docs(reference): document run_subagent's provider, three gateway groups, and max_tokens (#126)

Co-authored-by: Cursor <cursoragent@cursor.com>

packages/docs/content/configuration.en.md

@@ -32,12 +32,12 @@ When a model entry has no inline `api_key`, the AgentHub gateway falls back to t
 | --- | --- | --- |
 | deepseek | `DEEPSEEK_API_KEY` | `DEEPSEEK_BASE_URL` |
 | anthropic | `ANTHROPIC_API_KEY` | `ANTHROPIC_BASE_URL` |
-| openai, openrouter, siliconflow, custom | `OPENAI_API_KEY` | `OPENAI_BASE_URL` |
+| openai, openrouter, fireworks, siliconflow, qwen-token-plan, qwen-pay-as-you-go, custom | `OPENAI_API_KEY` | `OPENAI_BASE_URL` |
 | google | `GEMINI_API_KEY` | `GEMINI_BASE_URL` |
 | zhipu | `ZAI_API_KEY` | `ZAI_BASE_URL` |
 | moonshot | `MOONSHOT_API_KEY` | `MOONSHOT_BASE_URL` |
 
-The openrouter, siliconflow, and custom groups speak the OpenAI-compatible protocol, hence the shared `OPENAI_*` variables. Provider groups and the built-in model catalog are covered in [Models & Providers](/models).
+The openrouter, fireworks, siliconflow, qwen-token-plan, qwen-pay-as-you-go, and custom groups speak the OpenAI-compatible protocol, hence the shared `OPENAI_*` variables. Provider groups and the built-in model catalog are covered in [Models & Providers](/models).
 
 ## Project config
 
@@ -60,6 +60,7 @@ Model entry (`[[models]]`) fields:
 | `client_type` | AgentHub client protocol; inferred from `model_id` by default — third-party OpenAI-compatible models should set `openai` |
 | `display_name` | Display name; persisted only when it differs from the built-in catalog |
 | `vision` | Whether image input is supported; defaults to supported |
+| `max_tokens` | Per-model max output tokens; overrides the Agent's `model.max_tokens` when set, omitted = inherit it |
 | `pricing` | Three price buckets `cache_read` / `cache_write` / `output`, in USD per million Tokens (`unit = "usd_per_mtok"`) |
 | `api_key` | Inline credential; when empty, falls back to the provider environment variable |
 | `base_url` | Custom base URL; preset for gateway models |

packages/docs/content/configuration.zh.md

@@ -32,12 +32,12 @@ CLI 与服务端启动时会自动加载工作目录下的 `.env` 文件。
 | --- | --- | --- |
 | deepseek | `DEEPSEEK_API_KEY` | `DEEPSEEK_BASE_URL` |
 | anthropic | `ANTHROPIC_API_KEY` | `ANTHROPIC_BASE_URL` |
-| openai、openrouter、siliconflow、custom | `OPENAI_API_KEY` | `OPENAI_BASE_URL` |
+| openai、openrouter、fireworks、siliconflow、qwen-token-plan、qwen-pay-as-you-go、custom | `OPENAI_API_KEY` | `OPENAI_BASE_URL` |
 | google | `GEMINI_API_KEY` | `GEMINI_BASE_URL` |
 | zhipu | `ZAI_API_KEY` | `ZAI_BASE_URL` |
 | moonshot | `MOONSHOT_API_KEY` | `MOONSHOT_BASE_URL` |
 
-openrouter、siliconflow 与 custom 分组走 OpenAI 兼容协议，因此复用 `OPENAI_*` 变量。Provider 分组与内置模型目录见[模型与 Provider](/models)。
+openrouter、fireworks、siliconflow、qwen-token-plan、qwen-pay-as-you-go 与 custom 分组走 OpenAI 兼容协议，因此复用 `OPENAI_*` 变量。Provider 分组与内置模型目录见[模型与 Provider](/models)。
 
 ## Project 配置
 
@@ -60,6 +60,7 @@ openrouter、siliconflow 与 custom 分组走 OpenAI 兼容协议，因此复用
 | `client_type` | AgentHub 客户端协议；缺省由 `model_id` 推断，OpenAI 兼容的第三方模型应设为 `openai` |
 | `display_name` | 展示名；仅在与内置目录不同时持久化 |
 | `vision` | 是否支持图片输入；缺省视为支持 |
+| `max_tokens` | 单模型最大输出 Token；设置后覆盖 Agent 的 `model.max_tokens`，缺省则继承 |
 | `pricing` | 三档价格 `cache_read` / `cache_write` / `output`，单位 USD 每百万 Token（`unit = "usd_per_mtok"`） |
 | `api_key` | 内联凭证；留空回退到 Provider 环境变量 |
 | `base_url` | 自定义 Base URL；网关模型预置 |

packages/docs/content/tools.en.md

@@ -160,7 +160,8 @@ On POSIX, Ctrl-C sends `SIGINT` to the session's process group, interrupting the
 {
   prompt: string;          // required: the complete subtask (all context + the exact final output expected)
   agent_id?: string;       // the child Agent; defaults to the current Agent
-  model_id?: string;       // the child Session's model; inherits the parent Session's model when omitted
+  model_id?: string;       // the child Session's model, paired with provider; omit both to inherit the parent Session's model
+  provider?: string;       // the provider group model_id belongs to; required whenever model_id is given
   yield_time_ms?: number;  // foreground wait; default 300000
   description: string;     // required while call_description is on
 }

packages/docs/content/tools.zh.md

@@ -158,7 +158,8 @@ POSIX 上 Ctrl-C 向会话进程组发送 `SIGINT`，中断前台命令。Window
 {
   prompt: string;          // 必填:完整的子任务(含全部上下文与期望的最终产出)
   agent_id?: string;       // 子 Agent;缺省复用当前 Agent
-  model_id?: string;       // 子 Session 模型;缺省继承父 Session 的模型
+  model_id?: string;       // 子 Session 模型,须与 provider 成对给出;两者都缺省时继承父 Session 的模型
+  provider?: string;       // model_id 所属的 provider 组;给出 model_id 时必填
   yield_time_ms?: number;  // 前台等待时长;默认 300000
   description: string;     // 开关开启时必填
 }