Merge branch 'main' into feat/cli-skill-sync

- Add finetune video create subcommand (wan2.7/2.5/2.2 i2v + kf2v)
- Align video hyperparams with official docs (n_epochs=50, per-model batch_size/max_pixels)
- Add --last-frame flag to video generate for kf2v (image2video endpoint)
- Fix wan2.1-2.6 i2v input format (img_url instead of media[])
- Add training_cost field to finetune get/watch (catalog ft price, API-key domain only)
- Add --aigc-* flags to deploy create (optional, for video LoRA prompt config)

.github/workflows/publish-skills.yml

@@ -0,0 +1,27 @@
+# Poke the FC publish-skills flow after skills/ changes land.
+# The FC side reconciles this repo's skills/ directory against OSS
+# (bailian-wiki/skills/) using the repo HEAD snapshot as the only
+# source of truth — the request itself carries no content. Both the
+# repo and branch params are validated against FC-side whitelists
+# (PUBLISH_REPOS / PUBLISH_BRANCHES).
+#
+# feat/cli-skill-sync is temporary for end-to-end testing; remove it
+# (here and from the FC PUBLISH_BRANCHES whitelist) once the sync
+# link is verified on main.
+name: Publish skills to OSS
+
+on:
+  push:
+    branches:
+      - main
+      - feat/cli-skill-sync
+    paths:
+      - "skills/**"
+
+jobs:
+  poke:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Trigger FC publish-skills
+        run: |
+          curl -sf -X POST "${{ vars.FC_TRIGGER_URL }}/publish-skills?repo=modelstudioai/cli&branch=${{ github.ref_name }}"

packages/cli/src/commands.ts

@@ -62,6 +62,7 @@ import {
   finetuneTextCreate,
   finetuneAudioCreate,
   finetuneImageCreate,
+  finetuneVideoCreate,
   finetuneList,
   finetuneGet,
   finetuneCancel,
@@ -71,6 +72,7 @@ import {
   finetuneExport,
   finetuneWatch,
   finetuneCapability,
+  finetunePrice,
   deployTextCreate,
   deployAudioCreate,
   deployImageCreate,
@@ -80,6 +82,8 @@ import {
   deployScale,
   deployUpdate,
   deployDelete,
+  deployPause,
+  deployResume,
   tokenPlanListSeats,
   tokenPlanCreateKey,
   tokenPlanAssignSeats,
@@ -181,6 +185,7 @@ export const commands: Record<string, AnyCommand> = {
   "finetune text create": finetuneTextCreate,
   "finetune audio create": finetuneAudioCreate,
   "finetune image create": finetuneImageCreate,
+  "finetune video create": finetuneVideoCreate,
   "finetune list": finetuneList,
   "finetune get": finetuneGet,
   "finetune cancel": finetuneCancel,
@@ -190,6 +195,7 @@ export const commands: Record<string, AnyCommand> = {
   "finetune export": finetuneExport,
   "finetune watch": finetuneWatch,
   "finetune capability": finetuneCapability,
+  "finetune price": finetunePrice,
   "deploy text create": deployTextCreate,
   "deploy audio create": deployAudioCreate,
   "deploy image create": deployImageCreate,
@@ -199,6 +205,8 @@ export const commands: Record<string, AnyCommand> = {
   "deploy scale": deployScale,
   "deploy update": deployUpdate,
   "deploy delete": deployDelete,
+  "deploy pause": deployPause,
+  "deploy resume": deployResume,
   "token-plan list-seats": tokenPlanListSeats,
   "token-plan create-key": tokenPlanCreateKey,
   "token-plan assign-seats": tokenPlanAssignSeats,

packages/commands/src/commands/dataset/delete.ts

@@ -1,5 +1,5 @@
-import { defineCommand, detectOutputFormat, deleteDataset, type FlagsDef } from "bailian-cli-core";
-import { emitResult, emitBare, emitRequestId } from "bailian-cli-runtime";
+import { defineCommand, deleteDataset, type FlagsDef } from "bailian-cli-core";
+import { emitResult, emitBare } from "bailian-cli-runtime";
 
 const DELETE_FLAGS = {
   fileId: {
@@ -19,20 +19,18 @@ export default defineCommand({
   async run(ctx) {
     const { settings, flags } = ctx;
     const fileId = flags.fileId;
-    const format = detectOutputFormat(settings.output);
 
     if (settings.dryRun) {
-      emitResult({ action: "dataset.delete", file_id: fileId }, format);
+      emitResult({ action: "dataset.delete", file_id: fileId }, "json");
       return;
     }
 
     const response = await deleteDataset(ctx.client, fileId);
 
-    if (settings.quiet || format === "text") {
-      emitBare(`Deleted ${fileId}.`);
-      emitRequestId(response.request_id, settings.quiet);
+    if (settings.quiet) {
+      emitBare(fileId);
     } else {
-      emitResult(response, format);
+      emitResult(response, "json");
     }
   },
 });

packages/commands/src/commands/dataset/get.ts

@@ -1,5 +1,5 @@
-import { defineCommand, detectOutputFormat, getDataset, type FlagsDef } from "bailian-cli-core";
-import { emitResult, emitBare, emitRequestId } from "bailian-cli-runtime";
+import { defineCommand, getDataset, type FlagsDef } from "bailian-cli-core";
+import { emitResult, emitBare } from "bailian-cli-runtime";
 
 const GET_FLAGS = {
   fileId: {
@@ -19,10 +19,9 @@ export default defineCommand({
   async run(ctx) {
     const { settings, flags } = ctx;
     const fileId = flags.fileId;
-    const format = detectOutputFormat(settings.output);
 
     if (settings.dryRun) {
-      emitResult({ action: "dataset.get", file_id: fileId }, format);
+      emitResult({ action: "dataset.get", file_id: fileId }, "json");
       return;
     }
 
@@ -45,19 +44,10 @@ export default defineCommand({
       description: file.description ?? "",
     };
 
-    if (format === "json") {
-      emitResult({ ...item, request_id: response.request_id }, format);
-      return;
+    if (settings.quiet) {
+      emitBare(item.file_id);
+    } else {
+      emitResult({ ...item, request_id: response.request_id }, "json");
     }
-
-    // text / quiet
-    emitBare(`file_id:      ${item.file_id}`);
-    emitBare(`name:         ${item.name}`);
-    emitBare(`size:         ${item.size}`);
-    if (item.md5) emitBare(`md5:          ${item.md5}`);
-    if (item.purpose) emitBare(`purpose:      ${item.purpose}`);
-    if (item.created_at) emitBare(`created_at:   ${item.created_at}`);
-    if (item.description) emitBare(`description:  ${item.description}`);
-    emitRequestId(response.request_id, settings.quiet);
   },
 });

packages/commands/src/commands/dataset/list.ts

@@ -1,5 +1,5 @@
-import { defineCommand, detectOutputFormat, listDatasets, type FlagsDef } from "bailian-cli-core";
-import { emitResult, emitBare, emitRequestId, formatTable } from "bailian-cli-runtime";
+import { defineCommand, listDatasets, type FlagsDef } from "bailian-cli-core";
+import { emitResult, emitBare } from "bailian-cli-runtime";
 
 const LIST_FLAGS = {
   page: { type: "number", valueHint: "<n>", description: "Page number (default: 1)" },
@@ -23,7 +23,6 @@ export default defineCommand({
   exampleArgs: ["", "--purpose fine-tune", "--purpose evaluation --page-size 20", "--output json"],
   async run(ctx) {
     const { settings, flags } = ctx;
-    const format = detectOutputFormat(settings.output);
 
     if (settings.dryRun) {
       emitResult(
@@ -33,7 +32,7 @@ export default defineCommand({
           page_size: flags.pageSize,
           purpose: flags.purpose,
         },
-        format,
+        "json",
       );
       return;
     }
@@ -46,7 +45,6 @@ export default defineCommand({
     const files = response.data?.files ?? [];
     const total = response.data?.total;
 
-    // Normalize to consistent structure for both text/json output.
     const items = files.map((item) => ({
       file_id: item.file_id ?? "",
       name: item.name ?? "",
@@ -54,20 +52,10 @@ export default defineCommand({
       purpose: item.purpose ?? "",
     }));
 
-    if (format === "json") {
-      emitResult({ items, total, request_id: response.request_id }, format);
-      return;
+    if (settings.quiet) {
+      for (const item of items) emitBare(item.file_id);
+    } else {
+      emitResult({ items, total, request_id: response.request_id }, "json");
     }
-
-    // text / quiet
-    if (items.length === 0) {
-      emitBare("No dataset files found.");
-      return;
-    }
-    const headers = ["FILE_ID", "NAME", "SIZE", "PURPOSE"];
-    const rows = items.map((i) => [i.file_id, i.name, i.size, i.purpose]);
-    for (const line of formatTable(headers, rows)) emitBare(line);
-    if (total !== undefined) emitBare(`\nTotal: ${total}`);
-    emitRequestId(response.request_id, settings.quiet);
   },
 });

packages/commands/src/commands/dataset/upload.ts

@@ -1,6 +1,5 @@
 import {
   defineCommand,
-  detectOutputFormat,
   uploadDataset,
   validateDataset,
   parseDatasetSchemaFlag,
@@ -11,7 +10,7 @@ import {
   ExitCode,
   type FlagsDef,
 } from "bailian-cli-core";
-import { emitResult, emitBare, emitRequestId } from "bailian-cli-runtime";
+import { emitResult, emitBare } from "bailian-cli-runtime";
 
 const UPLOAD_FLAGS = {
   file: {
@@ -80,7 +79,6 @@ export default defineCommand({
         `Supported schemas: chatml, dpo, cpt, tts, image.`,
       );
     }
-    const format = detectOutputFormat(settings.output);
     // Image schema allows larger ZIPs (1 GB vs 300 MB for text).
     const isMediaSchema = schema === "image";
 
@@ -129,7 +127,7 @@ export default defineCommand({
           validate: !flags.noValidate,
           schema: schema ?? "auto",
         },
-        format,
+        "json",
       );
       return;
     }
@@ -142,11 +140,8 @@ export default defineCommand({
 
     if (settings.quiet) {
       emitBare(file.file_id);
-    } else if (format === "text") {
-      emitBare(`Uploaded ${file.name} → file_id=${file.file_id}`);
-      emitRequestId(request_id, settings.quiet);
     } else {
-      emitResult({ ...file, request_id }, format);
+      emitResult({ ...file, request_id }, "json");
     }
   },
 });

packages/commands/src/commands/dataset/validate.ts

@@ -1,26 +1,13 @@
 import {
   defineCommand,
-  detectOutputFormat,
   validateDataset,
   parseDatasetSchemaFlag,
-  formatIssue,
   BailianError,
   ExitCode,
-  type ValidationResult,
   type FlagsDef,
 } from "bailian-cli-core";
 import { emitResult, emitBare } from "bailian-cli-runtime";
 
-function formatStats(result: ValidationResult): string[] {
-  const out: string[] = [];
-  if (result.stats.totalRecords !== undefined) out.push(`records: ${result.stats.totalRecords}`);
-  if (result.stats.sampledRecords !== undefined)
-    out.push(`sampled: ${result.stats.sampledRecords}`);
-  if (result.stats.bytes !== undefined) out.push(`bytes: ${result.stats.bytes}`);
-  if (result.stats.durationMs !== undefined) out.push(`took: ${result.stats.durationMs}ms`);
-  return out;
-}
-
 const VALIDATE_FLAGS = {
   file: {
     type: "string",
@@ -79,8 +66,6 @@ export default defineCommand({
         `Supported schemas: chatml, dpo, cpt, tts, image.`,
       );
     }
-    const format = detectOutputFormat(settings.output);
-
     if (settings.dryRun) {
       emitResult(
         {
@@ -89,38 +74,17 @@ export default defineCommand({
           full: flags.fullValidate,
           schema: schema ?? "auto",
         },
-        format,
+        "json",
       );
       return;
     }
 
     const result = await validateDataset(filePath, { fullValidate: flags.fullValidate, schema });
 
