Merge pull request #8 from thieung/feat/getting-started-accuracy

docs: improve getting-started accuracy with source-verified content (EN+VI)

Author: mrgoonie

getting-started/configuration.md

@@ -314,7 +314,7 @@ Controls how agents can spawn child agents.
 
 ```jsonc
 "subagents": {
-  "maxConcurrent": 8,
+  "maxConcurrent": 20,
   "maxSpawnDepth": 1,
   "maxChildrenPerAgent": 5,
   "archiveAfterMinutes": 60,
@@ -324,7 +324,7 @@ Controls how agents can spawn child agents.
 
 | Field | Type | Default | Description |
 |-------|------|---------|-------------|
-| `maxConcurrent` | int | `8` | Max subagents running simultaneously |
+| `maxConcurrent` | int | `20` | Max subagents running simultaneously |
 | `maxSpawnDepth` | int | `1` | Max nesting depth (1–5); `1` = only root can spawn |
 | `maxChildrenPerAgent` | int | `5` | Max children per parent agent (1–20) |
 | `archiveAfterMinutes` | int | `60` | Archive idle subagents after this duration |
@@ -418,13 +418,13 @@ Docker-based isolation for code execution. Can be set globally or overridden per
   "token": "env:TELEGRAM_BOT_TOKEN",
   "proxy": "",
   "allow_from": ["123456789"],
-  "dm_policy": "open",
+  "dm_policy": "pairing",
   "group_policy": "allowlist",
   "require_mention": true,
   "history_limit": 50,
   "dm_stream": false,
   "group_stream": false,
-  "reaction_level": "minimal",
+  "reaction_level": "full",
   "media_max_bytes": 20971520,
   "link_preview": true,
   "block_reply": false,
@@ -444,13 +444,13 @@ Docker-based isolation for code execution. Can be set globally or overridden per
 | `token` | string | — | Bot token from @BotFather |
 | `proxy` | string | — | HTTP/SOCKS5 proxy URL |
 | `allow_from` | []string | — | Allowlisted user/chat IDs; empty = allow all |
-| `dm_policy` | string | `"open"` | DM access: `"pairing"`, `"allowlist"`, `"open"`, `"disabled"` |
+| `dm_policy` | string | `"pairing"` | DM access: `"pairing"`, `"allowlist"`, `"open"`, `"disabled"` |
 | `group_policy` | string | `"open"` | Group access: `"open"`, `"allowlist"`, `"disabled"` |
 | `require_mention` | bool | `true` | Require @bot mention in groups |
 | `history_limit` | int | `50` | Messages fetched for context on new conversation |
 | `dm_stream` | bool | `false` | Stream responses in DMs |
 | `group_stream` | bool | `false` | Stream responses in groups |
-| `reaction_level` | string | `"minimal"` | Emoji reactions: `"off"`, `"minimal"`, `"full"` |
+| `reaction_level` | string | `"full"` | Emoji reactions: `"off"`, `"minimal"`, `"full"` |
 | `media_max_bytes` | int | `20971520` | Max media file size (default 20 MB) |
 | `link_preview` | bool | `true` | Show link previews |
 | `block_reply` | bool | `false` | Override gateway `block_reply` for this channel |
@@ -509,7 +509,7 @@ Docker-based isolation for code execution. Can be set globally or overridden per
   "reaction_level": "minimal",
   "block_reply": false,
   "debounce_delay": 300,
-  "thread_ttl": "24h",
+  "thread_ttl": 24,
   "media_max_bytes": 20971520
 }
 ```
@@ -525,7 +525,7 @@ Docker-based isolation for code execution. Can be set globally or overridden per
 | `require_mention` | bool | `true` | Require @mention in channels |
 | `native_stream` | bool | `false` | Use Slack native streaming API |
 | `debounce_delay` | int | `300` | Message debounce in milliseconds |
-| `thread_ttl` | string | `"24h"` | How long to maintain thread context |
+| `thread_ttl` | int | `24` | Hours to maintain thread context; `0` = disabled (always require @mention) |
 | `media_max_bytes` | int | `20971520` | Max media size (default 20 MB) |
 
