddedFiles embed.FS
 
 func NewOnboardCommand() *cobra.Command {
 	cmd := &cobra.Command{
diff --git a/cmd/picoclaw/internal/status/helpers.go b/cmd/picoclaw/internal/status/helpers.go
index ab28f4885..dd7063fe6 100644
--- a/cmd/picoclaw/internal/status/helpers.go
+++ b/cmd/picoclaw/internal/status/helpers.go
@@ -6,6 +6,7 @@ import (
 
 	"github.com/sipeed/picoclaw/cmd/picoclaw/internal"
 	"github.com/sipeed/picoclaw/pkg/auth"
+	"github.com/sipeed/picoclaw/pkg/config"
 )
 
 func statusCmd() {
@@ -18,8 +19,8 @@ func statusCmd() {
 	configPath := internal.GetConfigPath()
 
 	fmt.Printf("%s picoclaw Status\n", internal.Logo)
-	fmt.Printf("Version: %s\n", internal.FormatVersion())
-	build, _ := internal.FormatBuildInfo()
+	fmt.Printf("Version: %s\n", config.FormatVersion())
+	build, _ := config.FormatBuildInfo()
 	if build != "" {
 		fmt.Printf("Build: %s\n", build)
 	}
diff --git a/cmd/picoclaw/internal/version/command.go b/cmd/picoclaw/internal/version/command.go
index 1cf686671..71c7dd2f8 100644
--- a/cmd/picoclaw/internal/version/command.go
+++ b/cmd/picoclaw/internal/version/command.go
@@ -6,6 +6,7 @@ import (
 	"github.com/spf13/cobra"
 
 	"github.com/sipeed/picoclaw/cmd/picoclaw/internal"
+	"github.com/sipeed/picoclaw/pkg/config"
 )
 
 func NewVersionCommand() *cobra.Command {
@@ -22,8 +23,8 @@ func NewVersionCommand() *cobra.Command {
 }
 
 func printVersion() {
-	fmt.Printf("%s picoclaw %s\n", internal.Logo, internal.FormatVersion())
-	build, goVer := internal.FormatBuildInfo()
+	fmt.Printf("%s picoclaw %s\n", internal.Logo, config.FormatVersion())
+	build, goVer := config.FormatBuildInfo()
 	if build != "" {
 		fmt.Printf("  Build: %s\n", build)
 	}
diff --git a/cmd/picoclaw/main.go b/cmd/picoclaw/main.go
index d9263462e..b82475905 100644
--- a/cmd/picoclaw/main.go
+++ b/cmd/picoclaw/main.go
@@ -22,15 +22,16 @@ import (
 	"github.com/sipeed/picoclaw/cmd/picoclaw/internal/skills"
 	"github.com/sipeed/picoclaw/cmd/picoclaw/internal/status"
 	"github.com/sipeed/picoclaw/cmd/picoclaw/internal/version"
+	"github.com/sipeed/picoclaw/pkg/config"
 )
 
 func NewPicoclawCommand() *cobra.Command {
-	short := fmt.Sprintf("%s picoclaw - Personal AI Assistant v%s\n\n", internal.Logo, internal.GetVersion())
+	short := fmt.Sprintf("%s picoclaw - Personal AI Assistant v%s\n\n", internal.Logo, config.GetVersion())
 
 	cmd := &cobra.Command{
 		Use:     "picoclaw",
 		Short:   short,
-		Example: "picoclaw list",
+		Example: "picoclaw version",
 	}
 
 	cmd.AddCommand(
diff --git a/config/config.example.json b/config/config.example.json
index 0e2cae8e5..b259df6f6 100644
--- a/config/config.example.json
+++ b/config/config.example.json
@@ -3,7 +3,7 @@
     "defaults": {
       "workspace": "~/.picoclaw/workspace",
       "restrict_to_workspace": true,
-      "model_name": "gpt4",
+      "model_name": "gpt-5.4",
       "max_tokens": 8192,
       "temperature": 0.7,
       "max_tool_iterations": 20,
@@ -13,8 +13,8 @@
   },
   "model_list": [
     {
-      "model_name": "gpt4",
-      "model": "openai/gpt-5.2",
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_key": "sk-your-openai-key",
       "api_base": "https://api.openai.com/v1"
     },
@@ -36,14 +36,19 @@
       "api_key": "sk-your-deepseek-key"
     },
     {
-      "model_name": "loadbalanced-gpt4",
-      "model": "openai/gpt-5.2",
+      "model_name": "longcat",
+      "model": "longcat/LongCat-Flash-Thinking",
+      "api_key": "your-longcat-api-key"
+    },
+    {
+      "model_name": "loadbalanced-gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_key": "sk-key1",
       "api_base": "https://api1.example.com/v1"
     },
     {
-      "model_name": "loadbalanced-gpt4",
-      "model": "openai/gpt-5.2",
+      "model_name": "loadbalanced-gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_key": "sk-key2",
       "api_base": "https://api2.example.com/v1"
     }
@@ -194,8 +199,13 @@
       "nickserv_password": "",
       "sasl_user": "",
       "sasl_password": "",
-      "channels": ["#mychannel"],
-      "request_caps": ["server-time", "message-tags"],
+      "channels": [
+        "#mychannel"
+      ],
+      "request_caps": [
+        "server-time",
+        "message-tags"
+      ],
       "allow_from": [],
       "group_trigger": {
         "mention_only": true
@@ -269,6 +279,10 @@
     "avian": {
       "api_key": "",
       "api_base": "https://api.avian.io/v1"
+    },
+    "longcat": {
+      "api_key": "",
+      "api_base": "https://api.longcat.chat/openai"
     }
   },
   "tools": {
@@ -279,6 +293,9 @@
       "brave": {
         "enabled": false,
         "api_key": "YOUR_BRAVE_API_KEY",
+        "api_keys": [
+          "YOUR_BRAVE_API_KEY"
+        ],
         "max_results": 5
       },
       "tavily": {
@@ -293,7 +310,10 @@
       },
       "perplexity": {
         "enabled": false,
-        "api_key": "",
+        "api_key": "pplx-xxx",
+        "api_keys": [
+          "pplx-xxx"
+        ],
         "max_results": 5
       },
       "searxng": {
@@ -316,6 +336,13 @@
     },
     "mcp": {
       "enabled": false,
+      "discovery": {
+        "enabled": false,
+        "ttl": 5,
+        "max_search_results": 5,
+        "use_bm25": true,
+        "use_regex": false
+      },
       "servers": {
         "context7": {
           "enabled": false,
@@ -459,6 +486,9 @@
     "enabled": false,
     "monitor_usb": true
   },
+  "voice": {
+    "echo_transcription": false
+  },
   "gateway": {
     "host": "127.0.0.1",
     "port": 18790
diff --git a/docker/docker-compose.yml b/docker/docker-compose.yml
index 9ec71abab..b26cf4199 100644
--- a/docker/docker-compose.yml
+++ b/docker/docker-compose.yml
@@ -19,7 +19,7 @@ services:
 