-    if (format === "json") {
-      // For json output we always emit the structured result, exit code conveys validity.
-      emitResult(result, format);
-    } else if (settings.quiet) {
+    if (settings.quiet) {
       emitBare(result.valid ? "ok" : "fail");
     } else {
-      const status = result.valid ? "PASSED" : "FAILED";
-      emitBare(`Dataset validation ${status} for ${result.filePath}`);
-      const stats = formatStats(result);
-      if (stats.length) emitBare(`  ${stats.join(" · ")}`);
-
-      if (result.errors.length) {
-        emitBare(`Errors (${result.errors.length}):`);
-        for (const error of result.errors.slice(0, 20)) emitBare(formatIssue(error));
-        if (result.errors.length > 20) {
-          emitBare(`  … and ${result.errors.length - 20} more.`);
-        }
-      }
-      if (result.warnings.length) {
-        emitBare(`Warnings (${result.warnings.length}):`);
-        for (const warning of result.warnings.slice(0, 10)) emitBare(formatIssue(warning));
-        if (result.warnings.length > 10) {
-          emitBare(`  … and ${result.warnings.length - 10} more.`);
-        }
-      }
+      emitResult(result, "json");
     }
 
     if (!result.valid) {

packages/commands/src/commands/deploy/create.ts

@@ -1,6 +1,5 @@
 import {
   defineCommand,
-  detectOutputFormat,
   createDeployment,
   pickPlanStrategy,
   STRATEGIES,
@@ -11,16 +10,16 @@ import {
   type CommandContext,
   type FlagsDef,
 } from "bailian-cli-core";
-import { emitResult, emitBare, emitRequestId } from "bailian-cli-runtime";
+import { emitResult, emitBare } from "bailian-cli-runtime";
 
 const CREATE_FLAGS = {
-  model: {
+  modelName: {
     type: "string",
-    valueHint: "<name>",
-    description: "Model name (catalog model or fine-tuned output) (required)",
+    valueHint: "<model_name>",
+    description: "Model to deploy — fine-tuned output name or catalog model (required)",
     required: true,
   },
-  name: {
+  displayName: {
     type: "string",
     valueHint: "<display_name>",
     description: "Console display name for the deployment (required)",
@@ -64,7 +63,7 @@ const CREATE_FLAGS = {
 } satisfies FlagsDef;
 
 const CREATE_USAGE =
-  "--model <model_name> --name <display_name> [--plan <plan>] [--deploy-spec <id>] [--capacity <n>] [--billing-method <m>] [--input-tpm <n>] [--output-tpm <n>] [--thinking-output-tpm <n>]";
+  "--model-name <model_name> --display-name <display_name> [--plan <plan>] [--deploy-spec <id>] [--capacity <n>] [--billing-method <m>] [--input-tpm <n>] [--output-tpm <n>] [--thinking-output-tpm <n>]";
 
 const CREATE_NOTES = [
   "Plan defaults to `lora` (Token-billed) for text/image and `mu` (model-unit-",
@@ -78,14 +77,11 @@ const CREATE_NOTES = [
   "Use `bl deploy models --source base` to inspect available templates.",
   "After creation, status starts at PENDING and transitions to RUNNING.",
   "Invoke the deployed model with: bl text chat --model <deployed_model>",
-  "WARNING: --model is overloaded across commands and refers to DIFFERENT",
-  "values. `bl deploy <modality> create --model` takes the exported model_name",
-  "(e.g. `qwen3-8b-ft-...`), but the create response also returns a",
-  "`deployed_model` field (the deployment instance id, e.g.",
-  "`qwen3-8b-5ecb5f068d79`). The inference call `bl text chat --model` must use",
-  "the `deployed_model` from the create response — NOT the `model_name` you",
-  "passed to `deploy <modality> create`. Do not reuse the value across the two",
-  "commands.",
+  "NOTE: --model-name is the model being deployed (e.g. `qwen3-8b-ft-...`).",
+  "The create response also returns a `deployed_model` field — the deployment",
+  "instance id (e.g. `qwen3-8b-5ecb5f068d79`). Use that id for inference",
+  "(`bl text chat --model <deployed_model>`) and lifecycle commands",
+  "(`deploy get/scale/pause/resume/delete --deployed-model <id>`).",
 ];
 
 /**
@@ -119,10 +115,9 @@ async function runCreate(
   ctx: CommandContext<typeof CREATE_FLAGS>,
 ): Promise<void> {
   const { identity, settings, flags } = ctx;
-  const model = flags.model as string;
-  const name = flags.name as string;
+  const model = flags.modelName as string;
+  const name = flags.displayName as string;
   const plan = (flags.plan as string | undefined) || defaultDeployPlan(modality);
-  const format = detectOutputFormat(settings.output);
 
   // Plan-specific behaviour is owned by core `plans.ts`. The strategy resolves
   // the plan-specific body fragment (mu may auto-pick a template from the
@@ -146,7 +141,7 @@ async function runCreate(
   };
 
   if (settings.dryRun) {
-    emitResult({ action: "deploy.create", body }, format);
+    emitResult({ action: "deploy.create", body }, "json");
     return;
   }
 
@@ -155,17 +150,8 @@ async function runCreate(
 
   if (settings.quiet) {
     emitBare(deployment?.deployed_model ?? "");
-  } else if (format === "text") {
-    emitBare(`Created deployment.`);
-    if (deployment?.deployed_model) emitBare(`  deployed_model:  ${deployment.deployed_model}`);
-    if (deployment?.status) emitBare(`  status:          ${deployment.status}`);
-    if (deployment?.plan) emitBare(`  plan:            ${deployment.plan}`);
-    emitBare(
-      `\nNext: track readiness with: ${identity.binName} deploy get --deployed-model ${deployment?.deployed_model ?? "<id>"}`,
-    );
-    emitRequestId(response.request_id, settings.quiet);
   } else {
-    emitResult(response, format);
+    emitResult(response, "json");
   }
 }
 
@@ -176,10 +162,10 @@ export const deployTextCreate = defineCommand({
   usageArgs: CREATE_USAGE,
   flags: CREATE_FLAGS,
   exampleArgs: [
-    "--model my-qwen-sft --name my-sft-test",
-    "--model qwen3.6-flash-2026-04-16 --name my-flash --plan ptu --input-tpm 10000 --output-tpm 1000",
-    "--model qwen3-8b --name my-qwen3-mu --plan mu",
-    "--model qwen3-8b --name my-qwen3 --plan mu --deploy-spec MU1 --capacity 2",
+    "--model-name my-qwen-sft --display-name my-sft-test",
+    "--model-name qwen3.6-flash-2026-04-16 --display-name my-flash --plan ptu --input-tpm 10000 --output-tpm 1000",
+    "--model-name qwen3-8b --display-name my-qwen3-mu --plan mu",
+    "--model-name qwen3-8b --display-name my-qwen3 --plan mu --deploy-spec MU1 --capacity 2",
   ],
   notes: CREATE_NOTES,
   validate: (flags) => validateCreate("text", flags),
@@ -193,9 +179,9 @@ export const deployAudioCreate = defineCommand({
   usageArgs: CREATE_USAGE,
   flags: CREATE_FLAGS,
   exampleArgs: [
-    "--model my-cosyvoice-ft --name my-tts",
-    "--model my-cosyvoice-ft --name my-tts --deploy-spec dps-xxxx --capacity 1",
-    "--model my-cosyvoice-ft --name my-tts --dry-run",
+    "--model-name my-cosyvoice-ft --display-name my-tts",
+    "--model-name my-cosyvoice-ft --display-name my-tts --deploy-spec dps-xxxx --capacity 1",
+    "--model-name my-cosyvoice-ft --display-name my-tts --dry-run",
   ],
   notes: CREATE_NOTES,
   validate: (flags) => validateCreate("audio", flags),
@@ -209,9 +195,9 @@ export const deployImageCreate = defineCommand({
   usageArgs: CREATE_USAGE,
   flags: CREATE_FLAGS,
   exampleArgs: [
-    "--model my-wan-ft --name my-wan",
-    "--model my-wan-ft --name my-wan-mu --plan mu",
-    "--model my-wan-ft --name my-wan --dry-run",
+    "--model-name my-wan-ft --display-name my-wan",
+    "--model-name my-wan-ft --display-name my-wan-mu --plan mu",
+    "--model-name my-wan-ft --display-name my-wan --dry-run",
   ],
   notes: CREATE_NOTES,
   validate: (flags) => validateCreate("image", flags),

packages/commands/src/commands/deploy/delete.ts

@@ -1,13 +1,12 @@
 import {
   defineCommand,
-  detectOutputFormat,
   deleteDeployment,
   getDeployment,
   BailianError,
   ExitCode,
   type FlagsDef,
 } from "bailian-cli-core";
-import { emitResult, emitBare, emitRequestId } from "bailian-cli-runtime";
+import { emitResult, emitBare } from "bailian-cli-runtime";
 
 const DELETE_FLAGS = {
   deployedModel: {
@@ -38,10 +37,9 @@ export default defineCommand({
   async run(ctx) {
     const { settings, flags } = ctx;
     const deployedModel = flags.deployedModel;
-    const format = detectOutputFormat(settings.output);
 
     if (settings.dryRun) {
-      emitResult({ action: "deploy.delete", deployed_model: deployedModel }, format);
+      emitResult({ action: "deploy.delete", deployed_model: deployedModel }, "json");
       return;
     }
 
@@ -55,7 +53,8 @@ export default defineCommand({
         if (status && status !== "STOPPED" && status !== "FAILED") {
           throw new BailianError(
             `Deployment ${deployedModel} is ${status}. Only STOPPED / FAILED deployments can be deleted. ` +
-              `Stop it first via the platform console, or pass --skip-precheck to attempt deletion anyway.`,
+              `Run \`bl deploy pause --deployed-model ${deployedModel}\` to pause it first, ` +
+              `or pass --skip-precheck to attempt deletion anyway.`,
             ExitCode.USAGE,
           );
         }
@@ -69,11 +68,8 @@ export default defineCommand({
 
     if (settings.quiet) {
       emitBare(deployedModel);
-    } else if (format === "text") {
-      emitBare(`Deleted ${deployedModel}.`);
-      emitRequestId(response.request_id, settings.quiet);
     } else {
-      emitResult(response, format);
+      emitResult(response, "json");
     }
   },
 });

packages/commands/src/commands/deploy/get.ts

@@ -1,5 +1,5 @@
-import { defineCommand, detectOutputFormat, getDeployment, type FlagsDef } from "bailian-cli-core";
-import { emitResult, emitBare, emitRequestId } from "bailian-cli-runtime";
+import { defineCommand, getDeployment, type FlagsDef } from "bailian-cli-core";
+import { emitResult } from "bailian-cli-runtime";
 
 const GET_FLAGS = {
   deployedModel: {
@@ -22,10 +22,9 @@ export default defineCommand({
   async run(ctx) {
     const { settings, flags } = ctx;
     const deployedModel = flags.deployedModel;
-    const format = detectOutputFormat(settings.output);
 
     if (settings.dryRun) {
-      emitResult({ action: "deploy.get", deployed_model: deployedModel }, format);
+      emitResult({ action: "deploy.get", deployed_model: deployedModel }, "json");
       return;
     }
 
@@ -33,7 +32,7 @@ export default defineCommand({
     const deployment = response.output ?? response.data;
 
     if (!deployment) {
-      emitBare(`No data returned for ${deployedModel}`);
+      emitResult({ deployed_model: deployedModel, request_id: response.request_id }, "json");
       return;
     }
 
@@ -57,18 +56,6 @@ export default defineCommand({
     if (deployment.gmt_create) item.created_at = deployment.gmt_create;
     if (deployment.gmt_modified) item.updated_at = deployment.gmt_modified;
 
-    if (format === "json") {
-      emitResult({ ...item, request_id: response.request_id }, format);
-      return;
-    }
-
-    // text / quiet — fixed-width label column for alignment
-    const label = (key: string) => `${key}:`.padEnd(18);
-    for (const [key, value] of Object.entries(item)) {
-      if (value === "" || value === undefined) continue;
-      const display = typeof value === "string" ? value : JSON.stringify(value);
-      emitBare(`${label(key)}${display}`);
-    }
-    emitRequestId(response.request_id, settings.quiet);
+    emitResult({ ...item, request_id: response.request_id }, "json");
   },
 });

packages/commands/src/commands/deploy/list.ts

@@ -1,10 +1,5 @@
-import {
-  defineCommand,
-  detectOutputFormat,
-  listDeployments,
-  type FlagsDef,
-} from "bailian-cli-core";
-import { emitResult, emitBare, emitRequestId, formatTable } from "bailian-cli-runtime";
+import { defineCommand, listDeployments, type FlagsDef } from "bailian-cli-core";
+import { emitResult } from "bailian-cli-runtime";
 
 const LIST_FLAGS = {
   page: { type: "number", valueHint: "<n>", description: "Page number (default: 1)" },
@@ -28,13 +23,12 @@ export default defineCommand({
   exampleArgs: ["", "--status RUNNING", "--page-size 20 --output json"],
   async run(ctx) {
     const { settings, flags } = ctx;
-    const format = detectOutputFormat(settings.output);
     const status = flags.status || undefined;
 
     if (settings.dryRun) {
       emitResult(
         { action: "deploy.list", page: flags.page, page_size: flags.pageSize, status },
-        format,
+        "json",
       );
       return;
     }
@@ -57,27 +51,6 @@ export default defineCommand({
       created_at: item.gmt_create ?? "",
     }));
 
