@@ -52,7 +52,7 @@ else:
 
 ## API Key Authentication
 
-The SDK uses API key for authentication. Please refer to [official documentation for alibabacloud china](https://www.alibabacloud.com/help/en/model-studio/) and [official documentation for alibabacloud international](https://www.alibabacloud.com/help/en/model-studio/) regarding how to obtain your api-key.
+The SDK uses API key for authentication. To obtain an API Key, see [How to get an API Key](https://help.aliyun.com/en/model-studio/get-api-key). Please refer to [official documentation for alibabacloud china](https://www.alibabacloud.com/help/en/model-studio/) and [official documentation for alibabacloud international](https://www.alibabacloud.com/help/en/model-studio/) regarding how to obtain your api-key.
 
 ### Using the API Key
 
@@ -95,6 +95,7 @@ The SDK ships with an interactive AI assistant, **DashScope SDK Expert**, built
 
 - Run `dashscope` with no arguments to start the assistant. On first run it offers to install the SDK Expert knowledge pack (per-domain quick-reference skills: text, multimodal, speech, retrieval, fine-tuning, agent, cli), so guidance comes from the SDK's public interfaces — parameters, outputs, error codes — without reading the source
 - Ask it instead of reading docs — e.g. `dashscope "how do I stream Generation output"` or `dashscope "CLI command to cancel a fine-tuning job"`. Type `/help` inside the assistant to list available commands (`/setup`, `/skill`, `/stats`, ...); classic SDK subcommands still work, and unrecognized commands are routed to the assistant
+- Full walkthrough: [DashScope SDK Expert guide](https://help.aliyun.com/en/model-studio/dashscope-sdk-expert)
 
 ## Supported Models
 
 
@@ -51,7 +51,7 @@ else:
 
 ## API Key 鉴权
 
-SDK 使用 API Key 进行鉴权。获取 API Key 的方法请参考[阿里云百炼官方文档（国内站）](https://help.aliyun.com/zh/model-studio/)和[阿里云百炼官方文档（国际站）](https://www.alibabacloud.com/help/en/model-studio/)。
+SDK 使用 API Key 进行鉴权。获取 API Key 请参见[如何获取 API Key](https://help.aliyun.com/zh/model-studio/get-api-key)，或参考[阿里云百炼官方文档（国内站）](https://help.aliyun.com/zh/model-studio/)和[阿里云百炼官方文档（国际站）](https://www.alibabacloud.com/help/en/model-studio/)。
 
 ### 使用 API Key
 
@@ -94,6 +94,7 @@ SDK 内置了交互式 AI 助手 **DashScope SDK Expert**，基于随包提供
 
 - 直接运行 `dashscope`（不带参数）即可启动助手。首次运行时会提示安装 SDK Expert 知识包（按领域划分的速查技能：文本、多模态、语音、检索、微调、Agent、CLI），使助手的指导来自 SDK 的公开接口——参数、输出、错误码——而无需阅读源码
 - 直接提问代替翻文档——如 `dashscope "如何流式输出 Generation 结果"` 或 `dashscope "取消微调任务的 CLI 命令"`。在助手内输入 `/help` 可列出可用命令（`/setup`、`/skill`、`/stats` 等）；经典 SDK 子命令依然可用，无法识别的命令会自动转给助手处理
+- 完整使用指南：[DashScope SDK Expert 文档](https://help.aliyun.com/zh/model-studio/dashscope-sdk-expert)
 
 ## 支持的模型
 
 
@@ -4,7 +4,7 @@
 Subagents are a subset of capabilities that function as autonomous workers
 you delegate tasks to (vs. tool capabilities that the main agent calls).
 Currently: local.subagent (built-in) + extension capabilities that act as
-remote agents (e.g., Coze workflows).
+remote agents (e.g., a hosted workflow engine).
 
 The /subagents command provides:
   - list: show all discovered subagents with status
 
@@ -256,6 +256,12 @@ def _copy_example_flat(src: Path, dst: Path, *, force: bool) -> bool:
         )
 
     console.print(f"[green]✓ Example copied to: {acli_dir}[/green]")
+    if src.name == "dashscope-sdk-expert":
+        from dashscope.acli.cli.handlers_key import _GUIDE_DOC, _doc_locale
+
+        console.print(
+            f"[dim]Guide: {_GUIDE_DOC.format(_doc_locale())}[/dim]",
+        )
     if backup_dir is not None:
         console.print(
             f"[dim]Overwritten files backed up to: {backup_dir} "
 
@@ -16,6 +16,21 @@
 
 console = Console()
 