 ### WhatsApp
@@ -556,7 +556,7 @@ Docker-based isolation for code execution. Can be set globally or overridden per
   "enabled": true,
   "token": "env:ZALO_OA_TOKEN",
   "allow_from": [],
-  "dm_policy": "open",
+  "dm_policy": "pairing",
   "webhook_url": "https://example.com/zalo/webhook",
   "webhook_secret": "env:ZALO_WEBHOOK_SECRET",
   "media_max_mb": 5,
@@ -568,7 +568,7 @@ Docker-based isolation for code execution. Can be set globally or overridden per
 |-------|------|---------|-------------|
 | `token` | string | — | Zalo OA access token |
 | `allow_from` | []string | — | Allowlisted user IDs |
-| `dm_policy` | string | `"open"` | DM access policy |
+| `dm_policy` | string | `"pairing"` | DM access policy |
 | `webhook_url` | string | — | Public webhook URL for Zalo callbacks |
 | `webhook_secret` | string | — | Webhook signature secret |
 | `media_max_mb` | int | `5` | Max media size (MB) |
@@ -580,7 +580,7 @@ Docker-based isolation for code execution. Can be set globally or overridden per
 "zalo_personal": {
   "enabled": true,
   "allow_from": [],
-  "dm_policy": "open",
+  "dm_policy": "pairing",
   "group_policy": "disabled",
   "require_mention": false,
   "history_limit": 50,
@@ -592,7 +592,7 @@ Docker-based isolation for code execution. Can be set globally or overridden per
 | Field | Type | Default | Description |
 |-------|------|---------|-------------|
 | `allow_from` | []string | — | Allowlisted user IDs |
-| `dm_policy` | string | `"open"` | DM access policy |
+| `dm_policy` | string | `"pairing"` | DM access policy |
 | `group_policy` | string | `"disabled"` | Group access policy |
 | `require_mention` | bool | `false` | Require mention in groups |
 | `history_limit` | int | `50` | Context history limit |
@@ -615,7 +615,7 @@ JSON key: `"feishu"`
   "webhook_port": 3000,
   "webhook_path": "/feishu/events",
   "allow_from": [],
-  "dm_policy": "open",
+  "dm_policy": "pairing",
   "group_policy": "open",
   "group_allow_from": [],
   "require_mention": true,

getting-started/installation.md

@@ -20,7 +20,7 @@ Install GoClaw directly on your machine. You manage Go, PostgreSQL, and the bina
 
 ### Step 1: Install PostgreSQL + pgvector
 
-GoClaw requires **PostgreSQL 15+** with the **pgvector** extension (for vector similarity search in memory and skills).
+GoClaw requires **PostgreSQL 15+** with the **pgvector** extension (for vector similarity search in memory and skills). Docker deployments use **PostgreSQL 18** with pgvector (`pgvector/pgvector:pg18` image).
 
 <details>
 <summary><strong>Ubuntu 24.04+ / Debian 12+</strong></summary>
@@ -96,8 +96,8 @@ go build -o goclaw .
 ```bash
 go build -tags otel -o goclaw .              # OpenTelemetry tracing
 go build -tags tsnet -o goclaw .             # Tailscale networking
-go build -tags sandbox -o goclaw .           # Code execution sandbox
-go build -tags "otel,tsnet,sandbox" -o goclaw .  # Combine multiple
+go build -tags redis -o goclaw .             # Redis caching
+go build -tags "otel,tsnet" -o goclaw .      # Combine multiple
 ```
 
 ### Step 3: Run Setup Wizard

getting-started/migrating-from-openclaw.md

@@ -13,13 +13,13 @@ GoClaw is the multi-tenant evolution of OpenClaw. If you've been running OpenCla
 | Multi-tenant | No (single user) | Yes (per-user isolation) |
 | Agent teams | Sub-agent delegation | Full team collaboration (shared task board, delegation) |
 | Credential storage | Plain text in config | AES-256-GCM encrypted in DB |
-| Memory | SQLite + QMD semantic search | PostgreSQL with hybrid search |
+| Memory | SQLite + QMD semantic search | PostgreSQL + SQLite (FTS5 hybrid search) |
 | Tracing | No | Full LLM call traces with cost tracking |
 | MCP support | Yes (via mcporter bridge) | Yes (stdio, SSE, streamable-http) |
 | Custom tools | Yes (52+ built-in skills) | Yes (define via dashboard or API) |
 | Code sandbox | Yes (Docker-based) | Yes (Docker-based with per-agent config) |
 | Database | SQLite | PostgreSQL (managed mode) |
-| Channels | 18 (9 core + 9 extensions) | 7 (Telegram, Discord, Slack, WhatsApp, Zalo OA, Zalo Personal, Larksuite) |
+| Channels | 18 (9 core + 9 extensions) | 7 (Telegram, Discord, Slack, WhatsApp, Zalo OA, Zalo Personal, Feishu) |
 | Dashboard | Basic web UI | Full management dashboard |
 