   # ─────────────────────────────────────────────
   # PicoClaw Gateway (Long-running Bot)
-  #   docker compose -f docker/docker-compose.yml up picoclaw-gateway
+  #   docker compose -f docker/docker-compose.yml --profile gateway up
   # ─────────────────────────────────────────────
   picoclaw-gateway:
     image: docker.io/sipeed/picoclaw:latest
@@ -32,3 +32,21 @@ services:
     #  - "host.docker.internal:host-gateway"
     volumes:
       - ./data:/root/.picoclaw
+
+  # ─────────────────────────────────────────────
+  # PicoClaw Launcher (Web Console + Gateway)
+  #   docker compose -f docker/docker-compose.yml --profile launcher up
+  # ─────────────────────────────────────────────
+  picoclaw-launcher:
+    image: docker.io/sipeed/picoclaw:launcher
+    container_name: picoclaw-launcher
+    restart: on-failure
+    profiles:
+      - launcher
+    environment:
+      - PICOCLAW_GATEWAY_HOST=0.0.0.0
+    ports:
+      - "127.0.0.1:18800:18800"
+      - "127.0.0.1:18790:18790"
+    volumes:
+      - ./data:/root/.picoclaw
diff --git a/docs/channels/matrix/README.md b/docs/channels/matrix/README.md
index c213aa80b..233f5c0a3 100644
--- a/docs/channels/matrix/README.md
+++ b/docs/channels/matrix/README.md
@@ -22,7 +22,8 @@ Add this to `config.json`:
         "enabled": true,
         "text": "Thinking..."
       },
-      "reasoning_channel_id": ""
+      "reasoning_channel_id": "",
+      "message_format": "richtext"
     }
   }
 }
@@ -42,10 +43,12 @@ Add this to `config.json`:
 | group_trigger        | object   | No       | Group trigger strategy (`mention_only` / `prefixes`) |
 | placeholder          | object   | No       | Placeholder message config |
 | reasoning_channel_id | string   | No       | Target channel for reasoning output |
+| message_format       | string   | No       | Output format: `"richtext"` (default) renders markdown as HTML; `"plain"` sends plain text only |
 
 ## 3. Currently Supported
 
-- Text message send/receive
+- Text message send/receive with markdown rendering (bold, italic, headers, code blocks, etc.)
+- Configurable message format (`richtext` / `plain`)
 - Incoming image/audio/video/file download (MediaStore first, local path fallback)
 - Incoming audio normalization into existing transcription flow (`[audio: ...]`)
 - Outgoing image/audio/video/file upload and send
diff --git a/docs/design/provider-refactoring.md b/docs/design/provider-refactoring.md
index a214d9857..38f379c50 100644
--- a/docs/design/provider-refactoring.md
+++ b/docs/design/provider-refactoring.md
@@ -66,7 +66,7 @@ Problem: Agent needs to know both `provider` and `model`, adding complexity.
 Inspired by [LiteLLM](https://docs.litellm.ai/docs/proxy/configs) design:
 
 1. **Model-centric**: Users care about models, not providers
-2. **Protocol prefix**: Use `protocol/model_name` format, e.g., `openai/gpt-5.2`, `anthropic/claude-sonnet-4.6`
+2. **Protocol prefix**: Use `protocol/model_name` format, e.g., `openai/gpt-5.4`, `anthropic/claude-sonnet-4.6`
 3. **Configuration-driven**: Adding new Providers only requires config changes, no code changes
 
 ### 2.2 New Configuration Structure
@@ -81,8 +81,8 @@ Inspired by [LiteLLM](https://docs.litellm.ai/docs/proxy/configs) design:
       "api_key": "sk-xxx"
     },
     {
-      "model_name": "gpt-5.2",
-      "model": "openai/gpt-5.2",
+      "model_name": "gpt-5.4",
+      "model": "openai/gpt-5.4",
       "api_key": "sk-xxx"
     },
     {
@@ -128,7 +128,7 @@ type Config struct {
 type ModelConfig struct {
     // Required
     ModelName string `json:"model_name"`  // user-facing name (alias)
-    Model     string `json:"model"`       // protocol/model, e.g., openai/gpt-5.2
+    Model     string `json:"model"`       // protocol/model, e.g., openai/gpt-5.4
 
     // Common config
     APIBase   string `json:"api_base,omitempty"`
@@ -180,7 +180,7 @@ Identify protocol via prefix in `model` field:
       "model": "deepseek-chat"
     },
     "coder": {
-      "model": "gpt-5.2",
+      "model": "gpt-5.4",
       "system_prompt": "You are a coding assistant..."
     },
     "translator": {
@@ -200,7 +200,7 @@ Each Agent only needs to specify `model` (corresponds to `model_name` in `model_
 model_list:
   - model_name: gpt-4o
     litellm_params:
-      model: openai/gpt-5.2
+      model: openai/gpt-5.4
       api_key: xxx
   - model_name: my-custom
     litellm_params:
diff --git a/docs/migration/model-list-migration.md b/docs/migration/model-list-migration.md
index 0d4af719c..eed228d4d 100644
--- a/docs/migration/model-list-migration.md
+++ b/docs/migration/model-list-migration.md
@@ -40,7 +40,7 @@ The new `model_list` configuration offers several advantages:
   "agents": {
     "defaults": {
       "provider": "openai",
-      "model": "gpt-5.2"
+      "model": "gpt-5.4"
     }
   }
 }
@@ -53,7 +53,7 @@ The new `model_list` configuration offers several advantages:
   "model_list": [
     {
       "model_name": "gpt4",
-      "model": "openai/gpt-5.2",
+      "model": "openai/gpt-5.4",
       "api_key": "sk-your-openai-key",
       "api_base": "https://api.openai.com/v1"
     },
@@ -82,7 +82,7 @@ The `model` field uses a protocol prefix format: `[protocol/]model-identifier`
 