-    if (format === "json") {
-      emitResult({ items, total, request_id: response.request_id }, format);
-      return;
-    }
-
-    // text / quiet
-    if (items.length === 0) {
-      emitBare("No deployments found.");
-      return;
-    }
-    const headers = ["DEPLOYED_MODEL", "MODEL_NAME", "STATUS", "PLAN", "CAPACITY", "CREATED_AT"];
-    const rows = items.map((item) => [
-      item.deployed_model,
-      item.model_name,
-      item.status,
-      item.plan,
-      item.capacity,
-      item.created_at,
-    ]);
-    for (const line of formatTable(headers, rows)) emitBare(line);
-    if (total !== undefined) emitBare(`\nTotal: ${total}`);
-    emitRequestId(response.request_id, settings.quiet);
+    emitResult({ items, total, request_id: response.request_id }, "json");
   },
 });

packages/commands/src/commands/deploy/models.ts

@@ -1,10 +1,5 @@
-import {
-  defineCommand,
-  detectOutputFormat,
-  listDeployableModels,
-  type FlagsDef,
-} from "bailian-cli-core";
-import { emitResult, emitBare, emitRequestId, formatTable } from "bailian-cli-runtime";
+import { defineCommand, listDeployableModels, type FlagsDef } from "bailian-cli-core";
+import { emitResult } from "bailian-cli-runtime";
 
 const MODELS_FLAGS = {
   page: { type: "number", valueHint: "<n>", description: "Page number (default: 1)" },
@@ -39,7 +34,6 @@ export default defineCommand({
   ],
   async run(ctx) {
     const { settings, flags } = ctx;
-    const format = detectOutputFormat(settings.output);
     // Default version to v1.0 — without it, the API returns the legacy catalog
     // (only old fine-tune outputs). Pass --catalog-version "" to opt out.
     const version = flags.catalogVersion === "" ? undefined : (flags.catalogVersion ?? "v1.0");
@@ -54,7 +48,7 @@ export default defineCommand({
           version,
           model_source: modelSource,
         },
-        format,
+        "json",
       );
       return;
     }
@@ -72,102 +66,55 @@ export default defineCommand({
     // Two response shapes:
     //   - custom (fine-tuned): top-level supported_plans: string[]
     //   - base (catalog):      plans: [{plan, templates?, cu_specs?}]
-    // For json: surface the deployment-relevant fields preserved as a tree, so
+    // Surface the deployment-relevant fields preserved as a tree, so
     // downstream tooling can drive `bl deploy <modality> create --deploy-spec <…>`
-    // without a second round-trip. For text: keep the compact one-line summary.
-    if (format === "json") {
-      const items = models.map((model) => {
-        const out: Record<string, unknown> = {
-          model_name: model.model_name ?? "",
-        };
-        if (model.base_model) out.base_model = model.base_model;
-        if (model.model_source) out.model_source = model.model_source;
-        if (model.supported_plans && model.supported_plans.length > 0) {
-          out.supported_plans = model.supported_plans;
-        }
-        if (model.plans && model.plans.length > 0) {
-          out.plans = model.plans.map((plan) => {
-            const planEntry: Record<string, unknown> = { plan: plan.plan ?? "" };
-            if (plan.cu_specs && plan.cu_specs.length > 0) {
-              planEntry.cu_specs = plan.cu_specs;
-            }
-            if (plan.templates && plan.templates.length > 0) {
-              // Pull the top 6 fields most useful for `bl deploy <modality> create`.
-              // Drop noisy/redundant: template_source, template_type,
-              // template_version, deploy_spec (typically == template_id).
-              planEntry.templates = plan.templates.map((template) => {
-                const tpl: Record<string, unknown> = {};
-                if (template.template_id) tpl.template_id = template.template_id;
-                if (template.template_name) tpl.template_name = template.template_name;
-                if (template.charge_type) tpl.charge_type = template.charge_type;
-                // Flatten roles.unified for the common COUPLED case.
-                const unified = template.roles?.unified;
-                if (unified?.model_unit_spec) tpl.model_unit_spec = unified.model_unit_spec;
-                if (unified?.capacity_unit_per_instance !== undefined)
-                  tpl.capacity_unit_per_instance = unified.capacity_unit_per_instance;
-                // Preserve split-role configs (SEPERATED) as-is so callers
-                // can still drive prefill/decode sizing.
-                if (template.roles?.prefill || template.roles?.decode) {
-                  tpl.roles = {
-                    prefill: template.roles?.prefill,
-                    decode: template.roles?.decode,
-                  };
-                }
-                if (template.template_desc) tpl.template_desc = template.template_desc;
-                return tpl;
-              });
-            }
-            return planEntry;
-          });
-        }
-        return out;
-      });
-      emitResult({ items, total, request_id: response.request_id }, format);
-      return;
-    }
-
-    // text / quiet — keep the compact single-line summary table.
-    const textItems = models.map((model) => {
-      let plansSummary = "";
-      if (model.supported_plans && model.supported_plans.length > 0) {
-        plansSummary = model.supported_plans.join(",");
-      } else if (model.plans && model.plans.length > 0) {
-        plansSummary = model.plans
-          .map((plan) => {
-            const planName = plan.plan ?? "?";
-            if (plan.templates && plan.templates.length > 0) {
-              return `${planName}(${plan.templates.length}t)`;
-            }
-            if (plan.cu_specs && plan.cu_specs.length > 0) {
-              return `${planName}(${plan.cu_specs.join("/")})`;
-            }
-            return planName;
-          })
-          .join(",");
-      } else {
-        plansSummary = "-";
-      }
-      return {
+    // without a second round-trip.
+    const items = models.map((model) => {
+      const out: Record<string, unknown> = {
         model_name: model.model_name ?? "",
-        base_model: model.base_model ?? "",
-        source: model.model_source ?? "",
-        plans: plansSummary,
       };
+      if (model.base_model) out.base_model = model.base_model;
+      if (model.model_source) out.model_source = model.model_source;
+      if (model.supported_plans && model.supported_plans.length > 0) {
+        out.supported_plans = model.supported_plans;
+      }
+      if (model.plans && model.plans.length > 0) {
+        out.plans = model.plans.map((plan) => {
+          const planEntry: Record<string, unknown> = { plan: plan.plan ?? "" };
+          if (plan.cu_specs && plan.cu_specs.length > 0) {
+            planEntry.cu_specs = plan.cu_specs;
+          }
+          if (plan.templates && plan.templates.length > 0) {
+            // Pull the top 6 fields most useful for `bl deploy <modality> create`.
+            // Drop noisy/redundant: template_source, template_type,
+            // template_version, deploy_spec (typically == template_id).
+            planEntry.templates = plan.templates.map((template) => {
+              const tpl: Record<string, unknown> = {};
+              if (template.template_id) tpl.template_id = template.template_id;
+              if (template.template_name) tpl.template_name = template.template_name;
+              if (template.charge_type) tpl.charge_type = template.charge_type;
+              // Flatten roles.unified for the common COUPLED case.
+              const unified = template.roles?.unified;
+              if (unified?.model_unit_spec) tpl.model_unit_spec = unified.model_unit_spec;
+              if (unified?.capacity_unit_per_instance !== undefined)
+                tpl.capacity_unit_per_instance = unified.capacity_unit_per_instance;
+              // Preserve split-role configs (SEPERATED) as-is so callers
+              // can still drive prefill/decode sizing.
+              if (template.roles?.prefill || template.roles?.decode) {
+                tpl.roles = {
+                  prefill: template.roles?.prefill,
+                  decode: template.roles?.decode,
+                };
+              }
+              if (template.template_desc) tpl.template_desc = template.template_desc;
+              return tpl;
+            });
+          }
+          return planEntry;
+        });
+      }
+      return out;
     });
-
-    if (textItems.length === 0) {
-      emitBare("No deployable models found.");
-      return;
-    }
-    const headers = ["MODEL_NAME", "BASE_MODEL", "SOURCE", "PLANS"];
-    const rows = textItems.map((item) => [
-      item.model_name,
-      item.base_model,
-      item.source,
-      item.plans,
-    ]);
-    for (const line of formatTable(headers, rows)) emitBare(line);
-    if (total !== undefined) emitBare(`\nTotal: ${total}`);
-    emitRequestId(response.request_id, settings.quiet);
+    emitResult({ items, total, request_id: response.request_id }, "json");
   },
 });

packages/commands/src/commands/deploy/pause.ts

@@ -0,0 +1,85 @@
+import {
+  defineCommand,
+  stopModelService,
+  listIndependentDeployedModels,
+  findDeploymentEntry,
+  BailianError,
+  ExitCode,
+  type FlagsDef,
+} from "bailian-cli-core";
+import { emitResult, emitBare } from "bailian-cli-runtime";
+
+const PAUSE_FLAGS = {
+  deployedModel: {
+    type: "string",
+    valueHint: "<id>",
+    description: "Deployed model identifier (required)",
+    required: true,
+  },
+  skipPrecheck: {
+    type: "switch",
+    description: "Skip the local RUNNING/PENDING status precheck",
+  },
+} satisfies FlagsDef;
+
+/**
+ * `bl deploy pause` — pause a running deployment.
+ *
+ * Takes the model service offline so it no longer serves inference requests.
+ * For mu/ptu plans, billing stops while paused.
+ * Precheck: status must be RUNNING or PENDING.
+ */
+export default defineCommand({
+  description: "Pause a running model deployment (stops billing for mu/ptu)",
+  auth: "console",
+  usageArgs: "--deployed-model <id> [--skip-precheck]",
+  flags: PAUSE_FLAGS,
+  exampleArgs: [
+    "--deployed-model dep-...",
+    "--deployed-model dep-... --skip-precheck",
+    "--deployed-model dep-... --dry-run",
+  ],
+  notes: [
+    "While paused, billing ceases for mu/ptu plans. Use `deploy resume` to bring it back online or `deploy delete` to remove.",
+    "Precheck verifies status is RUNNING/PENDING before issuing the pause; pass --skip-precheck to bypass.",
+  ],
+  async run(ctx) {
+    const { settings, flags } = ctx;
+    const deployedModel = flags.deployedModel;
+
+    if (settings.dryRun) {
+      emitResult({ action: "deploy.pause", deployed_model: deployedModel }, "json");
+      return;
+    }
+
+    // Precheck: verify the deployment is in a pausable state.
+    if (!flags.skipPrecheck) {
+      try {
+        const entries = await listIndependentDeployedModels(ctx.client);
+        const entry = findDeploymentEntry(entries, deployedModel);
+        if (entry) {
+          const status = (entry.status ?? "").toUpperCase();
+          if (status && status !== "RUNNING" && status !== "PENDING") {
+            throw new BailianError(
+              `Deployment ${deployedModel} is ${status}. Only RUNNING / PENDING deployments can be paused. ` +
+                `Pass --skip-precheck to attempt the pause anyway.`,
+              ExitCode.USAGE,
+            );
+          }
+        }
+        // If entry not found in list, proceed — the server will surface the real error.
+      } catch (error) {
+        if (error instanceof BailianError) throw error;
+        // If the list call itself failed, proceed and let the API call surface the error.
+      }
+    }
+
+    const response = await stopModelService(ctx.client, deployedModel);
+
+    if (settings.quiet) {
+      emitBare(deployedModel);
+    } else {
+      emitResult({ deployed_model: deployedModel, action: "pause", ...response }, "json");
+    }
+  },
+});

packages/commands/src/commands/deploy/resume.ts

@@ -0,0 +1,84 @@
+import {
+  defineCommand,
+  startModelService,
+  listIndependentDeployedModels,
+  findDeploymentEntry,
+  BailianError,
+  ExitCode,
+  type FlagsDef,
+} from "bailian-cli-core";
+import { emitResult, emitBare } from "bailian-cli-runtime";
+
+const RESUME_FLAGS = {
+  deployedModel: {
+    type: "string",
+    valueHint: "<id>",
+    description: "Deployed model identifier (required)",
+    required: true,
+  },
+  skipPrecheck: {
+    type: "switch",
+    description: "Skip the local STOPPED status precheck",
+  },
+} satisfies FlagsDef;
+
+/**
+ * `bl deploy resume` — resume a paused deployment.
+ *
+ * Brings the model service back online so it can serve inference requests.
+ * Precheck: status must be STOPPED.
+ */
+export default defineCommand({
+  description: "Resume a paused model deployment (brings service back online)",
+  auth: "console",
+  usageArgs: "--deployed-model <id> [--skip-precheck]",
+  flags: RESUME_FLAGS,
+  exampleArgs: [
+    "--deployed-model dep-...",
+    "--deployed-model dep-... --skip-precheck",
+    "--deployed-model dep-... --dry-run",
+  ],
+  notes: [
+    "Precheck verifies status is STOPPED before issuing the resume; pass --skip-precheck to bypass.",
+    "For mu/ptu plans, billing resumes once the service is back online.",
+  ],
+  async run(ctx) {
+    const { settings, flags } = ctx;
+    const deployedModel = flags.deployedModel;
+
+    if (settings.dryRun) {
+      emitResult({ action: "deploy.resume", deployed_model: deployedModel }, "json");
+      return;
+    }
+
+    // Precheck: verify the deployment is in a resumable state.
+    if (!flags.skipPrecheck) {
+      try {
+        const entries = await listIndependentDeployedModels(ctx.client);
+        const entry = findDeploymentEntry(entries, deployedModel);
+        if (entry) {
+          const status = (entry.status ?? "").toUpperCase();
+          if (status && status !== "STOPPED") {
+            throw new BailianError(
+              `Deployment ${deployedModel} is ${status}. Only STOPPED deployments can be resumed. ` +
+                `Pass --skip-precheck to attempt the resume anyway.`,
+              ExitCode.USAGE,
+            );
+          }
+        }
+        // If entry not found in list, proceed — the server will surface the real error.
+      } catch (error) {
+        if (error instanceof BailianError) throw error;
+        // If the list call itself failed, proceed and let the API call surface the error.
+      }
+    }
+
+    const response = await startModelService(ctx.client, deployedModel);
+
+    if (settings.quiet) {
+      emitBare(deployedModel);
+    } else {
+      emitResult({ deployed_model: deployedModel, action: "resume", ...response }, "json");
+    }
+  },
+});