+# Model Studio doc links for the no-key startup prompt; locale segment
+# comes from _doc_locale().
+_GET_API_KEY_DOC = "https://help.aliyun.com/{}/model-studio/get-api-key"
+_GUIDE_DOC = "https://help.aliyun.com/{}/model-studio/dashscope-sdk-expert"
+
+
+def _doc_locale() -> str:
+    """Pick the help-center locale from the process locale env vars."""
+    import os
+
+    for var in ("LC_ALL", "LC_MESSAGES", "LANG"):
+        if "zh" in (os.environ.get(var) or "").lower():
+            return "zh"
+    return "en"
+
 
 def all_key_targets(config: Config | None = None) -> dict[str, dict]:
     """Merge KEY_TARGETS (built-in) with extension providers into one dict.
@@ -63,6 +78,26 @@ def _prompt_input(prompt: str, secret: bool = False) -> str:
         return ""
 
 
+def _print_no_key_prompt(config: Config, env_name: str) -> None:
+    """Present the missing-key notice, doc links, and setup menu."""
+    console.print(
+        f"\n[yellow]No API Key detected for " f"{config.provider}[/yellow]",
+    )
+    if config.provider.lower() == "tongyi":
+        lang = _doc_locale()
+        console.print(
+            f"[dim]Get an API Key: {_GET_API_KEY_DOC.format(lang)}[/dim]",
+        )
+        console.print(f"[dim]Guide: {_GUIDE_DOC.format(lang)}[/dim]")
+    console.print("Choose how to set it up:")
+    if env_name:
+        console.print(f"  [1] Set env var {env_name} (exit and set)")
+    else:
+        console.print("  [1] Set corresponding env var (exit and set)")
+    console.print("  [2] Enter API Key now")
+    console.print("  [3] Set up later with /provider after startup")
+
+
 def ensure_provider_key(config: Config, agent) -> bool:
     """If the active provider has no resolvable key, prompt the user.
 
@@ -81,23 +116,27 @@ def ensure_provider_key(config: Config, agent) -> bool:
     ext = find_provider(config.provider)
     targets = all_key_targets(config)
     key_info = targets.get(config.provider)
+    if ext is None and key_info is None:
+        # Neither a built-in nor a loaded extension: this directory cannot
+        # build that provider, so collecting a key is a dead end — and the
+        # "<PROVIDER>_API_KEY" env var we would suggest is read by nothing.
+        console.print(
+            f"\n[yellow]Configured provider '{config.provider}' is not "
+            "available here (no built-in or loaded extension by that "
+            "name), so an API key alone will not make it work.[/yellow]",
+        )
+        console.print(
+            "[dim]Starting anyway; run /provider to pick an available "
+            "provider.[/dim]",
+        )
+        return True
+
     if key_info:
         env_name = key_info.get("env") or ""
-    elif ext is not None:
-        env_name = ext.api_key_env or ""
     else:
-        env_name = f"{config.provider.upper()}_API_KEY"
+        env_name = ext.api_key_env or ""
 
-    console.print(
-        f"\n[yellow]No API Key detected for " f"{config.provider}[/yellow]",
-    )
-    console.print("Choose how to set it up:")
-    if env_name:
-        console.print(f"  [1] Set env var {env_name} (exit and set)")
-    else:
-        console.print("  [1] Set corresponding env var (exit and set)")
-    console.print("  [2] Enter API Key now")
-    console.print("  [3] Set up later with /provider after startup")
+    _print_no_key_prompt(config, env_name)
     choice = input("\nChoose [1/2/3]: ").strip()
 
     if choice == "1":
@@ -219,7 +258,7 @@ def _set_extension_provider_token(
         console.print("[dim]Cancelled[/dim]")
         return False
 
-    # Save to the provider's dynamic slot, e.g. ideatalk_api_key.
+    # Save to the provider's dynamic slot, i.e. <name>_api_key.
     old_provider = config.provider
     try:
         config.provider = ext_prov.name
 
@@ -168,11 +168,32 @@ def _provider_wizard(agent: Agent, config: Config) -> bool:
     for err in loaded.errors:
         console.print(f"[yellow]custom-extensions.toml: {err}[/yellow]")
 
-    # 1) Provider — Enter keeps the current one.
+    # 1) Provider — Enter keeps the current one, but only when it is
+    # loadable. A persisted extension provider whose custom-extensions.toml
+    # is not present here is absent from `names`, so offering it as the
+    # default turns a bare Enter into "Unknown provider; cancelled".
     names = list(PROVIDER_MODELS) + [
         p.name for p in loaded.providers if p.name not in PROVIDER_MODELS
     ]
-    provider = _numbered_pick("Available providers", names, config.provider)
+    current = config.provider if config.provider in names else ""
+    if config.provider and not current:
+        console.print(
+            f"[yellow]Configured provider '{config.provider}' is not "
+            "available here (no built-in or loaded extension by that "
+            "name), so Enter cannot keep it — pick one below.[/yellow]",
+        )
+    provider = _numbered_pick(
+        "Available providers",
+        names,
+        current,
+        custom_hint=(
+            "Need one that is not listed? /dev provider add registers it "
+            "in custom-extensions.toml"
+        ),
+    )
+    if not provider:
+        console.print("[dim]No provider chosen; cancelled[/dim]")
+        return True
     if provider not in names:
         console.print(f"[red]Unknown provider: {provider}; cancelled[/red]")
         return True
 