 | Prefix | Description | Example |
 |--------|-------------|---------|
-| `openai/` | OpenAI API (default) | `openai/gpt-5.2` |
+| `openai/` | OpenAI API (default) | `openai/gpt-5.4` |
 | `anthropic/` | Anthropic API | `anthropic/claude-opus-4` |
 | `antigravity/` | Google via Antigravity OAuth | `antigravity/gemini-2.0-flash` |
 | `gemini/` | Google Gemini API | `gemini/gemini-2.0-flash-exp` |
@@ -109,7 +109,7 @@ The `model` field uses a protocol prefix format: `[protocol/]model-identifier`
 | Field | Required | Description |
 |-------|----------|-------------|
 | `model_name` | Yes | User-facing alias for the model |
-| `model` | Yes | Protocol and model identifier (e.g., `openai/gpt-5.2`) |
+| `model` | Yes | Protocol and model identifier (e.g., `openai/gpt-5.4`) |
 | `api_base` | No | API endpoint URL |
 | `api_key` | No* | API authentication key |
 | `proxy` | No | HTTP proxy URL |
@@ -130,19 +130,19 @@ Configure multiple endpoints for the same model to distribute load:
   "model_list": [
     {
       "model_name": "gpt4",
-      "model": "openai/gpt-5.2",
+      "model": "openai/gpt-5.4",
       "api_key": "sk-key1",
       "api_base": "https://api1.example.com/v1"
     },
     {
       "model_name": "gpt4",
-      "model": "openai/gpt-5.2",
+      "model": "openai/gpt-5.4",
       "api_key": "sk-key2",
       "api_base": "https://api2.example.com/v1"
     },
     {
       "model_name": "gpt4",
-      "model": "openai/gpt-5.2",
+      "model": "openai/gpt-5.4",
       "api_key": "sk-key3",
       "api_base": "https://api3.example.com/v1"
     }
diff --git a/docs/tools_configuration.md b/docs/tools_configuration.md
index e64a3a107..8c8eb31f0 100644
--- a/docs/tools_configuration.md
+++ b/docs/tools_configuration.md
@@ -7,11 +7,21 @@ PicoClaw's tools configuration is located in the `tools` field of `config.json`.
 ```json
 {
   "tools": {
-    "web": { ... },
-    "mcp": { ... },
-    "exec": { ... },
-    "cron": { ... },
-    "skills": { ... }
+    "web": {
+      ...
+    },
+    "mcp": {
+      ...
+    },
+    "exec": {
+      ...
+    },
+    "cron": {
+      ...
+    },
+    "skills": {
+      ...
+    }
   }
 }
 ```
@@ -23,7 +33,7 @@ Web tools are used for web search and fetching.
 ### Brave
 
 | Config        | Type   | Default | Description               |
-| ------------- | ------ | ------- | ------------------------- |
+|---------------|--------|---------|---------------------------|
 | `enabled`     | bool   | false   | Enable Brave search       |
 | `api_key`     | string | -       | Brave Search API key      |
 | `max_results` | int    | 5       | Maximum number of results |
@@ -31,14 +41,14 @@ Web tools are used for web search and fetching.
 ### DuckDuckGo
 
 | Config        | Type | Default | Description               |
-| ------------- | ---- | ------- | ------------------------- |
+|---------------|------|---------|---------------------------|
 | `enabled`     | bool | true    | Enable DuckDuckGo search  |
 | `max_results` | int  | 5       | Maximum number of results |
 
 ### Perplexity
 
 | Config        | Type   | Default | Description               |
-| ------------- | ------ | ------- | ------------------------- |
+|---------------|--------|---------|---------------------------|
 | `enabled`     | bool   | false   | Enable Perplexity search  |
 | `api_key`     | string | -       | Perplexity API key        |
 | `max_results` | int    | 5       | Maximum number of results |
@@ -48,7 +58,7 @@ Web tools are used for web search and fetching.
 The exec tool is used to execute shell commands.
 
 | Config                 | Type  | Default | Description                                |
-| ---------------------- | ----- | ------- | ------------------------------------------ |
+|------------------------|-------|---------|--------------------------------------------|
 | `enable_deny_patterns` | bool  | true    | Enable default dangerous command blocking  |
 | `custom_deny_patterns` | array | []      | Custom deny patterns (regular expressions) |
 
@@ -81,7 +91,10 @@ By default, PicoClaw blocks the following dangerous commands:
   "tools": {
     "exec": {
       "enable_deny_patterns": true,
-      "custom_deny_patterns": ["\\brm\\s+-r\\b", "\\bkillall\\s+python"]
+      "custom_deny_patterns": [
+        "\\brm\\s+-r\\b",
+        "\\bkillall\\s+python"
+      ]
     }
   }
 }
@@ -92,24 +105,47 @@ By default, PicoClaw blocks the following dangerous commands:
 The cron tool is used for scheduling periodic tasks.
 
 | Config                 | Type | Default | Description                                    |
-| ---------------------- | ---- | ------- | ---------------------------------------------- |
+|------------------------|------|---------|------------------------------------------------|
 | `exec_timeout_minutes` | int  | 5       | Execution timeout in minutes, 0 means no limit |
 
 ## MCP Tool
 
 The MCP tool enables integration with external Model Context Protocol servers.
 
+### Tool Discovery (Lazy Loading)
+
+When connecting to multiple MCP servers, exposing hundreds of tools simultaneously can exhaust the LLM's context window
+and increase API costs. The **Discovery** feature solves this by keeping MCP tools *hidden* by default.
+
+Instead of loading all tools, the LLM is provided with a lightweight search tool (using BM25 keyword matching or Regex).
+When the LLM needs a specific capability, it searches the hidden library. Matching tools are then temporarily "unlocked"
+and injected into the context for a configured number of turns (`ttl`).
+
 ### Global Config
 
-| Config    | Type   | Default | Description                         |
-| --------- | ------ | ------- | ----------------------------------- |
-| `enabled` | bool   | false   | Enable MCP integration globally     |
-| `servers` | object | `{}`    | Map of server name to server config |
+| Config      | Type   | Default | Description                                  |
+|-------------|--------|---------|----------------------------------------------|
+| `enabled`   | bool   | false   | Enable MCP integration globally              |
+| `discovery` | object | `{}`    | Configuration for Tool Discovery (see below) |
+| `servers`   | object | `{}`    | Map of server name to server config          |
+
+### Discovery Config (`discovery`)
+
+| Config               | Type | Default | Description                                                                                                                       |
+|----------------------|------|---------|-----------------------------------------------------------------------------------------------------------------------------------|
+| `enabled`            | bool | false   | If true, MCP tools are hidden and loaded on-demand via search. If false, all tools are loaded                                     |
+| `ttl`                | int  | 5       | Number of conversational turns a discovered tool remains unlocked                                                                 |
+| `max_search_results` | int  | 5       | Maximum number of tools returned per search query                                                                                 |
+| `use_bm25`           | bool | true    | Enable the natural language/keyword search tool (`tool_search_tool_bm25`). **Warning**: consumes more resources than regex search |
+| `use_regex`          | bool | false   | Enable the regex pattern search tool (`tool_search_tool_regex`)                                                                   |
+
+> **Note:** If `discovery.enabled` is `true`, you MUST enable at least one search engine (`use_bm25` or `use_regex`),
+> otherwise the application will fail to start.
 