packages/commands/src/commands/deploy/scale.ts

@@ -1,10 +1,5 @@
-import {
-  defineCommand,
-  detectOutputFormat,
-  scaleDeployment,
-  type FlagsDef,
-} from "bailian-cli-core";
-import { emitResult, emitBare, emitRequestId } from "bailian-cli-runtime";
+import { defineCommand, scaleDeployment, type FlagsDef } from "bailian-cli-core";
+import { emitResult, emitBare } from "bailian-cli-runtime";
 
 const SCALE_FLAGS = {
   deployedModel: {
@@ -52,7 +47,6 @@ export default defineCommand({
   async run(ctx) {
     const { settings, flags } = ctx;
     const deployedModel = flags.deployedModel;
-    const format = detectOutputFormat(settings.output);
 
     const body: Record<string, unknown> = {};
     if (flags.capacity !== undefined) body.capacity = flags.capacity;
@@ -60,21 +54,16 @@ export default defineCommand({
     if (flags.outputTpm !== undefined) body.output_tpm = flags.outputTpm;
 
     if (settings.dryRun) {
-      emitResult({ action: "deploy.scale", deployed_model: deployedModel, body }, format);
+      emitResult({ action: "deploy.scale", deployed_model: deployedModel, body }, "json");
       return;
     }
 
     const response = await scaleDeployment(ctx.client, deployedModel, body);
-    const deployment = response.output ?? response.data;
 
     if (settings.quiet) {
       emitBare(deployedModel);
-    } else if (format === "text") {
-      const cap = deployment?.capacity !== undefined ? ` (capacity=${deployment.capacity})` : "";
-      emitBare(`Scaled ${deployedModel}${cap}.`);
-      emitRequestId(response.request_id, settings.quiet);
     } else {
-      emitResult(response, format);
+      emitResult(response, "json");
     }
   },
 });

packages/commands/src/commands/deploy/update.ts

@@ -1,10 +1,5 @@
-import {
-  defineCommand,
-  detectOutputFormat,
-  updateDeployment,
-  type FlagsDef,
-} from "bailian-cli-core";
-import { emitResult, emitBare, emitRequestId } from "bailian-cli-runtime";
+import { defineCommand, updateDeployment, type FlagsDef } from "bailian-cli-core";
+import { emitResult, emitBare } from "bailian-cli-runtime";
 
 const UPDATE_FLAGS = {
   deployedModel: {
@@ -48,31 +43,22 @@ export default defineCommand({
   async run(ctx) {
     const { settings, flags } = ctx;
     const deployedModel = flags.deployedModel;
-    const format = detectOutputFormat(settings.output);
 
     const body: Record<string, unknown> = {};
     if (flags.rpmLimit !== undefined) body.rpm_limit = flags.rpmLimit;
     if (flags.tpmLimit !== undefined) body.tpm_limit = flags.tpmLimit;
 
     if (settings.dryRun) {
-      emitResult({ action: "deploy.update", deployed_model: deployedModel, body }, format);
+      emitResult({ action: "deploy.update", deployed_model: deployedModel, body }, "json");
       return;
     }
 
     const response = await updateDeployment(ctx.client, deployedModel, body);
-    const deployment = response.output ?? response.data;
 
     if (settings.quiet) {
       emitBare(deployedModel);
-    } else if (format === "text") {
-      const parts: string[] = [];
-      if (deployment?.rpm_limit !== undefined) parts.push(`rpm_limit=${deployment.rpm_limit}`);
-      if (deployment?.tpm_limit !== undefined) parts.push(`tpm_limit=${deployment.tpm_limit}`);
-      const summary = parts.length ? ` (${parts.join(", ")})` : "";
-      emitBare(`Updated ${deployedModel}${summary}.`);
-      emitRequestId(response.request_id, settings.quiet);
     } else {
-      emitResult(response, format);
+      emitResult(response, "json");
     }
   },
 });

packages/commands/src/commands/finetune/cancel.ts

@@ -1,5 +1,5 @@
-import { defineCommand, detectOutputFormat, cancelFineTune, type FlagsDef } from "bailian-cli-core";
-import { emitResult, emitBare, emitRequestId } from "bailian-cli-runtime";
+import { defineCommand, cancelFineTune, type FlagsDef } from "bailian-cli-core";
+import { emitResult, emitBare } from "bailian-cli-runtime";
 
 const CANCEL_FLAGS = {
   jobId: {
@@ -23,24 +23,18 @@ export default defineCommand({
   async run(ctx) {
     const { settings, flags } = ctx;
     const jobId = flags.jobId;
-    const format = detectOutputFormat(settings.output);
 
     if (settings.dryRun) {
-      emitResult({ action: "finetune.cancel", job_id: jobId }, format);
+      emitResult({ action: "finetune.cancel", job_id: jobId }, "json");
       return;
     }
 
     const response = await cancelFineTune(ctx.client, jobId);
-    const job = response.output ?? response.data;
 
     if (settings.quiet) {
       emitBare(jobId);
-    } else if (format === "text") {
-      const status = job?.status ? ` (status=${job.status})` : "";
-      emitBare(`Cancelled ${jobId}${status}.`);
-      emitRequestId(response.request_id, settings.quiet);
     } else {
-      emitResult(response, format);
+      emitResult(response, "json");
     }
   },
 });

packages/commands/src/commands/finetune/capability.ts

@@ -1,6 +1,5 @@
 import {
   defineCommand,
-  detectOutputFormat,
   fetchModelList,
   fetchModelCapability,
   listSupportedTrainingTypes,
@@ -43,19 +42,8 @@ async function fetchAllFoundationModels(settings: Settings): Promise<ModelCapabi
   return all as ModelCapability[];
 }
 
-const VARIANT_LABEL: Record<string, string> = {
-  full: "full-parameter",
-  lora: "LoRA",
-};
-
-function describeTrainingType(value: string): string {
-  if (!isTrainingTypeCli(value)) return value;
-  const { method, variant } = trainingTypeMethodVariant(value);
-  return `${VARIANT_LABEL[variant] ?? variant} ${method.toUpperCase()}`;
-}
-
 const CAPABILITY_FLAGS = {
-  model: {
+  baseModel: {
     type: "string",
     valueHint: "<m>",
     description: "List training types supported by this base model.",
@@ -71,31 +59,31 @@ export default defineCommand({
   description:
     "Query fine-tune training capability — by model (which training types it supports) or by training type (which models support it)",
   auth: "none",
-  usageArgs: "--model <m> | --training-type <t>",
+  usageArgs: "--base-model <m> | --training-type <t>",
   flags: CAPABILITY_FLAGS,
   exampleArgs: [
-    "--model qwen3-8b",
+    "--base-model qwen3-8b",
     "--training-type sft-lora",
     "--training-type cpt --output json",
     "--training-type sft --quiet",
   ],
   notes: [
-    "Exactly one of --model / --training-type is required.",
+    "Exactly one of --base-model / --training-type is required.",
     "Training-type values use the `<method>` / `<method>-lora` convention:",
     "sft | sft-lora | dpo | dpo-lora | cpt. (cpt has no -lora variant server-side.)",
     "Queries listFoundationModels, a public API — no console login needed.",
   ],
   validate: (f) => {
-    if (f.model && f.trainingType)
-      return "--model and --training-type are mutually exclusive; pass one.";
-    if (!f.model && !f.trainingType) return "one of --model / --training-type is required.";
+    if (f.baseModel && f.trainingType)
+      return "--base-model and --training-type are mutually exclusive; pass one.";
+    if (!f.baseModel && !f.trainingType)
+      return "one of --base-model / --training-type is required.";
     return undefined;
   },
   async run(ctx) {
     const { settings, flags } = ctx;
-    const model = flags.model || undefined;
+    const model = flags.baseModel || undefined;
     const trainingType = flags.trainingType || undefined;
-    const format = detectOutputFormat(settings.output);
 
     if (settings.dryRun) {
       emitResult(
@@ -104,7 +92,7 @@ export default defineCommand({
           model,
           training_type: trainingType,
         },
-        format,
+        "json",
       );
       return;
     }
@@ -113,7 +101,7 @@ export default defineCommand({
     if (model) {
       const capability = await fetchModelCapability(settings, model);
       if (!capability) {
-        emitBare(`No foundation model found matching "${model}".`);
+        emitResult({ model, error: `No foundation model found matching "${model}".` }, "json");
         return;
       }
       const supported = listSupportedTrainingTypes(capability);
@@ -121,23 +109,15 @@ export default defineCommand({
         for (const value of supported) emitBare(value);
         return;
       }
-      if (format !== "text") {
-        emitResult(
-          {
-            model: capability.model ?? model,
-            supported,
-            supports: capability.supports,
-            trainingTypes: capability.trainingTypes,
-          },
-          format,
-        );
-        return;
-      }
-      emitBare(`${capability.model ?? model}`);
-      emitBare(supported.length ? "Supported training types:" : "No supported training types.");
-      for (const value of supported) {
-        emitBare(`  ${value.padEnd(10)} ${describeTrainingType(value)}`);
-      }
+      emitResult(
+        {
+          model: capability.model ?? model,
+          supported,
+          supports: capability.supports,
+          trainingTypes: capability.trainingTypes,
+        },
+        "json",
+      );
       return;
     }
 
@@ -162,20 +142,15 @@ export default defineCommand({
       for (const entry of matched) emitBare(entry.model);
       return;
     }
-    if (format !== "text") {
-      emitResult(
-        {
-          training_type: trainingType,
-          method,
-          variant,
-          count: matched.length,
-          models: matched,
-        },
-        format,
-      );
-      return;
-    }
-    emitBare(`Models supporting ${trainingType} (${method} / ${variant}): ${matched.length}`);
-    for (const entry of matched) emitBare(`  ${entry.model}`);
+    emitResult(
+      {
+        training_type: trainingType,
+        method,
+        variant,
+        count: matched.length,
+        models: matched,
+      },
+      "json",
+    );
   },
 });

packages/commands/src/commands/finetune/checkpoints.ts

@@ -1,10 +1,5 @@
-import {
-  defineCommand,
-  detectOutputFormat,
-  listCheckpoints,
-  type FlagsDef,
-} from "bailian-cli-core";
-import { emitResult, emitBare, emitRequestId, formatTable } from "bailian-cli-runtime";
+import { defineCommand, listCheckpoints, type FlagsDef } from "bailian-cli-core";
+import { emitResult } from "bailian-cli-runtime";
 
 const CHECKPOINTS_FLAGS = {
   jobId: {
@@ -15,6 +10,8 @@ const CHECKPOINTS_FLAGS = {
   },
 } satisfies FlagsDef;
 
+const EXPIRY_WARN_THRESHOLD_MS = 72 * 60 * 60 * 1000; // 72 hours
+
 export default defineCommand({
   description: "List checkpoints produced by a fine-tune job",
   auth: "apiKey",
@@ -22,16 +19,15 @@ export default defineCommand({
   flags: CHECKPOINTS_FLAGS,
   exampleArgs: ["--job-id ft-xxx", "--job-id ft-xxx --output json"],
   notes: [
-    "Use the returned `checkpoint` value with `finetune export` to publish",
-    "a deployable model.",
+    "`model_name` (shown for SUCCEEDED checkpoints) is the direct input for `deploy create --model-name`.",
+    "Checkpoints expire ~15 days after creation; `expire_time` shows the deadline. Export or deploy before expiry.",
   ],
   async run(ctx) {
     const { settings, flags } = ctx;
     const jobId = flags.jobId;
-    const format = detectOutputFormat(settings.output);
 
     if (settings.dryRun) {
-      emitResult({ action: "finetune.checkpoints", job_id: jobId }, format);
+      emitResult({ action: "finetune.checkpoints", job_id: jobId }, "json");
       return;
     }
 
@@ -44,22 +40,26 @@ export default defineCommand({
       checkpoint: item.checkpoint ?? item.checkpoint_id ?? "",
       step: item.step !== undefined ? String(item.step) : "",
       status: item.status ?? "",
+      model_name: item.model_name ?? "",
+      expire_time: item.expire_time ?? "",
     }));
 
-    if (format === "json") {
-      emitResult({ items, total, request_id: response.request_id }, format);
-      return;
-    }
+    emitResult({ items, total, request_id: response.request_id }, "json");
 
-    // text / quiet
-    if (items.length === 0) {
-      emitBare("No checkpoints found.");
-      return;
+    // Near-expiry warning: check if any non-expired checkpoint is within 72h of expiry.
+    const now = Date.now();
+    const expiringSoon = items.filter((item) => {
+      if (!item.expire_time) return false;
+      const deadline = new Date(item.expire_time).getTime();
+      if (Number.isNaN(deadline)) return false;
+      const remaining = deadline - now;
+      return remaining > 0 && remaining < EXPIRY_WARN_THRESHOLD_MS;
+    });
+    if (expiringSoon.length > 0) {
+      process.stderr.write(
+        `\n[warning] ${expiringSoon.length} checkpoint(s) will expire within 72 hours. ` +
+          "Export or deploy before expiry to avoid losing the model artifact.\n",
+      );
     }
-    const headers = ["CHECKPOINT", "STEP", "STATUS"];
-    const rows = items.map((i) => [i.checkpoint, i.step, i.status]);
-    for (const line of formatTable(headers, rows)) emitBare(line);
-    emitBare(`\nTotal: ${total}`);
-    emitRequestId(response.request_id, settings.quiet);
   },
 });

packages/commands/src/commands/finetune/create.ts

@@ -1,6 +1,5 @@
 import {
   defineCommand,
-  detectOutputFormat,
   createFineTune,
   getDataset,
   uploadDataset,
@@ -27,7 +26,7 @@ import {
 } from "bailian-cli-core";
 import { existsSync, statSync } from "fs";
 import { basename } from "path";
-import { emitResult, emitBare, emitRequestId } from "bailian-cli-runtime";
+import { emitResult, emitBare } from "bailian-cli-runtime";
 