 ## Config Mapping
@@ -81,10 +81,19 @@ Additional context files for advanced features:
 | `MEMORY.md` | Long-term curated memory |
 | `DELEGATION.md` | Delegation instructions for sub-agents |
 | `TEAM.md` | Team coordination rules |
-| `AVAILABILITY.md` | Agent availability schedule |
+
+GoClaw supports both agent-level (shared) and per-user context file overrides. The file names listed are conventions, not requirements.
 
 **Key difference:** OpenClaw stores these on the filesystem. GoClaw stores them in PostgreSQL with per-user scoping — each user can have their own version of context files for the same agent.
 
+## What Migrates (and What Doesn't)
+
+| Migrates | Doesn't Migrate |
+|----------|----------------|
+| Agent config (provider, model, tools) | Message history (fresh start) |
+| Context files (manual upload) | Session state |
+| Channel tokens (via env vars) | User profiles (recreated on first login) |
+
 ## Migration Steps
 
 1. **Set up GoClaw** — Follow the [Installation](installation.md) and [Quick Start](quick-start.md) guides

getting-started/quick-start.md

@@ -19,6 +19,8 @@ On first login, the dashboard automatically navigates to the **Setup Wizard**. T
 2. **Create your first agent** — give it a name, system prompt, and select the provider/model from above.
 3. **Connect a channel** (optional) — link Telegram, Discord, WhatsApp, Zalo, Larksuite, or Slack.
 
+> **Tip:** You can click **"Skip setup and go to dashboard"** at the top of the wizard to skip it entirely and configure everything manually later. The Channel step (step 3) also has a **Skip** button if you don't need Telegram/Discord/etc. yet — you can always add channels later.
+
 After completing the wizard, you're ready to chat.
 
 ## Step 2: Add More Providers (Optional)
@@ -75,6 +77,25 @@ websocat ws://localhost:18790/ws
 {"type":"req","id":"2","method":"chat.send","params":{"agentId":"your-agent-key","message":"Hello! What can you do?"}}
 ```
 
+> **Tip:** If you omit `agentId`, GoClaw uses the `default` agent.
+
+**Response:**
+
+```json
+{
+  "type": "res",
+  "id": "2",
+  "ok": true,
+  "payload": {
+    "runId": "uuid-string",
+    "content": "Hello! How can I help you today?",
+    "usage": { "input_tokens": 150, "output_tokens": 25 }
+  }
+}
+```
+
+The `media` field appears in the payload only when the agent returns generated media files.
+
 ## Common Issues
 
 | Problem | Solution |

getting-started/web-dashboard-tour.md

@@ -99,7 +99,7 @@ Enable and configure messaging channels:
 - **WhatsApp** — Connection QR code
 - **Zalo** — App credentials
 - **Zalo Personal** — Personal Zalo account integration
-- **Larksuite** — App ID and secret
+- **Feishu / Lark** — App ID and secret
 - **Slack** — Bot token, workspace settings
 
 #### Nodes
@@ -175,7 +175,7 @@ Delegation history across all agents — track which agents delegated tasks to o
 
 #### Usage
 
-Usage metrics and cost tracking — monitor token consumption, API calls, and costs per agent/channel.
+Usage metrics and cost tracking — monitor token consumption, API calls, and costs per agent/channel. Accessed via the **Usage** tab on the Overview page, not a separate sidebar item.
 
 #### Logs
 

getting-started/what-is-goclaw.md

@@ -11,7 +11,7 @@ GoClaw is an open-source AI agent gateway written in Go. It lets you run AI agen
 | Category | What You Get |
 |----------|-------------|
 | **Multi-Tenant** | Per-user isolation for context, sessions, memory, and traces |
-| **13+ LLM Providers** | OpenAI, Anthropic, Google, Groq, DeepSeek, Mistral, xAI, and more |
+| **18+ LLM Providers** | OpenAI, Anthropic, Google, Groq, DeepSeek, Mistral, xAI, and more |
 | **7 Channels** | Telegram, Discord, WhatsApp, Zalo, Zalo Personal, Larksuite, Slack |
 | **30+ Built-in Tools** | File system, web search, browser, code execution, memory, and more |
 | **Agent Orchestration** | 4 patterns — delegation (sync/async), teams, handoff, evaluate loops |

vi/getting-started/configuration.md

@@ -316,7 +316,7 @@ Kiểm soát cách các agent có thể tạo agent con.
 