 ### Per-Server Config
 
 | Config     | Type   | Required | Description                                |
-| ---------- | ------ | -------- | ------------------------------------------ |
+|------------|--------|----------|--------------------------------------------|
 | `enabled`  | bool   | yes      | Enable this MCP server                     |
 | `type`     | string | no       | Transport type: `stdio`, `sse`, `http`     |
 | `command`  | string | stdio    | Executable command for stdio transport     |
@@ -122,8 +158,8 @@ The MCP tool enables integration with external Model Context Protocol servers.
 ### Transport Behavior
 
 - If `type` is omitted, transport is auto-detected:
-  - `url` is set → `sse`
-  - `command` is set → `stdio`
+    - `url` is set → `sse`
+    - `command` is set → `stdio`
 - `http` and `sse` both use `url` + optional `headers`.
 - `env` and `env_file` are only applied to `stdio` servers.
 
@@ -140,7 +176,11 @@ The MCP tool enables integration with external Model Context Protocol servers.
         "filesystem": {
           "enabled": true,
           "command": "npx",
-          "args": ["-y", "@modelcontextprotocol/server-filesystem", "/tmp"]
+          "args": [
+            "-y",
+            "@modelcontextprotocol/server-filesystem",
+            "/tmp"
+          ]
         }
       }
     }
@@ -170,20 +210,76 @@ The MCP tool enables integration with external Model Context Protocol servers.
 }
 ```
 
+#### 3) Massive MCP setup with Tool Discovery enabled
+
+*In this example, the LLM will only see the `tool_search_tool_bm25`. It will search and unlock Github or Postgres tools
+dynamically only when requested by the user.*
+
+```json
+{
+  "tools": {
+    "mcp": {
+      "enabled": true,
+      "discovery": {
+        "enabled": true,
+        "ttl": 5,
+        "max_search_results": 5,
+        "use_bm25": true,
+        "use_regex": false
+      },
+      "servers": {
+        "github": {
+          "enabled": true,
+          "command": "npx",
+          "args": [
+            "-y",
+            "@modelcontextprotocol/server-github"
+          ],
+          "env": {
+            "GITHUB_PERSONAL_ACCESS_TOKEN": "YOUR_GITHUB_TOKEN"
+          }
+        },
+        "postgres": {
+          "enabled": true,
+          "command": "npx",
+          "args": [
+            "-y",
+            "@modelcontextprotocol/server-postgres",
+            "postgresql://user:password@localhost/dbname"
+          ]
+        },
+        "slack": {
+          "enabled": true,
+          "command": "npx",
+          "args": [
+            "-y",
+            "@modelcontextprotocol/server-slack"
+          ],
+          "env": {
+            "SLACK_BOT_TOKEN": "YOUR_SLACK_BOT_TOKEN",
+            "SLACK_TEAM_ID": "YOUR_SLACK_TEAM_ID"
+          }
+        }
+      }
+    }
+  }
+}
+```
+
 ## Skills Tool
 
 The skills tool configures skill discovery and installation via registries like ClawHub.
 
 ### Registries
 
-| Config                             | Type   | Default              | Description             |
-| ---------------------------------- | ------ | -------------------- | ----------------------- |
-| `registries.clawhub.enabled`       | bool   | true                 | Enable ClawHub registry |
-| `registries.clawhub.base_url`      | string | `https://clawhub.ai` | ClawHub base URL        |
+| Config                             | Type   | Default              | Description                                  |
+|------------------------------------|--------|----------------------|----------------------------------------------|
+| `registries.clawhub.enabled`       | bool   | true                 | Enable ClawHub registry                      |
+| `registries.clawhub.base_url`      | string | `https://clawhub.ai` | ClawHub base URL                             |
 | `registries.clawhub.auth_token`    | string | `""`                 | Optional Bearer token for higher rate limits |
-| `registries.clawhub.search_path`   | string | `/api/v1/search`     | Search API path         |
-| `registries.clawhub.skills_path`   | string | `/api/v1/skills`     | Skills API path         |
-| `registries.clawhub.download_path` | string | `/api/v1/download`   | Download API path       |
+| `registries.clawhub.search_path`   | string | `/api/v1/search`     | Search API path                              |
+| `registries.clawhub.skills_path`   | string | `/api/v1/skills`     | Skills API path                              |
+| `registries.clawhub.download_path` | string | `/api/v1/download`   | Download API path                            |
 
 ### Configuration Example
 
@@ -217,4 +313,5 @@ For example:
 - `PICOCLAW_TOOLS_CRON_EXEC_TIMEOUT_MINUTES=10`
 - `PICOCLAW_TOOLS_MCP_ENABLED=true`
 
-Note: Nested map-style config (for example `tools.mcp.servers.<name>.*`) is configured in `config.json` rather than environment variables.
+Note: Nested map-style config (for example `tools.mcp.servers.<name>.*`) is configured in `config.json` rather than
+environment variables.
diff --git a/pkg/channels/base.go b/pkg/channels/base.go
index 5927408ee..edb5b6f08 100644
--- a/pkg/channels/base.go
+++ b/pkg/channels/base.go
@@ -5,6 +5,7 @@ import (
 	"crypto/rand"
 	"encoding/binary"
 	"encoding/hex"
+	"regexp"
 	"strconv"
 	"strings"
 	"sync/atomic"
@@ -32,6 +33,9 @@ func init() {
 	uniqueIDPrefix = hex.EncodeToString(b[:])