 /**
  * A `--datasets` / `--validations` token is treated as a local file to upload
@@ -208,7 +207,7 @@ async function uploadResolvedLocal(
 }
 
 /** The modality a `finetune <modality> create` subcommand is bound to. */
-type CommandModality = "text" | "audio" | "image";
+type CommandModality = "text" | "audio" | "image" | "video";
 
 /**
  * Flags shared by every `finetune <modality> create` subcommand: what to train
@@ -216,10 +215,10 @@ type CommandModality = "text" | "audio" | "image";
  * output. Every modality's model consumes these.
  */
 const COMMON_FLAGS = {
-  model: {
+  baseModel: {
     type: "string",
     valueHint: "<model>",
-    description: "Base model to fine-tune",
+    description: "Base model to fine-tune (e.g. qwen3-8b; not the output model name)",
     required: true,
   },
   datasets: {
@@ -317,13 +316,41 @@ const IMAGE_FLAGS = {
 } satisfies FlagsDef;
 
 const TEXT_USAGE =
-  "--model <model> --datasets <id|path,...> [--validations <id|path,...>] [--model-name <name>] [--suffix <text>] [--n-epochs <n>] [--batch-size <n>] [--learning-rate <str>] [--max-length <n>] [--training-type <sft|sft-lora|dpo|dpo-lora|cpt>]";
+  "--base-model <model> --datasets <id|path,...> [--validations <id|path,...>] [--model-name <name>] [--suffix <text>] [--n-epochs <n>] [--batch-size <n>] [--learning-rate <str>] [--max-length <n>] [--training-type <sft|sft-lora|dpo|dpo-lora|cpt>]";
 
 const AUDIO_USAGE =
-  "--model <model> --datasets <id|path> [--validations <id|path>] [--model-name <name>] [--suffix <text>]";
+  "--base-model <model> --datasets <id|path> [--validations <id|path>] [--model-name <name>] [--suffix <text>]";
 
 const IMAGE_USAGE =
-  "--model <model> --datasets <id|path> [--validations <id|path>] [--model-name <name>] [--suffix <text>] [--generation-type <t2i|i2i>] [--learning-rate <str>]";
+  "--base-model <model> --datasets <id|path> [--validations <id|path>] [--model-name <name>] [--suffix <text>] [--generation-type <t2i|i2i>] [--learning-rate <str>]";
+
+/**
+ * Video (Wan i2v/kf2v) flags: exposes the three hyper-parameters that the
+ * video API supports and users may want to override. Defaults are model-specific
+ * (resolved by the sft-lora profile: wan2.7 → batch_size 1 / max_pixels 102400,
+ * wan2.5 → 4 / 36864, wan2.2 → 4 / 262144).
+ */
+const VIDEO_FLAGS = {
+  ...COMMON_FLAGS,
+  nEpochs: {
+    type: "number",
+    valueHint: "<n>",
+    description: "Training epochs (default: 50)",
+  },
+  batchSize: {
+    type: "number",
+    valueHint: "<n>",
+    description: "Batch size (default: model-specific, 1 for wan2.7, 4 for wan2.5/2.2)",
+  },
+  learningRate: {
+    type: "string",
+    valueHint: "<str>",
+    description: 'Learning rate as a string to preserve precision (default: "2e-5")',
+  },
+} satisfies FlagsDef;
+
+const VIDEO_USAGE =
+  "--base-model <model> --datasets <id|path> [--validations <id|path>] [--model-name <name>] [--suffix <text>] [--n-epochs <n>] [--batch-size <n>] [--learning-rate <str>]";
 
 const COMMON_NOTES = [
   "Creating a job uploads any local datasets and consumes training quota.",
@@ -383,7 +410,7 @@ async function runCreate<F extends FlagsDef>(
 ): Promise<void> {
   const { identity, settings } = ctx;
   const flags = ctx.flags as Record<string, unknown>;
-  const model = flags.model as string;
+  const model = flags.baseModel as string;
   const datasetsRaw = flags.datasets as string;
 
   // CosyVoice audio fine-tuning accepts exactly one training file
@@ -606,8 +633,6 @@ async function runCreate<F extends FlagsDef>(
   if (modelName) body.model_name = modelName;
   if (suffix) body.finetuned_output_suffix = suffix;
 
-  const format = detectOutputFormat(settings.output);
-
   if (settings.dryRun) {
     const pending = [
       ...training.localPaths.map((path) => ({ field: "datasets", path })),
@@ -617,7 +642,7 @@ async function runCreate<F extends FlagsDef>(
       pending.length > 0
         ? { action: "finetune.create", body, pending_uploads: pending }
         : { action: "finetune.create", body },
-      format,
+      "json",
     );
     return;
   }
@@ -627,16 +652,8 @@ async function runCreate<F extends FlagsDef>(
 
   if (settings.quiet) {
     if (job?.job_id) emitBare(job.job_id);
-  } else if (format === "text") {
-    if (job?.job_id) {
-      emitBare(`Created fine-tune job: ${job.job_id}`);
-      if (job.status) emitBare(`Status: ${job.status}`);
-      emitRequestId(response.request_id, settings.quiet);
-    } else {
-      emitResult(response, format);
-    }
   } else {
-    emitResult(response, format);
+    emitResult(response, "json");
   }
 }
 
@@ -647,14 +664,14 @@ export const finetuneTextCreate = defineCommand({
   usageArgs: TEXT_USAGE,
   flags: TEXT_FLAGS,
   exampleArgs: [
-    "--model qwen3-8b --datasets file-xxx",
-    "--model qwen3-8b --datasets ./train.jsonl",
-    "--model qwen3-8b --datasets ./train.jsonl --validations ./eval.jsonl",
-    "--model qwen3-8b --datasets file-aaa,./extra.jsonl",
-    "--model qwen3-8b --datasets ./train.jsonl --training-type sft",
-    '--model qwen3-8b --datasets file-xxx --learning-rate "1.6e-5" --n-epochs 4',
-    "--model qwen3-8b --datasets file-xxx --output json",
-    "--model qwen3-8b --datasets file-xxx --dry-run",
+    "--base-model qwen3-8b --datasets file-xxx",
+    "--base-model qwen3-8b --datasets ./train.jsonl",
+    "--base-model qwen3-8b --datasets ./train.jsonl --validations ./eval.jsonl",
+    "--base-model qwen3-8b --datasets file-aaa,./extra.jsonl",
+    "--base-model qwen3-8b --datasets ./train.jsonl --training-type sft",
+    '--base-model qwen3-8b --datasets file-xxx --learning-rate "1.6e-5" --n-epochs 4',
+    "--base-model qwen3-8b --datasets file-xxx --output json",
+    "--base-model qwen3-8b --datasets file-xxx --dry-run",
   ],
   notes: TEXT_NOTES,
   run: (ctx) => runCreate("text", ctx),
@@ -667,11 +684,11 @@ export const finetuneAudioCreate = defineCommand({
   usageArgs: AUDIO_USAGE,
   flags: AUDIO_FLAGS,
   exampleArgs: [
-    "--model cosyvoice-v3-flash --datasets ./audio.zip",
-    "--model cosyvoice-v3-flash --datasets file-xxx",
-    "--model cosyvoice-v3-flash --datasets ./audio.zip --model-name my-tts",
-    "--model cosyvoice-v3-flash --datasets file-xxx --output json",
-    "--model cosyvoice-v3-flash --datasets ./audio.zip --dry-run",
+    "--base-model cosyvoice-v3-flash --datasets ./audio.zip",
+    "--base-model cosyvoice-v3-flash --datasets file-xxx",
+    "--base-model cosyvoice-v3-flash --datasets ./audio.zip --model-name my-tts",
+    "--base-model cosyvoice-v3-flash --datasets file-xxx --output json",
+    "--base-model cosyvoice-v3-flash --datasets ./audio.zip --dry-run",
   ],
   notes: AUDIO_NOTES,
   run: (ctx) => runCreate("audio", ctx),
@@ -684,13 +701,38 @@ export const finetuneImageCreate = defineCommand({
   usageArgs: IMAGE_USAGE,
   flags: IMAGE_FLAGS,
   exampleArgs: [
-    "--model wan2.7-image-pro --datasets ./images.zip",
-    "--model wan2.7-image-pro --datasets file-xxx",
-    "--model wan2.7-image-pro --datasets file-xxx --generation-type i2i",
-    "--model wan2.7-image-pro --datasets ./images.zip --model-name my-wan",
-    "--model wan2.7-image-pro --datasets file-xxx --output json",
-    "--model wan2.7-image-pro --datasets ./images.zip --dry-run",
+    "--base-model wan2.7-image-pro --datasets ./images.zip",
+    "--base-model wan2.7-image-pro --datasets file-xxx",
+    "--base-model wan2.7-image-pro --datasets file-xxx --generation-type i2i",
+    "--base-model wan2.7-image-pro --datasets ./images.zip --model-name my-wan",
+    "--base-model wan2.7-image-pro --datasets file-xxx --output json",
+    "--base-model wan2.7-image-pro --datasets ./images.zip --dry-run",
   ],
   notes: IMAGE_NOTES,
   run: (ctx) => runCreate("image", ctx),
 });
+
+const VIDEO_NOTES = [
+  ...COMMON_NOTES,
+  "Video generation training (Wan i2v/kf2v) runs efficient_sft with model-",
+  "specific defaults: wan2.7 (batch_size=1, max_pixels=102400), wan2.5/2.2",
+  "(batch_size=4, max_pixels per model). Override with --batch-size/--n-epochs.",
+  "Datasets are .zip archives with data.jsonl + frame images + videos.",
+  "Recommended: ≥10 training samples, 20-100 for stable results.",
+];
+
+/** `bl finetune video create` — fine-tune a video generation model. Datasets are `.zip`. */
+export const finetuneVideoCreate = defineCommand({
+  description: "Create a video generation model fine-tune job (Wan i2v/kf2v, efficient_sft)",
+  auth: "apiKey",
+  usageArgs: VIDEO_USAGE,
+  flags: VIDEO_FLAGS,
+  exampleArgs: [
+    "--base-model wan2.7-i2v --datasets file-xxx",
+    "--base-model wan2.7-i2v --datasets ./i2v-data.zip",
+    "--base-model wan2.2-kf2v-flash --datasets file-xxx --n-epochs 100",
+    "--base-model wan2.7-i2v --datasets file-xxx --dry-run",
+  ],
+  notes: VIDEO_NOTES,
+  run: (ctx) => runCreate("video", ctx),
+});

packages/commands/src/commands/finetune/delete.ts

@@ -1,5 +1,5 @@
-import { defineCommand, detectOutputFormat, deleteFineTune, type FlagsDef } from "bailian-cli-core";
-import { emitResult, emitBare, emitRequestId } from "bailian-cli-runtime";
+import { defineCommand, deleteFineTune, type FlagsDef } from "bailian-cli-core";
+import { emitResult, emitBare } from "bailian-cli-runtime";
 
 const DELETE_FLAGS = {
   jobId: {
@@ -23,10 +23,9 @@ export default defineCommand({
   async run(ctx) {
     const { settings, flags } = ctx;
     const jobId = flags.jobId;
-    const format = detectOutputFormat(settings.output);
 
     if (settings.dryRun) {
-      emitResult({ action: "finetune.delete", job_id: jobId }, format);
+      emitResult({ action: "finetune.delete", job_id: jobId }, "json");
       return;
     }
 
@@ -34,11 +33,8 @@ export default defineCommand({
 
     if (settings.quiet) {
       emitBare(jobId);
-    } else if (format === "text") {
-      emitBare(`Deleted ${jobId}.`);
-      emitRequestId(response.request_id, settings.quiet);
     } else {
-      emitResult(response, format);
+      emitResult(response, "json");
     }
   },
 });

packages/commands/src/commands/finetune/export.ts

@@ -1,10 +1,5 @@
-import {
-  defineCommand,
-  detectOutputFormat,
-  exportCheckpoint,
-  type FlagsDef,
-} from "bailian-cli-core";
-import { emitResult, emitBare, emitRequestId } from "bailian-cli-runtime";
+import { defineCommand, exportCheckpoint, type FlagsDef } from "bailian-cli-core";
+import { emitResult, emitBare } from "bailian-cli-runtime";
 
 const EXPORT_FLAGS = {
   jobId: {
@@ -39,11 +34,10 @@ export default defineCommand({
     "explicit export is the canonical path for non-best checkpoints.",
   ],
   async run(ctx) {
-    const { identity, settings, flags } = ctx;
+    const { settings, flags } = ctx;
     const jobId = flags.jobId;
     const checkpoint = flags.checkpoint;
     const modelName = flags.modelName;
-    const format = detectOutputFormat(settings.output);
 
     if (settings.dryRun) {
       emitResult(
@@ -53,7 +47,7 @@ export default defineCommand({
           checkpoint,
           model_name: modelName,
         },
-        format,
+        "json",
       );
       return;
     }
@@ -64,14 +58,8 @@ export default defineCommand({
 
     if (settings.quiet) {
       emitBare(exported);
-    } else if (format === "text") {
-      emitBare(`Exported ${jobId} / ${checkpoint} → model_name=${exported}`);
-      emitBare(
-        `Next: ${identity.binName} deploy text create --model ${exported} --name <display-name>`,
-      );
-      emitRequestId(response.request_id, settings.quiet);
     } else {
-      emitResult(response, format);
+      emitResult(response, "json");
     }
   },
 });

packages/commands/src/commands/finetune/fee.ts

@@ -0,0 +1,105 @@
+/**
+ * Best-effort actual training fee calculation using the model catalog's
+ * "ft" (fine-tune) price entry. Pure API-key domain — no console auth needed.
+ *
+ * The model catalog (`listFoundationModels` via public gateway) returns a
+ * `prices[]` array **only when `queryPrice: true` is passed** (the same flag
+ * `fetchModelDetail` uses). Combined with the job's `output.usage` (actual
+ * consumed tokens, present on SUCCEEDED / CANCELED), this gives the exact
+ * training cost without any console-domain login.
+ */
+import {
+  callConsoleGateway,
+  effectiveConsoleGatewayConfig,
+  unwrapResponse,
+  MODEL_LIST_API,
+  type Settings,
+  type ModelPriceInfo,
+} from "bailian-cli-core";
+
+export interface ActualFee {
+  cost: number;
+  unitPrice: number;
+  priceUnit: string;
+}
+
+/**
+ * Fetch the model's training price from the public catalog gateway.
+ * Uses the same anonymous gateway path as `fetchModelCapability` (no console
+ * token required), but adds `queryPrice: true` to include the prices array.
+ */
+async function fetchTrainingPrice(
+  settings: Settings,
+  model: string,
+): Promise<ModelPriceInfo | null> {
+  const eff = effectiveConsoleGatewayConfig(settings);
+  const result = await callConsoleGateway(
+    { region: eff.consoleRegion, site: eff.consoleSite, switchAgent: eff.consoleSwitchAgent },
+    settings.timeout,
+    {
+      api: MODEL_LIST_API,
+      data: {
+        input: {
+          pageNo: 1,
+          pageSize: 10,
+          group: true,
+          model,
+          queryPrice: true,
+          querySampleCode: false,
+          queryGroupByModel: true,
+          queryQuota: false,
+          queryQpmInfo: false,
+          queryApplyStatus: false,
+          queryPermissions: false,
+          queryActivationStatus: false,
+        },
+      },
+    },
+  );
+  const responseData = unwrapResponse(result as Record<string, unknown>);
+  const list = (responseData.list as Record<string, unknown>[]) ?? [];
+  // The response is grouped; find the exact model in items.
+  for (const group of list) {
+    const items = (group.items as Record<string, unknown>[]) ?? [];
+    for (const item of items) {
+      if (item.model === model) {
+        const prices = (item.prices as ModelPriceInfo[]) ?? [];
+        return prices.find((entry) => entry.type === "ft") ?? null;
+      }
+    }
+    // Flat response fallback (no items nesting).
+    if (group.model === model) {
+      const prices = (group.prices as ModelPriceInfo[]) ?? [];
+      return prices.find((entry) => entry.type === "ft") ?? null;
+    }
+  }
+  return null;
+}
+
+/**
+ * Compute the actual training fee from the model catalog's "ft" price entry.
+ * Returns null when the price is unavailable (network error, model not in
+ * catalog, or no "ft" entry). Never throws.
+ *
+ * Only uses the public model catalog (model metadata) — does NOT call
+ * console-domain pricing APIs (modelCenter.getModelPrice). Models whose
+ * catalog entry lacks a "ft" price (e.g. CosyVoice) will simply omit the
+ * training_cost field until the platform adds it to the catalog.
+ */
+export async function computeActualFee(
+  settings: Settings,
+  model: string,
+  usageTokens: number,
+): Promise<ActualFee | null> {
+  try {
+    const ftEntry = await fetchTrainingPrice(settings, model);
+    const unitPrice = Number(ftEntry?.price);
+    if (!Number.isFinite(unitPrice) || unitPrice <= 0) return null;
+    const priceUnit = ftEntry?.priceUnit ?? "每百万tokens";
+    // Catalog price is yuan per million tokens.
+    const cost = (usageTokens / 1_000_000) * unitPrice;
+    return { cost: Number(cost.toFixed(4)), unitPrice, priceUnit };
+  } catch {
+    return null;
+  }
+}

packages/commands/src/commands/finetune/get.ts

@@ -1,5 +1,6 @@
-import { defineCommand, detectOutputFormat, getFineTune, type FlagsDef } from "bailian-cli-core";
-import { emitResult, emitBare, emitRequestId } from "bailian-cli-runtime";
+import { defineCommand, getFineTune, type FlagsDef } from "bailian-cli-core";
+import { emitResult } from "bailian-cli-runtime";
+import { computeActualFee } from "./fee.ts";
 
 const GET_FLAGS = {
   jobId: {
@@ -17,12 +18,11 @@ export default defineCommand({
   flags: GET_FLAGS,
   exampleArgs: ["--job-id ft-xxx", "--job-id ft-xxx --output json"],
   async run(ctx) {
-    const { identity, settings, flags } = ctx;
+    const { settings, flags } = ctx;
     const jobId = flags.jobId;
-    const format = detectOutputFormat(settings.output);
 
     if (settings.dryRun) {
-      emitResult({ action: "finetune.get", job_id: jobId }, format);
+      emitResult({ action: "finetune.get", job_id: jobId }, "json");
       return;
     }
 
@@ -30,18 +30,24 @@ export default defineCommand({
     const job = response.output ?? response.data;
 
     if (!job) {
-      emitBare(`No data returned for ${jobId}`);
+      emitResult({ job_id: jobId, error: "No data returned" }, "json");
       return;
     }
 
-    const hp = job.hyper_parameters;
+    const hyperParameters = job.hyper_parameters;
     const hyperParts: string[] = [];
-    if (hp?.n_epochs !== undefined) hyperParts.push(`n_epochs=${hp.n_epochs}`);
-    if (hp?.batch_size !== undefined) hyperParts.push(`batch_size=${hp.batch_size}`);
-    if (hp?.learning_rate !== undefined) hyperParts.push(`learning_rate=${hp.learning_rate}`);
-    if (hp?.max_length !== undefined) hyperParts.push(`max_length=${hp.max_length}`);
+    if (hyperParameters?.n_epochs !== undefined)
+      hyperParts.push(`n_epochs=${hyperParameters.n_epochs}`);
+    if (hyperParameters?.batch_size !== undefined)
+      hyperParts.push(`batch_size=${hyperParameters.batch_size}`);
+    if (hyperParameters?.learning_rate !== undefined)
+      hyperParts.push(`learning_rate=${hyperParameters.learning_rate}`);
+    if (hyperParameters?.max_length !== undefined)
+      hyperParts.push(`max_length=${hyperParameters.max_length}`);
 
-    const item = {
+    const usageTokens = typeof job.usage === "number" ? job.usage : undefined;
+
+    const item: Record<string, unknown> = {
       job_id: job.job_id ?? jobId,
       base_model: job.model ?? "",
       status: job.status ?? "",
@@ -53,29 +59,20 @@ export default defineCommand({
       model_name: job.model_name ?? "",
       created_at: job.create_time ?? job.gmt_create ?? "",
       updated_at: job.end_time ?? job.gmt_modified ?? "",
+      usage_tokens: usageTokens ?? "",
+      charge_type: typeof job.charge_type === "string" ? job.charge_type : "",
     };
 
-    if (format === "json") {
-      emitResult({ ...item, request_id: response.request_id }, format);
-      return;
+    // Actual fee: only when the platform reports a concrete token count
+    // (SUCCEEDED / CANCELED). Best-effort — silently omitted on lookup failure.
+    if (usageTokens !== undefined && usageTokens > 0 && job.model) {
+      const fee = await computeActualFee(settings, job.model, usageTokens);
+      if (fee) {
+        item.training_cost = fee.cost;
+        item.cost_basis = `${fee.unitPrice} 元/${fee.priceUnit}`;
+      }
     }
 
-    // text / quiet
-    emitBare(`job_id:           ${item.job_id}`);
-    if (item.base_model) emitBare(`base_model:       ${item.base_model}`);
-    if (item.status) emitBare(`status:           ${item.status}`);
-    if (item.training_type) emitBare(`training_type:    ${item.training_type}`);
-    if (item.training_files.length) emitBare(`training_files:   ${item.training_files.join(", ")}`);
-    if (item.validation_files.length)
-      emitBare(`validation_files: ${item.validation_files.join(", ")}`);
-    if (item.hyper_params) emitBare(`hyper_params:     ${item.hyper_params}`);
-    if (item.output_model)
-      emitBare(
-        `output_model:     ${item.output_model}  (→ ${identity.binName} deploy text create --model)`,
-      );
-    if (item.model_name) emitBare(`model_name:       ${item.model_name}`);
-    if (item.created_at) emitBare(`created_at:       ${item.created_at}`);
-    if (item.updated_at) emitBare(`updated_at:       ${item.updated_at}`);
-    emitRequestId(response.request_id, settings.quiet);
+    emitResult({ ...item, request_id: response.request_id }, "json");
   },
 });

packages/commands/src/commands/finetune/list.ts

@@ -1,5 +1,5 @@
-import { defineCommand, detectOutputFormat, listFineTunes, type FlagsDef } from "bailian-cli-core";
-import { emitResult, emitBare, emitRequestId, formatTable } from "bailian-cli-runtime";
+import { defineCommand, listFineTunes, type FlagsDef } from "bailian-cli-core";
+import { emitResult } from "bailian-cli-runtime";
 
 const LIST_FLAGS = {
   page: { type: "number", valueHint: "<n>", description: "Page number (default: 1)" },
@@ -13,71 +13,48 @@ const LIST_FLAGS = {
     valueHint: "<s>",
     description: "Filter by status (PENDING / RUNNING / SUCCEEDED / FAILED / CANCELED)",
   },
+  baseModel: {
+    type: "string",
+    valueHint: "<model>",
+    description: "Filter by base model ID (server-side)",
+  },
 } satisfies FlagsDef;
 
 export default defineCommand({
   description: "List fine-tune jobs",
   auth: "apiKey",
-  usageArgs: "[--page <n>] [--page-size <n>] [--status <s>]",
+  usageArgs: "[--page <n>] [--page-size <n>] [--status <s>] [--base-model <model>]",
   flags: LIST_FLAGS,
-  exampleArgs: ["", "--status RUNNING", "--page-size 20 --output json"],
+  exampleArgs: ["", "--status RUNNING", "--base-model qwen3-8b", "--page-size 20"],
   async run(ctx) {
-    const { identity, settings, flags } = ctx;
-    const format = detectOutputFormat(settings.output);
+    const { settings, flags } = ctx;
     const pageNo = flags.page;
     const pageSize = flags.pageSize;
     const status = flags.status || undefined;
+    const model = flags.baseModel || undefined;
 
     if (settings.dryRun) {
-      emitResult({ action: "finetune.list", page: pageNo, page_size: pageSize, status }, format);
+      emitResult(
+        { action: "finetune.list", page: pageNo, page_size: pageSize, status, model },
+        "json",
+      );
       return;
     }
 
-    const response = await listFineTunes(ctx.client, { pageNo, pageSize, status });
+    const response = await listFineTunes(ctx.client, { pageNo, pageSize, status, model });
     const payload = response.output ?? response.data;
     const jobs = payload?.jobs ?? [];
     const total = payload?.total;
 
-    const items = jobs.map((item) => ({
-      job_id: item.job_id ?? "",
-      base_model: item.model ?? "",
-      status: item.status ?? "",
-      training_type: item.training_type ?? "",
-      output_model: item.finetuned_output ?? "",
-      created_at: item.create_time ?? item.gmt_create ?? "",
+    const items = jobs.map((job) => ({
+      job_id: job.job_id ?? "",
+      base_model: job.model ?? "",
+      status: job.status ?? "",
+      training_type: job.training_type ?? "",
+      output_model: job.finetuned_output ?? "",
+      created_at: job.create_time ?? job.gmt_create ?? "",
     }));
 
-    if (format === "json") {
-      emitResult({ items, total, request_id: response.request_id }, format);
-      return;
-    }
-
-    // text / quiet
-    if (items.length === 0) {
-      emitBare("No fine-tune jobs found.");
-      return;
-    }
-    const headers = [
-      "JOB_ID",
-      "BASE_MODEL",
-      "STATUS",
-      "TRAINING_TYPE",
-      "OUTPUT_MODEL",
-      "CREATED_AT",
-    ];
-    const rows = items.map((i) => [
-      i.job_id,
-      i.base_model,
-      i.status,
-      i.training_type,
-      i.output_model,
-      i.created_at,
-    ]);
-    for (const line of formatTable(headers, rows)) emitBare(line);
-    if (total !== undefined) emitBare(`\nTotal: ${total}`);
-    emitBare(
-      `Tip: OUTPUT_MODEL is the input for \`${identity.binName} deploy text create --model\``,
-    );
-    emitRequestId(response.request_id, settings.quiet);
+    emitResult({ items, total, request_id: response.request_id }, "json");
   },
 });

packages/commands/src/commands/finetune/logs.ts

@@ -1,25 +1,24 @@
 import {
   defineCommand,
-  detectOutputFormat,
   getFineTuneLogs,
   type Client,
   type FineTuneLogEntry,
   type FlagsDef,
 } from "bailian-cli-core";
-import { emitResult, emitBare, emitRequestId } from "bailian-cli-runtime";
+import { emitResult } from "bailian-cli-runtime";
 