 ```jsonc
 "subagents": {
-  "maxConcurrent": 8,
+  "maxConcurrent": 20,
   "maxSpawnDepth": 1,
   "maxChildrenPerAgent": 5,
   "archiveAfterMinutes": 60,
@@ -326,7 +326,7 @@ Kiểm soát cách các agent có thể tạo agent con.
 
 | Trường | Kiểu | Mặc định | Mô tả |
 |--------|------|---------|-------|
-| `maxConcurrent` | int | `8` | Số subagent chạy đồng thời tối đa |
+| `maxConcurrent` | int | `20` | Số subagent chạy đồng thời tối đa |
 | `maxSpawnDepth` | int | `1` | Độ sâu lồng nhau tối đa (1–5); `1` = chỉ root mới được tạo |
 | `maxChildrenPerAgent` | int | `5` | Số agent con tối đa mỗi agent cha (1–20) |
 | `archiveAfterMinutes` | int | `60` | Lưu trữ subagent không hoạt động sau khoảng thời gian này |
@@ -420,13 +420,13 @@ Cô lập dựa trên Docker cho thực thi code. Có thể đặt toàn cục h
   "token": "env:TELEGRAM_BOT_TOKEN",
   "proxy": "",
   "allow_from": ["123456789"],
-  "dm_policy": "open",
+  "dm_policy": "pairing",
   "group_policy": "allowlist",
   "require_mention": true,
   "history_limit": 50,
   "dm_stream": false,
   "group_stream": false,
-  "reaction_level": "minimal",
+  "reaction_level": "full",
   "media_max_bytes": 20971520,
   "link_preview": true,
   "block_reply": false,
@@ -446,13 +446,13 @@ Cô lập dựa trên Docker cho thực thi code. Có thể đặt toàn cục h
 | `token` | string | — | Bot token từ @BotFather |
 | `proxy` | string | — | URL proxy HTTP/SOCKS5 |
 | `allow_from` | []string | — | ID người dùng/chat được phép; để trống = cho phép tất cả |
-| `dm_policy` | string | `"open"` | Truy cập DM: `"pairing"`, `"allowlist"`, `"open"`, `"disabled"` |
+| `dm_policy` | string | `"pairing"` | Truy cập DM: `"pairing"`, `"allowlist"`, `"open"`, `"disabled"` |
 | `group_policy` | string | `"open"` | Truy cập nhóm: `"open"`, `"allowlist"`, `"disabled"` |
 | `require_mention` | bool | `true` | Yêu cầu đề cập @bot trong nhóm |
 | `history_limit` | int | `50` | Số tin nhắn tải để lấy ngữ cảnh khi bắt đầu hội thoại |
 | `dm_stream` | bool | `false` | Phản hồi streaming trong DM |
 | `group_stream` | bool | `false` | Phản hồi streaming trong nhóm |
-| `reaction_level` | string | `"minimal"` | Reaction emoji: `"off"`, `"minimal"`, `"full"` |
+| `reaction_level` | string | `"full"` | Reaction emoji: `"off"`, `"minimal"`, `"full"` |
 | `media_max_bytes` | int | `20971520` | Kích thước file media tối đa (mặc định 20 MB) |
 | `link_preview` | bool | `true` | Hiển thị xem trước liên kết |
 | `block_reply` | bool | `false` | Ghi đè `block_reply` của gateway cho kênh này |
@@ -511,7 +511,7 @@ Cô lập dựa trên Docker cho thực thi code. Có thể đặt toàn cục h
   "reaction_level": "minimal",
   "block_reply": false,
   "debounce_delay": 300,
-  "thread_ttl": "24h",
+  "thread_ttl": 24,
   "media_max_bytes": 20971520
 }
 ```
@@ -527,7 +527,7 @@ Cô lập dựa trên Docker cho thực thi code. Có thể đặt toàn cục h
 | `require_mention` | bool | `true` | Yêu cầu @mention trong kênh |
 | `native_stream` | bool | `false` | Dùng Slack native streaming API |
 | `debounce_delay` | int | `300` | Debounce tin nhắn tính bằng millisecond |
-| `thread_ttl` | string | `"24h"` | Thời gian duy trì ngữ cảnh thread |