 }
 
+// audioAnnotationRe matches audio/voice annotations injected by channels (e.g. [voice], [audio: file.ogg]).
+var audioAnnotationRe = regexp.MustCompile(`\[(voice|audio)(?::[^\]]*)?\]`)
+
 // uniqueID generates a process-unique ID using a random prefix and an atomic counter.
 // This ID is intended for internal correlation (e.g. media scope keys) and is NOT
 // cryptographically secure — it must not be used in contexts where unpredictability matters.
@@ -285,10 +289,10 @@ func (c *BaseChannel) HandleMessage(
 			}
 		}
 		// Placeholder — independent pipeline.
-		// Skip for DraftSender channels: the streaming draft bubble serves
-		// as the placeholder, and sendMessage on final response replaces it.
-		// Sending both a placeholder AND drafts causes duplicate chat bubbles.
-		if _, isDrafter := c.owner.(DraftSender); !isDrafter {
+		// Skip when the message contains audio: the agent will send the
+		// placeholder after transcription completes, so the user sees
+		// "Thinking…" only once the voice has been processed.
+		if !audioAnnotationRe.MatchString(content) {
 			if pc, ok := c.owner.(PlaceholderCapable); ok {
 				if phID, err := pc.SendPlaceholder(ctx, chatID); err == nil && phID != "" {
 					c.placeholderRecorder.RecordPlaceholder(c.name, chatID, phID)
diff --git a/pkg/channels/dingtalk/dingtalk.go b/pkg/channels/dingtalk/dingtalk.go
index 8642ad362..c03122892 100644
--- a/pkg/channels/dingtalk/dingtalk.go
+++ b/pkg/channels/dingtalk/dingtalk.go
@@ -10,6 +10,7 @@ import (
 
 	"github.com/open-dingtalk/dingtalk-stream-sdk-go/chatbot"
 	"github.com/open-dingtalk/dingtalk-stream-sdk-go/client"
+	dinglog "github.com/open-dingtalk/dingtalk-stream-sdk-go/logger"
 
 	"github.com/sipeed/picoclaw/pkg/bus"
 	"github.com/sipeed/picoclaw/pkg/channels"
@@ -39,6 +40,9 @@ func NewDingTalkChannel(cfg config.DingTalkConfig, messageBus *bus.MessageBus) (
 		return nil, fmt.Errorf("dingtalk client_id and client_secret are required")
 	}
 
+	// Set the logger for the Stream SDK
+	dinglog.SetLogger(logger.NewLogger("dingtalk"))
+
 	base := channels.NewBaseChannel("dingtalk", cfg, messageBus, cfg.AllowFrom,
 		channels.WithMaxMessageLength(20000),
 		channels.WithGroupTrigger(cfg.GroupTrigger),
diff --git a/pkg/channels/line/line.go b/pkg/channels/line/line.go
index b36350a06..56ba02183 100644
--- a/pkg/channels/line/line.go
+++ b/pkg/channels/line/line.go
@@ -32,6 +32,10 @@ const (
 	lineBotInfoEndpoint  = lineAPIBase + "/info"
 	lineLoadingEndpoint  = lineAPIBase + "/chat/loading/start"
 	lineReplyTokenMaxAge = 25 * time.Second
+
+	// Limit request body to prevent memory exhaustion (DoS).
+	// LINE webhook payloads are typically a few KB; 1 MiB is generous.
+	maxWebhookBodySize = 1 << 20 // 1 MiB
 )
 
 type replyTokenEntry struct {
@@ -166,7 +170,7 @@ func (c *LINEChannel) webhookHandler(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 
-	body, err := io.ReadAll(r.Body)
+	body, err := io.ReadAll(io.LimitReader(r.Body, maxWebhookBodySize+1))
 	if err != nil {
 		logger.ErrorCF("line", "Failed to read request body", map[string]any{
 			"error": err.Error(),
@@ -174,6 +178,11 @@ func (c *LINEChannel) webhookHandler(w http.ResponseWriter, r *http.Request) {
 		http.Error(w, "Bad request", http.StatusBadRequest)
 		return
 	}
+	if int64(len(body)) > maxWebhookBodySize {
+		logger.WarnC("line", "Webhook request body too large, rejected")
+		http.Error(w, "Request entity too large", http.StatusRequestEntityTooLarge)
+		return
+	}
 
 	signature := r.Header.Get("X-Line-Signature")
 	if !c.verifySignature(body, signature) {
diff --git a/pkg/commands/builtin.go b/pkg/commands/builtin.go
index a36dd3eba..aed6a1874 100644
--- a/pkg/commands/builtin.go
+++ b/pkg/commands/builtin.go
@@ -12,5 +12,6 @@ func BuiltinDefinitions() []Definition {
 		listCommand(),
 		switchCommand(),
 		checkCommand(),
+		clearCommand(),
 	}
 }
diff --git a/pkg/commands/runtime.go b/pkg/commands/runtime.go
index 227d495f4..037184686 100644
--- a/pkg/commands/runtime.go
+++ b/pkg/commands/runtime.go
@@ -13,4 +13,5 @@ type Runtime struct {
 	GetEnabledChannels func() []string
 	SwitchModel        func(value string) (oldModel string, err error)
 	SwitchChannel      func(value string) error
+	ClearHistory       func() error
 }
diff --git a/pkg/config/config.go b/pkg/config/config.go
index 45cf8976e..0d1bacdbc 100644
--- a/pkg/config/config.go
+++ b/pkg/config/config.go
@@ -227,18 +227,18 @@ type AgentDefaults struct {
 	ModelName                 string         `json:"model_name,omitempty"            env:"PICOCLAW_AGENTS_DEFAULTS_MODEL_NAME"`
 	Model                     string         `json:"model"                           env:"PICOCLAW_AGENTS_DEFAULTS_MODEL"` // Deprecated: use model_name instead
 	ModelFallbacks            []string       `json:"model_fallbacks,omitempty"`
-	ImageModel                string         `json:"image_model,omitempty"           env:"PICOCLAW_AGENTS_DEFAULTS_IMAGE_MODEL"`
-	ImageModelFallbacks       []string       `json:"image_model_fallbacks,omitempty"`
 	PlanModel                 string         `json:"plan_model,omitempty"            env:"PICOCLAW_AGENTS_DEFAULTS_PLAN_MODEL"`
 	PlanModelFallbacks        []string       `json:"plan_model_fallbacks,omitempty"`
+	ImageModel                string         `json:"image_model,omitempty"           env:"PICOCLAW_AGENTS_DEFAULTS_IMAGE_MODEL"`