 /**
- * Render a single log entry as a single line (mirrors the flatten logic used
- * for non-search text output: prefer common fields, fall back to JSON).
+ * Render a single log entry as a single line (used for search matching:
+ * prefer common fields, fall back to JSON).
  */
 function renderEntry(entry: FineTuneLogEntry | string): string {
   if (typeof entry === "string") return entry;
   const record = entry as Record<string, unknown>;
-  const ts = (record.timestamp ?? record.time ?? record.create_time ?? "") as string;
+  const timestamp = (record.timestamp ?? record.time ?? record.create_time ?? "") as string;
   const level = (record.level ?? "") as string;
-  const msg = (record.message ?? record.msg ?? record.log ?? "") as string;
-  if (msg || ts || level) {
-    return [ts, level, msg].filter(Boolean).join("\t");
+  const message = (record.message ?? record.msg ?? record.log ?? "") as string;
+  if (message || timestamp || level) {
+    return [timestamp, level, message].filter(Boolean).join("\t");
   }
   return JSON.stringify(entry);
 }
@@ -48,16 +47,16 @@ async function fetchAllLogs(
   let total = 0;
   // Hard cap to avoid an unbounded loop if the server misreports `total`.
   const maxPages = 200;
-  for (let i = 0; i < maxPages; i++) {
+  for (let page = 0; page < maxPages; page++) {
     const response = await getFineTuneLogs(client, jobId, { pageNo, pageSize });
     const payload = response.output ?? response.data;
-    const page = payload?.logs ?? [];
+    const logs = payload?.logs ?? [];
     total = payload?.total ?? total;
-    if (page.length === 0) break;
-    entries.push(...page);
+    if (logs.length === 0) break;
+    entries.push(...logs);
     // Stop once we've collected everything the server claims exists.
     if (total && entries.length >= total) break;
-    if (page.length < pageSize) break;
+    if (logs.length < pageSize) break;
     pageNo++;
   }
   return { entries, total };
@@ -110,7 +109,6 @@ export default defineCommand({
     const pageSize = flags.pageSize;
     const search = flags.search || undefined;
     const tail = flags.tail;
-    const format = detectOutputFormat(settings.output);
 
     if (settings.dryRun) {
       emitResult(
@@ -122,7 +120,7 @@ export default defineCommand({
           search,
           tail,
         },
-        format,
+        "json",
       );
       return;
     }
@@ -147,18 +145,6 @@ export default defineCommand({
       const result =
         tailApplied !== undefined ? scanned.slice(scanned.length - tailApplied) : scanned;
 
-      if (settings.quiet || format === "text") {
-        if (result.length === 0) {
-          emitBare(search ? `No logs matched "${search}".` : "No logs returned.");
-          return;
-        }
-        for (const entry of result) emitBare(renderEntry(entry));
-        const parts: string[] = [`${result.length} shown`];
-        if (matched !== undefined) parts.push(`matched ${matched}`);
-        parts.push(`of ${entries.length}` + (total ? ` (total ${total})` : ""));
-        emitBare(`\n${parts.join(", ")}`);
-        return;
-      }
       emitResult(
         {
           ...(matched !== undefined ? { matched } : {}),
@@ -168,28 +154,13 @@ export default defineCommand({
           ...(tailApplied !== undefined ? { tail: tailApplied } : {}),
           logs: result,
         },
-        format,
+        "json",
       );
       return;
     }
 
     // Default: single page, verbatim response.
     const response = await getFineTuneLogs(ctx.client, jobId, { pageNo, pageSize });
-    const payload = response.output ?? response.data;
-    const logs = payload?.logs ?? [];
-
-    if (settings.quiet || format === "text") {
-      if (logs.length === 0) {
-        emitBare("No logs returned.");
-        return;
-      }
-      for (const entry of logs) {
-        emitBare(renderEntry(entry));
-      }
-      if (payload?.total !== undefined) emitBare(`\nTotal: ${payload.total}`);
-      emitRequestId(response.request_id, settings.quiet);
-    } else {
-      emitResult(response, format);
-    }
+    emitResult(response, "json");
   },
 });

packages/commands/src/commands/finetune/price.ts

@@ -0,0 +1,139 @@
+import {
+  defineCommand,
+  fetchTrainingModelPrice,
+  estimateSftDpoTokens,
+  estimateCptTokens,
+  BailianError,
+  ExitCode,
+  type FlagsDef,
+} from "bailian-cli-core";
+import { emitResult } from "bailian-cli-runtime";
+
+const PRICE_FLAGS = {
+  baseModel: {
+    type: "string",
+    valueHint: "<model>",
+    description: "Base model to fine-tune (e.g. qwen3-8b; not the output model name)",
+    required: true,
+  },
+  datasets: {
+    type: "string",
+    valueHint: "<ids>",
+    description: "Training dataset file IDs, comma-separated (required)",
+    required: true,
+  },
+  trainingType: {
+    type: "string",
+    valueHint: "<type>",
+    description: "Training type: sft | dpo | cpt (default: sft)",
+  },
+  nEpochs: {
+    type: "number",
+    valueHint: "<n>",
+    description: "Number of training epochs (default: 3)",
+  },
+} satisfies FlagsDef;
+
+const SUPPORTED_TRAINING_TYPES = ["sft", "dpo", "cpt"];
+
+// Fixed hyper-parameters used for estimation. Only n_epochs materially affects
+// the estimate; the rest are held at representative defaults (not exposed as
+// flags to keep the command surface minimal).
+const ESTIMATE_BATCH_SIZE = 16;
+const ESTIMATE_MAX_LENGTH = 8192;
+const DEFAULT_N_EPOCHS = 3;
+
+export default defineCommand({
+  description: "Estimate the training cost for a fine-tune job (token billing)",
+  auth: "console",
+  usageArgs: "--base-model <model> --datasets <ids> [--training-type <type>] [--n-epochs <n>]",
+  flags: PRICE_FLAGS,
+  exampleArgs: [
+    "--base-model qwen3-8b --datasets file-ft-xxx",
+    "--base-model qwen3-8b --datasets file-ft-xxx,file-ft-yyy --n-epochs 2",
+    "--base-model qwen3-8b --datasets file-ft-xxx --training-type cpt",
+  ],
+  notes: [
+    "Estimate only — the server computes token usage from the datasets; final cost is subject to the bill.",
+    "Covers token billing for sft / dpo / cpt. Training-unit (MTU) billing is not supported by this command.",
+    "Hyper-parameters other than --n-epochs are fixed at representative defaults for estimation.",
+  ],
+  async run(ctx) {
+    const { settings, flags } = ctx;
+    const model = flags.baseModel;
+    const datasetIds = flags.datasets
+      .split(",")
+      .map((datasetId) => datasetId.trim())
+      .filter(Boolean);
+    const trainingType = (flags.trainingType ?? "sft").toLowerCase();
+    const nEpochs = flags.nEpochs ?? DEFAULT_N_EPOCHS;
+
+    if (!SUPPORTED_TRAINING_TYPES.includes(trainingType)) {
+      throw new BailianError(
+        `Unsupported training type "${trainingType}". Supported: ${SUPPORTED_TRAINING_TYPES.join(", ")}.`,
+        ExitCode.USAGE,
+      );
+    }
+    if (datasetIds.length === 0) {
+      throw new BailianError("--datasets must contain at least one file ID.", ExitCode.USAGE);
+    }
+
+    if (settings.dryRun) {
+      emitResult(
+        { action: "finetune.price", model, datasets: datasetIds, trainingType, nEpochs },
+        "json",
+      );
+      return;
+    }
+
+    // Unit price (yuan per 千Token).
+    const priceInfo = await fetchTrainingModelPrice(ctx.client, model);
+    const unitPrice = Number(priceInfo.price);
+    if (!Number.isFinite(unitPrice)) {
+      throw new BailianError(
+        `No training price found for model "${model}".`,
+        ExitCode.GENERAL,
+        undefined,
+        { rawResponse: JSON.stringify(priceInfo) },
+      );
+    }
+
+    // Per-epoch token estimate (min/max range).
+    const estimate =
+      trainingType === "cpt"
+        ? await estimateCptTokens(ctx.client, model, datasetIds.join(","), nEpochs)
+        : await estimateSftDpoTokens(ctx.client, datasetIds, {
+            nEpochs,
+            batchSize: ESTIMATE_BATCH_SIZE,
+            maxLength: ESTIMATE_MAX_LENGTH,
+          });
+
+    const minPerEpoch = estimate.estimatedDatasetConsumedTokensMinPerEpoch ?? 0;
+    const maxPerEpoch = estimate.estimatedDatasetConsumedTokensMaxPerEpoch ?? 0;
+    const mixedMinPerEpoch = estimate.estimatedMixedConsumedTokensMinPerEpoch ?? 0;
+    const mixedMaxPerEpoch = estimate.estimatedMixedConsumedTokensMaxPerEpoch ?? 0;
+
+    const minTokens = (minPerEpoch + mixedMinPerEpoch) * nEpochs;
+    const maxTokens = (maxPerEpoch + mixedMaxPerEpoch) * nEpochs;
+    // price is yuan per 1000 tokens.
+    const minFee = (minTokens / 1000) * unitPrice;
+    const maxFee = (maxTokens / 1000) * unitPrice;
+
+    emitResult(
+      {
+        model,
+        training_type: trainingType,
+        n_epochs: nEpochs,
+        unit_price: unitPrice,
+        price_unit: priceInfo.priceUnit ?? "千Token",
+        estimated_tokens: { min: minTokens, max: maxTokens },
+        estimated_fee_yuan: {
+          min: Number(minFee.toFixed(4)),
+          max: Number(maxFee.toFixed(4)),
+        },
+        disclaimer: "Server-side estimate; final cost is subject to the bill.",
+      },
+      "json",
+    );
+  },
+});

packages/commands/src/commands/finetune/watch.ts

@@ -1,12 +1,12 @@
 import {
   defineCommand,
-  detectOutputFormat,
   getFineTune,
   BailianError,
   ExitCode,
   type FlagsDef,
 } from "bailian-cli-core";
-import { emitResult, emitBare, emitRequestId } from "bailian-cli-runtime";
+import { emitResult, emitBare } from "bailian-cli-runtime";
+import { computeActualFee } from "./fee.ts";
 
 const DEFAULT_INTERVAL_SEC = 10;
 const MIN_INTERVAL_SEC = 1;
@@ -103,7 +103,6 @@ export default defineCommand({
     const follow = flags.follow;
     const intervalSec = Math.max(MIN_INTERVAL_SEC, flags.interval ?? DEFAULT_INTERVAL_SEC);
     const pollTimeoutSec = flags.pollTimeout;
-    const format = detectOutputFormat(settings.output);
 
     if (settings.dryRun) {
       emitResult(
@@ -114,7 +113,7 @@ export default defineCommand({
           interval: intervalSec,
           timeout: pollTimeoutSec,
         },
-        format,
+        "json",
       );
       return;
     }
@@ -132,16 +131,24 @@ export default defineCommand({
       if (settings.quiet) {
         // Just the status word — ideal for `status=$(... finetune watch ... --quiet)`.
         emitBare(status || "UNKNOWN");
-      } else if (format === "text") {
-        emitBare(`${nowStamp()}  ${jobId}  ${status || "UNKNOWN"}`);
-        if (status === "SUCCEEDED") emitBare(`✓ ${jobId}  ${status}`);
-        emitRequestId(response.request_id, settings.quiet);
       } else {
-        // json: a compact, purpose-built status probe.
-        emitResult(
-          { job_id: jobId, status: status || "UNKNOWN", terminal, request_id: response.request_id },
-          format,
-        );
+        const output: Record<string, unknown> = {
+          job_id: jobId,
+          status: status || "UNKNOWN",
+          terminal,
+          request_id: response.request_id,
+        };
+        // Enrich terminal output with actual fee when usage is reported.
+        const usageTokens = typeof job?.usage === "number" ? job.usage : undefined;
+        if (terminal && usageTokens && usageTokens > 0 && job?.model) {
+          output.usage_tokens = usageTokens;
+          const fee = await computeActualFee(settings, job.model as string, usageTokens);
+          if (fee) {
+            output.training_cost = fee.cost;
+            output.cost_basis = `${fee.unitPrice} 元/${fee.priceUnit}`;
+          }
+        }
+        emitResult(output, "json");
       }
 
       if (terminal && status !== "SUCCEEDED") {
@@ -168,18 +175,28 @@ export default defineCommand({
         const job = response.output ?? response.data;
         const status = String(job?.status ?? "").toUpperCase();
 