+| `thread_ttl` | int | `24` | Số giờ duy trì ngữ cảnh thread; `0` = vô hiệu hóa (luôn yêu cầu @mention) |
 | `media_max_bytes` | int | `20971520` | Kích thước media tối đa (mặc định 20 MB) |
 
 ### WhatsApp
@@ -558,7 +558,7 @@ Cô lập dựa trên Docker cho thực thi code. Có thể đặt toàn cục h
   "enabled": true,
   "token": "env:ZALO_OA_TOKEN",
   "allow_from": [],
-  "dm_policy": "open",
+  "dm_policy": "pairing",
   "webhook_url": "https://example.com/zalo/webhook",
   "webhook_secret": "env:ZALO_WEBHOOK_SECRET",
   "media_max_mb": 5,
@@ -570,7 +570,7 @@ Cô lập dựa trên Docker cho thực thi code. Có thể đặt toàn cục h
 |--------|------|---------|-------|
 | `token` | string | — | Access token Zalo OA |
 | `allow_from` | []string | — | ID người dùng được phép |
-| `dm_policy` | string | `"open"` | Chính sách truy cập DM |
+| `dm_policy` | string | `"pairing"` | Chính sách truy cập DM |
 | `webhook_url` | string | — | URL webhook công khai cho callback Zalo |
 | `webhook_secret` | string | — | Secret chữ ký webhook |
 | `media_max_mb` | int | `5` | Kích thước media tối đa (MB) |
@@ -582,7 +582,7 @@ Cô lập dựa trên Docker cho thực thi code. Có thể đặt toàn cục h
 "zalo_personal": {
   "enabled": true,
   "allow_from": [],
-  "dm_policy": "open",
+  "dm_policy": "pairing",
   "group_policy": "disabled",
   "require_mention": false,
   "history_limit": 50,
@@ -594,7 +594,7 @@ Cô lập dựa trên Docker cho thực thi code. Có thể đặt toàn cục h
 | Trường | Kiểu | Mặc định | Mô tả |
 |--------|------|---------|-------|
 | `allow_from` | []string | — | ID người dùng được phép |
-| `dm_policy` | string | `"open"` | Chính sách truy cập DM |
+| `dm_policy` | string | `"pairing"` | Chính sách truy cập DM |
 | `group_policy` | string | `"disabled"` | Chính sách truy cập nhóm |
 | `require_mention` | bool | `false` | Yêu cầu mention trong nhóm |
 | `history_limit` | int | `50` | Giới hạn lịch sử ngữ cảnh |
@@ -617,7 +617,7 @@ Khóa JSON: `"feishu"`
   "webhook_port": 3000,
   "webhook_path": "/feishu/events",
   "allow_from": [],
-  "dm_policy": "open",
+  "dm_policy": "pairing",
   "group_policy": "open",
   "group_allow_from": [],
   "require_mention": true,

vi/getting-started/installation.md

@@ -22,7 +22,7 @@ Cài GoClaw trực tiếp trên máy. Bạn tự quản lý Go, PostgreSQL và b
 
 ### Bước 1: Cài PostgreSQL + pgvector
 
-GoClaw yêu cầu **PostgreSQL 15+** với extension **pgvector** (dùng cho tìm kiếm vector trong memory và skills).
+GoClaw yêu cầu **PostgreSQL 15+** với extension **pgvector** (dùng cho tìm kiếm vector trong memory và skills). Triển khai qua Docker sử dụng **PostgreSQL 18** với pgvector (image `pgvector/pgvector:pg18`).
 
 <details>
 <summary><strong>Ubuntu 24.04+ / Debian 12+</strong></summary>
@@ -98,8 +98,8 @@ go build -o goclaw .
 ```bash
 go build -tags otel -o goclaw .              # OpenTelemetry tracing
 go build -tags tsnet -o goclaw .             # Tailscale networking
-go build -tags sandbox -o goclaw .           # Code execution sandbox
-go build -tags "otel,tsnet,sandbox" -o goclaw .  # Kết hợp nhiều tag
+go build -tags redis -o goclaw .             # Redis caching
+go build -tags "otel,tsnet" -o goclaw .      # Kết hợp nhiều tag
 ```
 
 ### Bước 3: Chạy wizard thiết lập