+	ImageModelFallbacks       []string       `json:"image_model_fallbacks,omitempty"`
 	MaxTokens                 int            `json:"max_tokens"                      env:"PICOCLAW_AGENTS_DEFAULTS_MAX_TOKENS"`
 	Temperature               *float64       `json:"temperature,omitempty"           env:"PICOCLAW_AGENTS_DEFAULTS_TEMPERATURE"`
 	MaxToolIterations         int            `json:"max_tool_iterations"             env:"PICOCLAW_AGENTS_DEFAULTS_MAX_TOOL_ITERATIONS"`
-	TaskReminderInterval      int            `json:"task_reminder_interval"          env:"PICOCLAW_AGENTS_DEFAULTS_TASK_REMINDER_INTERVAL"`
-	Orchestration             bool           `json:"orchestration,omitempty"         env:"PICOCLAW_AGENTS_DEFAULTS_ORCHESTRATION"`
 	SummarizeMessageThreshold int            `json:"summarize_message_threshold"     env:"PICOCLAW_AGENTS_DEFAULTS_SUMMARIZE_MESSAGE_THRESHOLD"`
 	SummarizeTokenPercent     int            `json:"summarize_token_percent"         env:"PICOCLAW_AGENTS_DEFAULTS_SUMMARIZE_TOKEN_PERCENT"`
 	MaxMediaSize              int            `json:"max_media_size,omitempty"        env:"PICOCLAW_AGENTS_DEFAULTS_MAX_MEDIA_SIZE"`
+	TaskReminderInterval      int            `json:"task_reminder_interval"          env:"PICOCLAW_AGENTS_DEFAULTS_TASK_REMINDER_INTERVAL"`
+	Orchestration             bool           `json:"orchestration,omitempty"         env:"PICOCLAW_AGENTS_DEFAULTS_ORCHESTRATION"`
 	Routing                   *RoutingConfig `json:"routing,omitempty"`
 }
 
@@ -304,19 +304,20 @@ type WhatsAppConfig struct {
 	AllowFrom          FlexibleStringSlice `json:"allow_from"           env:"PICOCLAW_CHANNELS_WHATSAPP_ALLOW_FROM"`
 	ReasoningChannelID string              `json:"reasoning_channel_id" env:"PICOCLAW_CHANNELS_WHATSAPP_REASONING_CHANNEL_ID"`
 }
+
 type TelegramConfig struct {
 	Enabled            bool                `json:"enabled"                 env:"PICOCLAW_CHANNELS_TELEGRAM_ENABLED"`
 	Token              string              `json:"token"                   env:"PICOCLAW_CHANNELS_TELEGRAM_TOKEN"`
 	BaseURL            string              `json:"base_url"                env:"PICOCLAW_CHANNELS_TELEGRAM_BASE_URL"`
 	Proxy              string              `json:"proxy"                   env:"PICOCLAW_CHANNELS_TELEGRAM_PROXY"`
-	WebAppURL          string              `json:"web_app_url"             env:"PICOCLAW_CHANNELS_TELEGRAM_WEB_APP_URL"`
 	AllowFrom          FlexibleStringSlice `json:"allow_from"              env:"PICOCLAW_CHANNELS_TELEGRAM_ALLOW_FROM"`
 	GroupTrigger       GroupTriggerConfig  `json:"group_trigger,omitempty"`
 	Typing             TypingConfig        `json:"typing,omitempty"`
 	Placeholder        PlaceholderConfig   `json:"placeholder,omitempty"`
+	ReasoningChannelID string              `json:"reasoning_channel_id"    env:"PICOCLAW_CHANNELS_TELEGRAM_REASONING_CHANNEL_ID"`
+	WebAppURL          string              `json:"web_app_url"             env:"PICOCLAW_CHANNELS_TELEGRAM_WEB_APP_URL"`
 	SubagentThreadID   int                 `json:"subagent_thread_id,omitempty"  env:"PICOCLAW_CHANNELS_TELEGRAM_SUBAGENT_THREAD_ID"`
 	HeartbeatThreadID  int                 `json:"heartbeat_thread_id,omitempty" env:"PICOCLAW_CHANNELS_TELEGRAM_HEARTBEAT_THREAD_ID"`
-	ReasoningChannelID string              `json:"reasoning_channel_id"    env:"PICOCLAW_CHANNELS_TELEGRAM_REASONING_CHANNEL_ID"`
 }
 
 type FeishuConfig struct {
@@ -394,7 +395,7 @@ type MatrixConfig struct {
 	AllowFrom          FlexibleStringSlice `json:"allow_from"               env:"PICOCLAW_CHANNELS_MATRIX_ALLOW_FROM"`
 	GroupTrigger       GroupTriggerConfig  `json:"group_trigger,omitempty"`
 	Placeholder        PlaceholderConfig   `json:"placeholder,omitempty"`
-	ReasoningChannelID string              `json:"reasoning_channel_id"    env:"PICOCLAW_CHANNELS_MATRIX_REASONING_CHANNEL_ID"`
+	ReasoningChannelID string              `json:"reasoning_channel_id"     env:"PICOCLAW_CHANNELS_MATRIX_REASONING_CHANNEL_ID"`
 }
 
 type LINEConfig struct {
@@ -609,12 +610,13 @@ type ModelConfig struct {
 	AuthMethod  string `json:"auth_method,omitempty"`  // Authentication method: oauth, token
 	ConnectMode string `json:"connect_mode,omitempty"` // Connection mode: stdio, grpc
 	Workspace   string `json:"workspace,omitempty"`    // Workspace path for CLI-based providers
+
 	// Optional optimizations
 	RPM            int    `json:"rpm,omitempty"`              // Requests per minute limit
 	MaxTokensField string `json:"max_tokens_field,omitempty"` // Field name for max tokens (e.g., "max_completion_tokens")
-	Stream         *bool  `json:"stream,omitempty"`           // Use SSE streaming (default: protocol-dependent)
 	RequestTimeout int    `json:"request_timeout,omitempty"`
 	ThinkingLevel  string `json:"thinking_level,omitempty"` // Extended thinking: off|low|medium|high|xhigh|adaptive
+	Stream         *bool  `json:"stream,omitempty"`           // Use SSE streaming (default: protocol-dependent)
 }
 
 // Validate checks if the ModelConfig has all required fields.
diff --git a/pkg/config/migration.go b/pkg/config/migration.go
index bb04fd2a8..af6391651 100644
--- a/pkg/config/migration.go
+++ b/pkg/config/migration.go
@@ -407,6 +407,23 @@ func ConvertProvidersToModelList(cfg *Config) []ModelConfig {
 				}, true
 			},
 		},
+		{
+			providerNames: []string{"longcat"},
+			protocol:      "longcat",
+			buildConfig: func(p ProvidersConfig) (ModelConfig, bool) {