@@ -156,6 +156,11 @@ def _print_banner(config: Config | None = None) -> None:
                 f"[dim]{', '.join(sdk_index)}[/dim]",
             )
 
+        # Scenario doc link (embedded mode only)
+        guide_url = getattr(config, "_embedded_guide_url", "")
+        if guide_url:
+            console.print(f"  [bold]Guide:[/bold]  [dim]{guide_url}[/dim]")
+
         console.print()
 
     console.print("  [dim]Session: /help /clear /exit[/dim]")
 
@@ -466,8 +466,8 @@ def _load_global(self):
             key_field = f"{prov}_api_key"
             if key_field in data and not getattr(self, key_field):
                 setattr(self, key_field, decrypt_value(str(data[key_field])))
-        # Extension providers (ideatalk/deepseek/zhipu/...) may also store keys
-        # as <name>_api_key in the global config file.
+        # Extension providers may also store keys as <name>_api_key in
+        # the global config file.
         for key, val in data.items():
             if (
                 key.endswith("_api_key")
@@ -740,8 +740,7 @@ def _global_lines(self) -> list[str]:
                 lines.append(
                     f"{prov}_api_key = {toml_str(encrypt_value(key_val))}",
                 )
-        # Extension provider keys stored as <name>_api_key (e.g.
-        # ideatalk_api_key)
+        # Extension provider keys stored as <name>_api_key
         for attr in self.__dict__:
             if attr.endswith("_api_key") and attr not in built_in_key_fields:
                 key_val = getattr(self, attr, "")
 
@@ -146,15 +146,14 @@ def _model_list(config: Config) -> None:
 > Wire a new LLM into acli's chat / stream / tool-call loop.
 > In most scenarios **no code is needed** — just fill in a TOML block.
 
-acli ships only 3 protocol implementations; every provider (including
-built-ins tongyi/anthropic/openai/deepseek/zhipu/ideatalk/ollama) is
-configured via `custom-extensions.toml`:
+acli ships 3 protocol implementations and 3 built-in providers
+(tongyi / anthropic / openai), which need no TOML at all. Every other
+provider is configured via `custom-extensions.toml`:
 
 | Protocol    | Implementation      | Use case                        |
 |-------------|---------------------|---------------------------------|
 | `openai`    | `OpenAIProvider`    | OpenAI-compatible endpoints     |
-|             |                     | (Moonshot/Yi/Step/Deepseek/     |
-|             |                     | Zhipu/Ollama…)                  |
+|             |                     | (any vendor, or local Ollama…)  |
 | `anthropic` | `AnthropicProvider` | Anthropic Messages API (Claude  |
 |             |                     | / proxied endpoints)            |
 | `dashscope` | `TongyiProvider`    | DashScope OpenAI-compat         |
@@ -168,13 +167,13 @@ def _model_list(config: Config) -> None:
    (global) or `./.acli/custom-extensions.toml` (workspace):
 
 ```toml
-# Moonshot / Kimi — OpenAI compatible
+# Any OpenAI-compatible endpoint
 [[providers]]
-name = "moonshot"
-base_url = "https://api.moonshot.cn/v1"
-api_key_env = "MOONSHOT_API_KEY"
-default_model = "kimi-k2"
-models = ["kimi-k1"]
+name = "my-llm"
+base_url = "https://llm.example.com/v1"
+api_key_env = "MY_LLM_API_KEY"
+default_model = "my-model"
+models = ["my-model", "my-model-lite"]
 protocol = "openai"
 
 # Access Qwen via an Anthropic-protocol proxy
@@ -527,7 +526,7 @@ def _provider_add(config: Config) -> None:
                 return
             api_key_enc = encrypt_for_toml(secret)
         else:
-            api_key_env = _prompt("Env var name (e.g. MOONSHOT_API_KEY)")
+            api_key_env = _prompt("Env var name (e.g. MY_LLM_API_KEY)")
             if not api_key_env:
                 console.print("[red]Env var name must not be empty[/red]")
                 return
@@ -1102,7 +1101,7 @@ def handle_dev_command(cmd: str, config: Config) -> None:
             if len(parts) >= 5:
                 _model_add(config, parts[3], parts[4])
             elif len(parts) == 4:
-                # Allow shorthand: /dev model add glm-image
+                # Allow shorthand: /dev model add qwen-image
                 model = parts[3]
                 provider = _infer_provider_from_model(model)
                 if provider is None: