Merge pull request #80 from modelstudioai/feat/model-train

feat: add model finetune/deploy/dataset commend to support one step model training by Agent

Author: gujieye

README.md

@@ -38,6 +38,7 @@ Equip your AI Agent out-of-the-box with these capabilities, composable across co
 - **MCP integration** — Orchestrate Bailian MCP servers: list services, inspect tools, and invoke any tool directly from the terminal
 - **Web search** — Real-time internet retrieval for up-to-date, accurate answers
 - **Model recommendation** — Describe your scenario and get best-fit model suggestions; supports scoped search, model comparison, and alternative discovery
+- **Fine-tuning & deployment** — Upload datasets, create SFT/LoRA/DPO/CPT jobs (`finetune create`), probe job status non-blockingly (`finetune watch`), query per-model training capability (`finetune capability`), and deploy trained models as endpoints (`deploy create`)
 - **Console capabilities** — Browse Bailian apps (`app list`), check free-tier quota (`usage free`), view model usage statistics (`usage stats`), manage workspaces (`workspace list`), and manage rate limits (`quota list/request/check/history`)
 - **Local file auto-upload** — Every URL parameter accepts a local path; uploaded to free temp storage with 48-hour validity
 
@@ -111,22 +112,30 @@ bl advisor recommend --message "qwen-max vs deepseek-v3 for code generation"
 # Browser login (required for console capability commands)
 bl auth login --console
 
+# Fine-tune & deploy — a one-shot train-to-serve workflow
+bl dataset upload --file ./train.jsonl                 # Upload a .jsonl dataset (validated first)
+bl finetune create --model qwen3-8b --datasets ./train.jsonl --training-type sft-lora  # Local paths auto-upload
+bl finetune watch --job-id ft-xxx --output json       # Non-blocking status probe (exit 0/1/3 = done/failed/running)
+bl finetune capability --model qwen3-8b               # Which training types a model supports
+bl deploy create --model qwen3-8b --name my-svc --plan mu  # Deploy the trained model as an endpoint
+
 # Browse apps / free-tier quota / usage statistics / workspaces
 bl app list
-bl usage free --model qwen3-max
-bl usage free --expiring 30                           # Quotas expiring within 30 days
-bl usage free --sort remaining                        # Sort by remaining % ascending
-bl usage stats --workspace-id <id>                    # Usage overview for a workspace
-bl usage stats --model qwen-turbo --workspace-id <id> # Per-model usage
+bl usage free                                         # Free-tier quota across models (add --model/--expiring/--sort)
+bl usage stats --workspace-id <id>                    # Model usage statistics (add --model for per-model)
 bl workspace list                                     # List all workspaces
 
-# Rate limit management
-bl quota list                                         # View RPM/TPM limits for all models
-bl quota list --model qwen3.6-plus                    # View limits for a specific model
-bl quota check                                        # Current usage vs rate limits
-bl quota check --model qwen3.6-plus --period 5        # Check usage over last 5 minutes
+# Rate limit management (list / check / request / history)
+bl quota list                                         # View RPM/TPM limits (add --model to filter)
+bl quota check                                        # Current usage vs rate limits (add --model/--period)
 bl quota request --model qwen3.6-plus --tpm 6000000   # Request a temporary TPM increase
-bl quota history                                      # View quota change history
+bl quota history                                      # View quota-change history
+
+# Token Plan team management (requires AK/SK, see auth below)
+bl token-plan list-seats                                # View subscription seat details
+bl token-plan add-member --account-name dev --org-id org_xxx
+bl token-plan assign-seats --workspace-id ws_xxx --seat-type standard --account-id acc_xxx
+bl token-plan create-key --account-id acc_xxx --workspace-id ws_xxx
 ```
 
 > More examples and scenarios: [Aliyun Model Studio CLI Site](https://bailian.console.aliyun.com/cli?source_channel=cli_github&)
@@ -156,9 +165,9 @@ Required for console capability commands (`app list`, `usage free`, `usage stats
 bl auth login --console
 ```
 
-### Alibaba Cloud AK/SK (Knowledge Base only)
+### Alibaba Cloud AK/SK (Knowledge Base & Token Plan)
 
-Required for `knowledge retrieve`. Get your AccessKey from [RAM Console](https://ram.console.aliyun.com/manage/ak).
+Required for `knowledge retrieve` and the `token-plan` command group. Get your AccessKey from [RAM Console](https://ram.console.aliyun.com/manage/ak).
 
 > Recommended: create a RAM sub-account with minimum privileges instead of using the root account's AK/SK.
 

README.zh.md

@@ -38,6 +38,7 @@ _专为 AI Agent 打造，每个命令均可作为结构化工具调用。_
 - **MCP 集成** — 统一调度百炼 MCP 服务：列出服务、查看工具、直接在终端调用任意工具
 - **联网搜索** — 实时互联网信息检索，提升回答准确性及时效性
 - **模型推荐** — 描述你的场景，智能推荐最适合的模型；支持限定范围搜索、模型对比和替代发现
+- **微调与部署** — 上传数据集、创建 SFT/LoRA/DPO/CPT 调优任务（`finetune create`）、非阻塞探测任务状态（`finetune watch`）、按模型查训练能力（`finetune capability`），并把训练好的模型部署为推理服务（`deploy create`）
 - **控制台能力** — 浏览百炼应用（`app list`），查询模型免费额度（`usage free`），查看模型用量统计（`usage stats`），管理业务空间（`workspace list`），管理限流与提额（`quota list/request/check/history`）
 - **本地文件自动上传** — 所有 URL 参数同时支持本地路径，免费临时存储 48 小时
 
@@ -82,7 +83,10 @@ npx skills add modelstudioai/cli --all -g
 ## 快速开始
 
 ```bash
-# 认证
+# 认证（推荐浏览器登录）
+bl auth login --console
+
+# 或使用 API key 认证
 bl auth login --api-key sk-xxxxx
 
 # 和通义千问对话
@@ -106,22 +110,30 @@ bl advisor recommend --message "qwen-max 和 deepseek-v3 哪个更适合做代
 # 浏览器登录（控制台能力相关命令需要）
 bl auth login --console
 
+# 微调与部署 — 从训练到服务的一站式流程
+bl dataset upload --file ./train.jsonl                 # 上传 .jsonl 数据集（先校验）
+bl finetune create --model qwen3-8b --datasets ./train.jsonl --training-type sft-lora  # 本地路径自动上传
+bl finetune watch --job-id ft-xxx --output json       # 非阻塞状态探测（退出码 0/1/3 = 成功/失败/进行中）
+bl finetune capability --model qwen3-8b               # 查询模型支持哪些训练方式
+bl deploy create --model qwen3-8b --name my-svc --plan mu  # 把训练好的模型部署为推理服务
+
 # 浏览应用 / 免费额度 / 用量统计 / 业务空间
 bl app list
-bl usage free --model qwen3-max
-bl usage free --expiring 30                           # 30 天内过期的额度
-bl usage free --sort remaining                        # 按剩余百分比升序排列
-bl usage stats --workspace-id <id>                    # 指定空间的用量概览
-bl usage stats --model qwen-turbo --workspace-id <id> # 指定模型用量
+bl usage free                                         # 各模型免费额度（可加 --model/--expiring/--sort）
+bl usage stats --workspace-id <id>                    # 模型用量统计（加 --model 查单模型）
 bl workspace list                                     # 列出所有业务空间
 
-# 限流管理与提额
-bl quota list                                         # 查看所有模型的 RPM/TPM 限额
-bl quota list --model qwen3.6-plus                    # 查看指定模型限额
-bl quota check                                        # 查看当前用量 vs 限流阈值
-bl quota check --model qwen3.6-plus --period 5        # 查看最近 5 分钟用量
+# 限流管理与提额（list / check / request / history）
+bl quota list                                         # 查看 RPM/TPM 限额（加 --model 过滤）
+bl quota check                                        # 当前用量 vs 限流阈值（加 --model/--period）
 bl quota request --model qwen3.6-plus --tpm 6000000   # 申请临时 TPM 提额
 bl quota history                                      # 查看提额历史记录
+
+# Token Plan 团队版管理（需 AK/SK，见下方认证说明）
+bl token-plan list-seats                                # 查看订阅席位明细
+bl token-plan add-member --account-name dev --org-id org_xxx
+bl token-plan assign-seats --workspace-id ws_xxx --seat-type standard --account-id acc_xxx
+bl token-plan create-key --account-id acc_xxx --workspace-id ws_xxx
 ```
 
 > 更多案例与使用场景：[阿里云百炼 CLI 官方主页](https://bailian.console.aliyun.com/cli?source_channel=cli_github&)
@@ -151,9 +163,9 @@ bl text chat --api-key sk-xxxxx --message "你好"
 bl auth login --console
 ```
 
-### 阿里云 AK/SK（仅知识库检索）
+### 阿里云 AK/SK（知识库检索与 Token Plan）
 
-`knowledge retrieve` 命令需要阿里云 AccessKey。前往 [RAM 控制台](https://ram.console.aliyun.com/manage/ak) 获取。
+`knowledge retrieve` 与 `token-plan` 命令组需要阿里云 AccessKey。前往 [RAM 控制台](https://ram.console.aliyun.com/manage/ak) 获取。
 
 > 建议：创建 RAM 子账号并授予最小权限，避免使用主账号 AK/SK。
 

packages/cli/README.md

@@ -38,6 +38,7 @@ Equip your AI Agent out-of-the-box with these capabilities, composable across co
 - **MCP integration** — Orchestrate Bailian MCP servers: list services, inspect tools, and invoke any tool directly from the terminal
 - **Web search** — Real-time internet retrieval for up-to-date, accurate answers
 - **Model recommendation** — Describe your scenario and get best-fit model suggestions; supports scoped search, model comparison, and alternative discovery
+- **Fine-tuning & deployment** — Upload datasets, create SFT/LoRA/DPO/CPT jobs (`finetune create`), probe job status non-blockingly (`finetune watch`), query per-model training capability (`finetune capability`), and deploy trained models as endpoints (`deploy create`)
 - **Console capabilities** — Browse Bailian apps (`app list`), check free-tier quota (`usage free`), view model usage statistics (`usage stats`), manage workspaces (`workspace list`), and manage rate limits (`quota list/request/check/history`)
 - **Local file auto-upload** — Every URL parameter accepts a local path; uploaded to free temp storage with 48-hour validity
 
@@ -111,22 +112,30 @@ bl advisor recommend --message "qwen-max vs deepseek-v3 for code generation"
 # Browser login (required for console capability commands)
 bl auth login --console
 
+# Fine-tune & deploy — a one-shot train-to-serve workflow
+bl dataset upload --file ./train.jsonl                 # Upload a .jsonl dataset (validated first)
+bl finetune create --model qwen3-8b --datasets ./train.jsonl --training-type sft-lora  # Local paths auto-upload
+bl finetune watch --job-id ft-xxx --output json       # Non-blocking status probe (exit 0/1/3 = done/failed/running)
+bl finetune capability --model qwen3-8b               # Which training types a model supports
+bl deploy create --model qwen3-8b --name my-svc --plan mu  # Deploy the trained model as an endpoint
+
 # Browse apps / free-tier quota / usage statistics / workspaces
 bl app list
-bl usage free --model qwen3-max
-bl usage free --expiring 30                           # Quotas expiring within 30 days
-bl usage free --sort remaining                        # Sort by remaining % ascending
-bl usage stats --workspace-id <id>                    # Usage overview for a workspace
-bl usage stats --model qwen-turbo --workspace-id <id> # Per-model usage
+bl usage free                                         # Free-tier quota across models (add --model/--expiring/--sort)
+bl usage stats --workspace-id <id>                    # Model usage statistics (add --model for per-model)
 bl workspace list                                     # List all workspaces
 
-# Rate limit management
-bl quota list                                         # View RPM/TPM limits for all models
-bl quota list --model qwen3.6-plus                    # View limits for a specific model
-bl quota check                                        # Current usage vs rate limits
-bl quota check --model qwen3.6-plus --period 5        # Check usage over last 5 minutes
+# Rate limit management (list / check / request / history)
+bl quota list                                         # View RPM/TPM limits (add --model to filter)
+bl quota check                                        # Current usage vs rate limits (add --model/--period)
 bl quota request --model qwen3.6-plus --tpm 6000000   # Request a temporary TPM increase
-bl quota history                                      # View quota change history
+bl quota history                                      # View quota-change history
+
+# Token Plan team management (requires AK/SK, see auth below)
+bl token-plan list-seats                                # View subscription seat details
+bl token-plan add-member --account-name dev --org-id org_xxx
+bl token-plan assign-seats --workspace-id ws_xxx --seat-type standard --account-id acc_xxx
+bl token-plan create-key --account-id acc_xxx --workspace-id ws_xxx
 ```
 
 > More examples and scenarios: [Aliyun Model Studio CLI Site](https://bailian.console.aliyun.com/cli?source_channel=cli_github&)
@@ -156,9 +165,9 @@ Required for console capability commands (`app list`, `usage free`, `usage stats
 bl auth login --console
 ```
 
-### Alibaba Cloud AK/SK (Knowledge Base only)
+### Alibaba Cloud AK/SK (Knowledge Base & Token Plan)
 
-Required for `knowledge retrieve`. Get your AccessKey from [RAM Console](https://ram.console.aliyun.com/manage/ak).
+Required for `knowledge retrieve` and the `token-plan` command group. Get your AccessKey from [RAM Console](https://ram.console.aliyun.com/manage/ak).
 
 > Recommended: create a RAM sub-account with minimum privileges instead of using the root account's AK/SK.
 

packages/cli/README.zh.md

@@ -38,6 +38,7 @@ _专为 AI Agent 打造，每个命令均可作为结构化工具调用。_
 - **MCP 集成** — 统一调度百炼 MCP 服务：列出服务、查看工具、直接在终端调用任意工具
 - **联网搜索** — 实时互联网信息检索，提升回答准确性及时效性
 - **模型推荐** — 描述你的场景，智能推荐最适合的模型；支持限定范围搜索、模型对比和替代发现
+- **微调与部署** — 上传数据集、创建 SFT/LoRA/DPO/CPT 调优任务（`finetune create`）、非阻塞探测任务状态（`finetune watch`）、按模型查训练能力（`finetune capability`），并把训练好的模型部署为推理服务（`deploy create`）
 - **控制台能力** — 浏览百炼应用（`app list`），查询模型免费额度（`usage free`），查看模型用量统计（`usage stats`），管理业务空间（`workspace list`），管理限流与提额（`quota list/request/check/history`）
 - **本地文件自动上传** — 所有 URL 参数同时支持本地路径，免费临时存储 48 小时
 
@@ -82,7 +83,10 @@ npx skills add modelstudioai/cli --all -g
 ## 快速开始
 
 ```bash
-# 认证
+# 认证（推荐浏览器登录）
+bl auth login --console
+
+# 或使用 API key 认证
 bl auth login --api-key sk-xxxxx
 
 # 和通义千问对话
@@ -106,20 +110,22 @@ bl advisor recommend --message "qwen-max 和 deepseek-v3 哪个更适合做代
 # 浏览器登录（控制台能力相关命令需要）
 bl auth login --console
 
+# 微调与部署 — 从训练到服务的一站式流程
+bl dataset upload --file ./train.jsonl                 # 上传 .jsonl 数据集（先校验）
+bl finetune create --model qwen3-8b --datasets ./train.jsonl --training-type sft-lora  # 本地路径自动上传
+bl finetune watch --job-id ft-xxx --output json       # 非阻塞状态探测（退出码 0/1/3 = 成功/失败/进行中）
+bl finetune capability --model qwen3-8b               # 查询模型支持哪些训练方式
+bl deploy create --model qwen3-8b --name my-svc --plan mu  # 把训练好的模型部署为推理服务
+
 # 浏览应用 / 免费额度 / 用量统计 / 业务空间
 bl app list
-bl usage free --model qwen3-max
-bl usage free --expiring 30                           # 30 天内过期的额度
-bl usage free --sort remaining                        # 按剩余百分比升序排列
-bl usage stats --workspace-id <id>                    # 指定空间的用量概览
-bl usage stats --model qwen-turbo --workspace-id <id> # 指定模型用量
+bl usage free                                         # 各模型免费额度（可加 --model/--expiring/--sort）
+bl usage stats --workspace-id <id>                    # 模型用量统计（加 --model 查单模型）
 bl workspace list                                     # 列出所有业务空间
 
-# 限流管理与提额
-bl quota list                                         # 查看所有模型的 RPM/TPM 限额
-bl quota list --model qwen3.6-plus                    # 查看指定模型限额
-bl quota check                                        # 查看当前用量 vs 限流阈值
-bl quota check --model qwen3.6-plus --period 5        # 查看最近 5 分钟用量
+# 限流管理与提额（list / check / request / history）
+bl quota list                                         # 查看 RPM/TPM 限额（加 --model 过滤）
+bl quota check                                        # 当前用量 vs 限流阈值（加 --model/--period）
 bl quota request --model qwen3.6-plus --tpm 6000000   # 申请临时 TPM 提额
 bl quota history                                      # 查看提额历史记录
 

packages/cli/src/commands/catalog.ts

@@ -34,6 +34,28 @@ import searchWeb from "./search/web.ts";
 import speechSynthesize from "./speech/synthesize.ts";
 import speechRecognize from "./speech/recognize.ts";
 import fileUpload from "./file/upload.ts";
+import datasetUpload from "./dataset/upload.ts";
+import datasetList from "./dataset/list.ts";
+import datasetGet from "./dataset/get.ts";
+import datasetDelete from "./dataset/delete.ts";
+import datasetValidate from "./dataset/validate.ts";
+import finetuneCreate from "./finetune/create.ts";
+import finetuneList from "./finetune/list.ts";
+import finetuneGet from "./finetune/get.ts";
+import finetuneCancel from "./finetune/cancel.ts";
+import finetuneDelete from "./finetune/delete.ts";
+import finetuneLogs from "./finetune/logs.ts";
+import finetuneCheckpoints from "./finetune/checkpoints.ts";
+import finetuneExport from "./finetune/export.ts";
+import finetuneWatch from "./finetune/watch.ts";
+import finetuneCapability from "./finetune/capability.ts";
+import deployCreate from "./deploy/create.ts";
+import deployList from "./deploy/list.ts";
+import deployGet from "./deploy/get.ts";
+import deployModels from "./deploy/models.ts";
+import deployScale from "./deploy/scale.ts";
+import deployUpdate from "./deploy/update.ts";
+import deployDelete from "./deploy/delete.ts";
 import consoleCall from "./console/call.ts";
 import usageFree from "./usage/free.ts";
 import usageFreetier from "./usage/freetier.ts";
@@ -83,6 +105,28 @@ export const commands: Record<string, Command> = {
   "speech synthesize": speechSynthesize,
   "speech recognize": speechRecognize,
   "file upload": fileUpload,
+  "dataset upload": datasetUpload,
+  "dataset list": datasetList,
+  "dataset get": datasetGet,
+  "dataset delete": datasetDelete,
+  "dataset validate": datasetValidate,
+  "finetune create": finetuneCreate,
+  "finetune list": finetuneList,
+  "finetune get": finetuneGet,
+  "finetune cancel": finetuneCancel,
+  "finetune delete": finetuneDelete,
+  "finetune logs": finetuneLogs,
+  "finetune checkpoints": finetuneCheckpoints,
+  "finetune export": finetuneExport,
+  "finetune watch": finetuneWatch,
+  "finetune capability": finetuneCapability,
+  "deploy create": deployCreate,
+  "deploy list": deployList,
+  "deploy get": deployGet,
+  "deploy models": deployModels,
+  "deploy scale": deployScale,
+  "deploy update": deployUpdate,
+  "deploy delete": deployDelete,
   "console call": consoleCall,
   "usage free": usageFree,
   "usage freetier": usageFreetier,