+				if p.LongCat.APIKey == "" && p.LongCat.APIBase == "" {
+					return ModelConfig{}, false
+				}
+				return ModelConfig{
+					ModelName:      "longcat",
+					Model:          "longcat/LongCat-Flash-Thinking",
+					APIKey:         p.LongCat.APIKey,
+					APIBase:        p.LongCat.APIBase,
+					Proxy:          p.LongCat.Proxy,
+					RequestTimeout: p.LongCat.RequestTimeout,
+				}, true
+			},
+		},
 	}
 
 	// Process each provider migration
diff --git a/pkg/health/server.go b/pkg/health/server.go
index 0a530a3e8..5609ebdf6 100644
--- a/pkg/health/server.go
+++ b/pkg/health/server.go
@@ -2,7 +2,6 @@ package health
 
 import (
 	"context"
-	"crypto/tls"
 	"encoding/json"
 	"fmt"
 	"maps"
@@ -13,7 +12,6 @@ import (
 
 type Server struct {
 	server    *http.Server
-	mux       *http.ServeMux
 	mu        sync.RWMutex
 	ready     bool
 	checks    map[string]Check
@@ -36,7 +34,6 @@ type StatusResponse struct {
 func NewServer(host string, port int) *Server {
 	mux := http.NewServeMux()
 	s := &Server{
-		mux:       mux,
 		ready:     false,
 		checks:    make(map[string]Check),
 		startTime: time.Now(),
@@ -49,34 +46,13 @@ func NewServer(host string, port int) *Server {
 	s.server = &http.Server{
 		Addr:         addr,
 		Handler:      mux,
-		ReadTimeout:  30 * time.Second,
-		WriteTimeout: 30 * time.Second,
+		ReadTimeout:  5 * time.Second,
+		WriteTimeout: 5 * time.Second,
 	}
 
 	return s
 }
 
-// Mux returns the underlying ServeMux so additional routes can be registered.
-func (s *Server) Mux() *http.ServeMux {
-	return s.mux
-}
-
-// StartTLS starts the server with TLS using the provided certificate and key files.
-func (s *Server) StartTLS(certFile, keyFile string) error {
-	s.mu.Lock()
-	s.ready = true
-	s.mu.Unlock()
-
-	cert, err := tls.LoadX509KeyPair(certFile, keyFile)
-	if err != nil {
-		return fmt.Errorf("failed to load TLS cert: %w", err)
-	}
-	s.server.TLSConfig = &tls.Config{
-		Certificates: []tls.Certificate{cert},
-	}
-	return s.server.ListenAndServeTLS("", "")
-}
-
 func (s *Server) Start() error {
 	s.mu.Lock()
 	s.ready = true
diff --git a/pkg/health/server_ext.go b/pkg/health/server_ext.go
new file mode 100644
index 000000000..8fff4a74c
--- /dev/null
+++ b/pkg/health/server_ext.go
@@ -0,0 +1,28 @@
+package health
+
+import (
+	"crypto/tls"
+	"fmt"
+	"net/http"
+)
+
+// Mux returns the underlying ServeMux so additional routes can be registered.
+func (s *Server) Mux() *http.ServeMux {
+	return s.server.Handler.(*http.ServeMux)
+}
+
+// StartTLS starts the server with TLS using the provided certificate and key files.
+func (s *Server) StartTLS(certFile, keyFile string) error {
+	s.mu.Lock()
+	s.ready = true
+	s.mu.Unlock()
+
+	cert, err := tls.LoadX509KeyPair(certFile, keyFile)
+	if err != nil {
+		return fmt.Errorf("failed to load TLS cert: %w", err)
+	}
+	s.server.TLSConfig = &tls.Config{
+		Certificates: []tls.Certificate{cert},
+	}
+	return s.server.ListenAndServeTLS("", "")
+}
diff --git a/pkg/memory/jsonl.go b/pkg/memory/jsonl.go
index e12e2c5ab..afe374166 100644
--- a/pkg/memory/jsonl.go
+++ b/pkg/memory/jsonl.go
@@ -86,14 +86,14 @@ func (s *JSONLStore) metaPath(key string) string {
 
 // sanitizeKey converts a session key to a safe filename component.
 // Mirrors pkg/session.sanitizeFilename so that migration paths match.
-//
-// Note: this is a lossy mapping — "telegram:123" and "telegram_123"
-// both produce the same filename. This is an intentional tradeoff:
-// keys with colons (e.g. from channels) are by far the common case,
-// and a bidirectional encoding (like URL-encoding) would complicate
-// file listings and debugging.
+// Replaces ':' with '_' (session key separator) and '/' and '\' with '_'
+// so composite IDs (e.g. Telegram forum "chatID/threadID", Slack "channel/thread_ts")
+// do not create subdirectories or break on Windows.
 func sanitizeKey(key string) string {
-	return strings.ReplaceAll(key, ":", "_")
+	s := strings.ReplaceAll(key, ":", "_")
+	s = strings.ReplaceAll(s, "/", "_")
+	s = strings.ReplaceAll(s, "\\", "_")
+	return s
 }
 
 // readMeta loads the metadata file for a session.
diff --git a/pkg/memory/migration.go b/pkg/memory/migration.go
index c9d5176ab..b64c62a9f 100644
--- a/pkg/memory/migration.go
+++ b/pkg/memory/migration.go
@@ -48,6 +48,12 @@ func MigrateFromJSON(
 		if !strings.HasSuffix(name, ".json") {
 			continue
 		}
+		// Skip JSONL metadata files. They are part of the new storage format,
+		// not legacy session snapshots, and re-importing them would overwrite
+		// the paired .jsonl history with an empty message list.
+		if strings.HasSuffix(name, ".meta.json") {
+			continue
+		}
 		// Skip already-migrated files.
 		if strings.HasSuffix(name, ".migrated") {
 			continue
diff --git a/pkg/migrate/sources/openclaw/common.go b/pkg/migrate/sources/openclaw/common.go
index d57dbe34f..7cbd2d1e6 100644
--- a/pkg/migrate/sources/openclaw/common.go
+++ b/pkg/migrate/sources/openclaw/common.go
@@ -4,8 +4,8 @@ var migrateableFiles = []string{
 	"AGENTS.md",
 	"SOUL.md",
 	"USER.md",
-	"TOOLS.md",
 	"HEARTBEAT.md",
+	"TOOLS.md",
 }
 
 var migrateableDirs = []string{
diff --git a/pkg/providers/anthropic/provider.go b/pkg/providers/anthropic/provider.go
index 7a17e92bf..242ded175 100644
--- a/pkg/providers/anthropic/provider.go
+++ b/pkg/providers/anthropic/provider.go
@@ -181,8 +181,10 @@ func buildParams(
 				}
 				for _, tc := range msg.ToolCalls {
 					args := tc.Arguments
-					if args == nil && tc.Function != nil && len(tc.Function.Arguments) > 0 {
-						args = tc.Function.Arguments
+					if args == nil && tc.Function != nil && tc.Function.Arguments != "" {
+						if err := json.Unmarshal([]byte(tc.Function.Arguments), &args); err != nil {
+							args = map[string]any{}
+						}
 					}
 					if args == nil {
 						args = map[string]any{}
@@ -306,19 +308,16 @@ func levelToBudget(level string) int {
 func translateTools(tools []ToolDefinition) []anthropic.ToolUnionParam {
 	result := make([]anthropic.ToolUnionParam, 0, len(tools))
 	for _, t := range tools {
-		params := t.Function.ParametersMap()
 		tool := anthropic.ToolParam{
 			Name: t.Function.Name,
 			InputSchema: anthropic.ToolInputSchemaParam{
-				Properties: params["properties"],
+				Properties: t.Function.Parameters["properties"],
 			},
 		}
 		if desc := t.Function.Description; desc != "" {
 			tool.Description = anthropic.String(desc)
 		}
-
-		switch req := params["required"].(type) {
-		case []any:
+		if req, ok := t.Function.Parameters["required"].([]any); ok {
 			required := make([]string, 0, len(req))
 			for _, r := range req {
 				if s, ok := r.(string); ok {
@@ -326,8 +325,6 @@ func translateTools(tools []ToolDefinition) []anthropic.ToolUnionParam {
 				}
 			}
 			tool.InputSchema.Required = required
-		case []string:
-			tool.InputSchema.Required = append([]string(nil), req...)
 		}
 		result = append(result, anthropic.ToolUnionParam{OfTool: &tool})
 	}
diff --git a/pkg/routing/session_key.go b/pkg/routing/session_key.go
index 19e6dd390..fa08fdde3 100644
--- a/pkg/routing/session_key.go
+++ b/pkg/routing/session_key.go
@@ -42,11 +42,6 @@ func BuildAgentMainSessionKey(agentID string) string {
 	return fmt.Sprintf("agent:%s:%s", NormalizeAgentID(agentID), DefaultMainKey)
 }
 
-// BuildSubagentSessionKey returns "subagent:<taskID>" for subagent sessions.
-func BuildSubagentSessionKey(taskID string) string {
-	return fmt.Sprintf("subagent:%s", taskID)
-}
-
 // BuildAgentPeerSessionKey constructs a session key based on agent, channel, peer, and DM scope.
 func BuildAgentPeerSessionKey(params SessionKeyParams) string {
 	agentID := NormalizeAgentID(params.AgentID)
@@ -195,3 +190,8 @@ func resolveLinkedPeerID(identityLinks map[string][]string, channel, peerID stri
 	}
 	return ""
 }
+
+// BuildSubagentSessionKey returns "subagent:<taskID>" for subagent sessions.
+func BuildSubagentSessionKey(taskID string) string {
+	return fmt.Sprintf("subagent:%s", taskID)
+}
diff --git a/pkg/skills/clawhub_registry.go b/pkg/skills/clawhub_registry.go
index 76e717e4b..bd4bed8fb 100644
--- a/pkg/skills/clawhub_registry.go
+++ b/pkg/skills/clawhub_registry.go
@@ -8,7 +8,6 @@ import (
 	"net/http"
 	"net/url"
 	"os"
-	"strconv"
 	"time"
 
 	"github.com/sipeed/picoclaw/pkg/utils"
@@ -112,7 +111,7 @@ func (c *ClawHubRegistry) Search(ctx context.Context, query string, limit int) (
 	q := u.Query()
 	q.Set("q", query)
 	if limit > 0 {
-		q.Set("limit", strconv.Itoa(limit))
+		q.Set("limit", fmt.Sprintf("%d", limit))
 	}
 	u.RawQuery = q.Encode()
 
diff --git a/pkg/skills/registry.go b/pkg/skills/registry.go
index 5cc9ac0a9..45ae72253 100644
--- a/pkg/skills/registry.go
+++ b/pkg/skills/registry.go
@@ -180,7 +180,7 @@ func (rm *RegistryManager) SearchAll(ctx context.Context, query string, limit in
 		close(resultsCh)
 	}()
 
-	merged := make([]SearchResult, 0, len(regs)*limit)
+	var merged []SearchResult
 	var lastErr error
 
 	var anyRegistrySucceeded bool
diff --git a/pkg/skills/search_cache.go b/pkg/skills/search_cache.go
index 76a9147d2..1686e3f98 100644
--- a/pkg/skills/search_cache.go
+++ b/pkg/skills/search_cache.go
@@ -39,8 +39,8 @@ func NewSearchCache(maxEntries int, ttl time.Duration) *SearchCache {
 		ttl = 5 * time.Minute
 	}
 	return &SearchCache{
-		entries:    make(map[string]*cacheEntry, maxEntries),
-		order:      make([]string, 0, maxEntries),
+		entries:    make(map[string]*cacheEntry),
+		order:      make([]string, 0),
 		maxEntries: maxEntries,
 		ttl:        ttl,
 	}
diff --git a/pkg/utils/media.go b/pkg/utils/media.go
index 31d888f79..3e1c5d88e 100644
--- a/pkg/utils/media.go
+++ b/pkg/utils/media.go
@@ -14,13 +14,11 @@ import (
 	"github.com/sipeed/picoclaw/pkg/logger"
 )
 
-var (
-	audioExtensions = []string{".mp3", ".wav", ".ogg", ".m4a", ".flac", ".aac", ".wma"}
-	audioTypes      = []string{"audio/", "application/ogg", "application/x-ogg"}
-)
-
 // IsAudioFile checks if a file is an audio file based on its filename extension and content type.
 func IsAudioFile(filename, contentType string) bool {
+	audioExtensions := []string{".mp3", ".wav", ".ogg", ".m4a", ".flac", ".aac", ".wma"}
+	audioTypes := []string{"audio/", "application/ogg", "application/x-ogg"}
+
 	for _, ext := range audioExtensions {
 		if strings.HasSuffix(strings.ToLower(filename), ext) {
 			return true
diff --git a/workspace/IDENTITY.md b/workspace/IDENTITY.md
index dabb0e14b..20e3e49fa 100644
--- a/workspace/IDENTITY.md
+++ b/workspace/IDENTITY.md
@@ -6,9 +6,6 @@ PicoClaw 🦞
 ## Description
 Ultra-lightweight personal AI assistant written in Go, inspired by nanobot.
 
-## Version
-0.1.0
-
 ## Purpose
 - Provide intelligent AI assistance with minimal resource usage
 - Support multiple LLM providers (OpenAI, Anthropic, Zhipu, etc.)