-        if (format === "text" && !settings.quiet && status !== lastStatus) {
-          emitBare(`${nowStamp()}  ${jobId}  ${status || "UNKNOWN"}`);
+        if (!settings.quiet && status !== lastStatus) {
+          process.stderr.write(`${nowStamp()}  ${jobId}  ${status || "UNKNOWN"}\n`);
           lastStatus = status;
         }
 
         if (TERMINAL_STATUSES.has(status)) {
           const elapsed = Date.now() - startedAt;
-          if (format !== "text" || settings.quiet) {
-            emitResult(response, format);
-          } else if (status === "SUCCEEDED") {
-            emitBare(`\n✓ ${jobId}  ${status}  (elapsed ${formatElapsed(elapsed)})`);
-            emitRequestId(response.request_id, settings.quiet);
+          if (settings.quiet) {
+            emitBare(status || "UNKNOWN");
+          } else {
+            // Enrich the raw response with actual fee when usage is available.
+            const usageTokens = typeof job?.usage === "number" ? job.usage : undefined;
+            const enriched: Record<string, unknown> = { ...response };
+            if (usageTokens && usageTokens > 0 && job?.model) {
+              const fee = await computeActualFee(settings, job.model as string, usageTokens);
+              if (fee) {
+                enriched.training_cost = fee.cost;
+                enriched.usage_tokens = usageTokens;
+                enriched.cost_basis = `${fee.unitPrice} 元/${fee.priceUnit}`;
+              }
+            }
+            emitResult(enriched, "json");
           }
           if (status !== "SUCCEEDED") {
             throw new BailianError(
@@ -205,7 +222,7 @@ export default defineCommand({
       // Any other error (including the BailianError thrown above) propagates to
       // the central handler.
       if (controller.signal.aborted) {
-        emitBare("\nInterrupted.");
+        process.stderr.write("\nInterrupted.\n");
         return;
       }
       throw error;

packages/commands/src/commands/video/generate.ts

@@ -1,6 +1,7 @@
 import {
   defineCommand,
   videoGeneratePath,
+  image2videoPath,
   taskPath,
   detectOutputFormat,
   type DashScopeVideoRequest,
@@ -43,6 +44,11 @@ export default defineCommand({
       valueHint: "<url>",
       description: "Input image URL for image-to-video generation",
     },
+    lastFrame: {
+      type: "string",
+      valueHint: "<url>",
+      description: "Last frame image URL (with --image, enables kf2v first+last frame mode)",
+    },
     negativePrompt: {
       type: "string",
       valueHint: "<text>",
@@ -110,12 +116,20 @@ export default defineCommand({
     const format = detectOutputFormat(settings.output);
 
     const imageUrl = flags.image;
+    const lastFrameUrl = flags.lastFrame as string | undefined;
 
     // Auto-upload local image file for i2v
     let resolvedImageUrl: string | undefined;
     if (imageUrl) {
       resolvedImageUrl = await ctx.client.resolveImageInput(imageUrl, model);
     }
+    let resolvedLastFrameUrl: string | undefined;
+    if (lastFrameUrl) {
+      resolvedLastFrameUrl = await ctx.client.resolveImageInput(lastFrameUrl, model);
+    }
+
+    // kf2v mode: both --image and --last-frame provided.
+    const isKf2v = Boolean(resolvedImageUrl && resolvedLastFrameUrl);
 
     const watermark = resolveWatermark(flags.watermark);
     const promptExtend = resolveBooleanFlag(flags.promptExtend, undefined, "prompt-extend");
@@ -125,10 +139,16 @@ export default defineCommand({
       input: {
         prompt: prompt,
         negative_prompt: flags.negativePrompt || undefined,
-        // i2v models (happyhorse-1.1-i2v) require input.media with type 'first_frame'
-        ...(resolvedImageUrl
-          ? { media: [{ type: "first_frame" as const, url: resolvedImageUrl }] }
-          : {}),
+        // kf2v: first+last frame flat fields via image2video endpoint.
+        // wan2.1~2.6 i2v: flat img_url via video-generation endpoint.
+        // wan2.7+ / happyhorse i2v: media[] via video-generation endpoint.
+        ...(isKf2v
+          ? { first_frame_url: resolvedImageUrl, last_frame_url: resolvedLastFrameUrl }
+          : resolvedImageUrl
+            ? /wan[x]?2\.[1-6]/i.test(model)
+              ? { img_url: resolvedImageUrl }
+              : { media: [{ type: "first_frame" as const, url: resolvedImageUrl }] }
+            : {}),
       },
       parameters: {
         resolution: flags.resolution || undefined,
@@ -141,15 +161,28 @@ export default defineCommand({
     };
 
     if (settings.dryRun) {
-      const previewBody = resolvedImageUrl
-        ? {
-            ...body,
-            input: {
-              ...body.input,
-              media: [{ type: "first_frame" as const, url: redactDataUri(resolvedImageUrl) }],
-            },
-          }
-        : body;
+      let previewBody = body;
+      if (isKf2v) {
+        previewBody = {
+          ...body,
+          input: {
+            ...body.input,
+            first_frame_url: redactDataUri(resolvedImageUrl ?? ""),
+            last_frame_url: redactDataUri(resolvedLastFrameUrl ?? ""),
+          },
+        };
+      } else if (resolvedImageUrl) {
+        const redactedUrl = redactDataUri(resolvedImageUrl);
+        previewBody = {
+          ...body,
+          input: {
+            ...body.input,
+            ...(/wan[x]?2\.[1-6]/i.test(model)
+              ? { img_url: redactedUrl }
+              : { media: [{ type: "first_frame" as const, url: redactedUrl }] }),
+          },
+        };
+      }
       emitResult({ request: previewBody }, format);
       return;
     }
@@ -162,7 +195,7 @@ export default defineCommand({
       settings,
       () =>
         ctx.client.requestJson<DashScopeAsyncResponse>({
-          path: videoGeneratePath(),
+          path: isKf2v ? image2videoPath() : videoGeneratePath(),
           method: "POST",
           body,
           async: true,

packages/commands/src/index.ts

@@ -66,6 +66,7 @@ export {
   finetuneTextCreate,
   finetuneAudioCreate,
   finetuneImageCreate,
+  finetuneVideoCreate,
 } from "./commands/finetune/create.ts";
 export { default as finetuneList } from "./commands/finetune/list.ts";
 export { default as finetuneGet } from "./commands/finetune/get.ts";
@@ -76,6 +77,7 @@ export { default as finetuneCheckpoints } from "./commands/finetune/checkpoints.
 export { default as finetuneExport } from "./commands/finetune/export.ts";
 export { default as finetuneWatch } from "./commands/finetune/watch.ts";
 export { default as finetuneCapability } from "./commands/finetune/capability.ts";
+export { default as finetunePrice } from "./commands/finetune/price.ts";
 export {
   deployTextCreate,
   deployAudioCreate,
@@ -87,6 +89,8 @@ export { default as deployModels } from "./commands/deploy/models.ts";
 export { default as deployScale } from "./commands/deploy/scale.ts";
 export { default as deployUpdate } from "./commands/deploy/update.ts";
 export { default as deployDelete } from "./commands/deploy/delete.ts";
+export { default as deployPause } from "./commands/deploy/pause.ts";
+export { default as deployResume } from "./commands/deploy/resume.ts";
 export { default as tokenPlanListSeats } from "./commands/token-plan/list-seats.ts";
 export { default as tokenPlanCreateKey } from "./commands/token-plan/create-key.ts";
 export { default as tokenPlanAssignSeats } from "./commands/token-plan/assign-seats.ts";

packages/commands/tests/e2e/deploy.e2e.test.ts

@@ -30,7 +30,7 @@ describe.skipIf(!isDashScopeE2EReady())("e2e: deploy (offline)", () => {
       "--help",
     ]);
     expect(exitCode, stderr).toBe(0);
-    expect(stderr).toMatch(/--model|--name/i);
+    expect(stderr).toMatch(/--model-name|--display-name/i);
   });
 
   test("deploy create --dry-run 构造 lora 部署请求体", async () => {
@@ -38,9 +38,9 @@ describe.skipIf(!isDashScopeE2EReady())("e2e: deploy (offline)", () => {
       "deploy",
       "text",
       "create",
-      "--model",
+      "--model-name",
       "qwen-plus-2025-12-01",
-      "--name",
+      "--display-name",
       "my-qwen-plus",
       "--dry-run",
       "--output",
@@ -68,9 +68,9 @@ describe.skipIf(!isDashScopeE2EReady())("e2e: deploy (offline)", () => {
       "deploy",
       "text",
       "create",
-      "--model",
+      "--model-name",
       "qwen3-8b",
-      "--name",
+      "--display-name",
       "my-qwen3-mu",
       "--plan",
       "mu",
@@ -102,9 +102,9 @@ describe.skipIf(!isDashScopeE2EReady())("e2e: deploy (offline)", () => {
       "deploy",
       "audio",
       "create",
-      "--model",
+      "--model-name",
       "my-cosyvoice-ft",
-      "--name",
+      "--display-name",
       "my-tts",
       "--dry-run",
       "--output",

packages/commands/tests/e2e/finetune.e2e.test.ts

@@ -31,7 +31,7 @@ describe.skipIf(!isDashScopeE2EReady())("e2e: finetune (offline)", () => {
       "--help",
     ]);
     expect(exitCode, stderr).toBe(0);
-    expect(stderr).toMatch(/--model|--datasets/i);
+    expect(stderr).toMatch(/--base-model|--datasets/i);
   });
 
   test("finetune create --dry-run 构造 SFT 默认请求体", async () => {
@@ -39,7 +39,7 @@ describe.skipIf(!isDashScopeE2EReady())("e2e: finetune (offline)", () => {
       "finetune",
       "text",
       "create",
-      "--model",
+      "--base-model",
       "qwen3-8b",
       "--datasets",
       "file-aaa,file-bbb",
@@ -73,7 +73,7 @@ describe.skipIf(!isDashScopeE2EReady())("e2e: finetune (offline)", () => {
       "finetune",
       "text",
       "create",
-      "--model",
+      "--base-model",
       "qwen3-8b",
       "--datasets",
       "file-aaa",
@@ -135,7 +135,7 @@ describe.skipIf(!isDashScopeE2EReady())("e2e: finetune (offline)", () => {
         "finetune",
         "text",
         "create",
-        "--model",
+        "--base-model",
         "qwen3-8b",
         "--datasets",
         "file-aaa",
@@ -157,7 +157,7 @@ describe.skipIf(!isDashScopeE2EReady())("e2e: finetune (offline)", () => {
       "finetune",
       "text",
       "create",
-      "--model",
+      "--base-model",
       "qwen3-8b",
       "--datasets",
       "file-aaa",
@@ -176,7 +176,7 @@ describe.skipIf(!isDashScopeE2EReady())("e2e: finetune (offline)", () => {
       "finetune",
       "text",
       "create",
-      "--model",
+      "--base-model",
       "qwen3-8b",
       "--datasets",
       `${localPath},file-bbb`,
@@ -207,7 +207,7 @@ describe.skipIf(!isDashScopeE2EReady())("e2e: finetune (offline)", () => {
       "finetune",
       "text",
       "create",
-      "--model",
+      "--base-model",
       "qwen3-8b",
       "--datasets",
       " , ",
@@ -228,7 +228,7 @@ describe.skipIf(!isDashScopeE2EReady())("e2e: finetune (offline)", () => {
       "finetune",
       "text",
       "create",
-      "--model",
+      "--base-model",
       "qwen3-8b",
       "--datasets",
       localPath,
@@ -250,7 +250,7 @@ describe.skipIf(!isDashScopeE2EReady())("e2e: finetune (offline)", () => {
       "finetune",
       "text",
       "create",
-      "--model",
+      "--base-model",
       "qwen3-8b",
       "--datasets",
       localPath,
@@ -272,7 +272,7 @@ describe.skipIf(!isDashScopeE2EReady())("e2e: finetune (offline)", () => {
     ["cancel", ["--job-id", "ft-xxx"]],
     ["delete", ["--job-id", "ft-xxx"]],
     ["watch", ["--job-id", "ft-xxx"]],
-    ["capability", ["--model", "qwen3-8b"]],
+    ["capability", ["--base-model", "qwen3-8b"]],
   ])("finetune %s --dry-run 发出结构化动作", async (sub, extra) => {
     const { stdout, stderr, exitCode } = await runCommandE2e(FINETUNE_ROUTES, [
       "finetune",
@@ -292,7 +292,7 @@ describe.skipIf(!isDashScopeE2EReady())("e2e: finetune (offline)", () => {
       "finetune",
       "text",
       "create",
-      "--model",
+      "--base-model",
       "qwen3-8b",
       "--datasets",
       " file-a , ,file-b ",
@@ -314,7 +314,7 @@ describe.skipIf(!isDashScopeE2EReady())("e2e: finetune (offline)", () => {
       "finetune",
       "audio",
       "create",
-      "--model",
+      "--base-model",
       "cosyvoice-v3-flash",
       "--datasets",
       "file-audio",
@@ -343,7 +343,7 @@ describe.skipIf(!isDashScopeE2EReady())("e2e: finetune (offline)", () => {
       "--help",
     ]);
     expect(exitCode, stderr).toBe(0);
-    expect(stderr).toMatch(/--model|--datasets/i);
+    expect(stderr).toMatch(/--base-model|--datasets/i);
     expect(stderr).not.toMatch(/--training-type|--n-epochs|--batch-size|--max-length/);
   });
 
@@ -352,7 +352,7 @@ describe.skipIf(!isDashScopeE2EReady())("e2e: finetune (offline)", () => {
       "finetune",
       "image",
       "create",
-      "--model",
+      "--base-model",
       "wan2.7-image-pro",
       "--datasets",
       "file-image",
@@ -365,6 +365,104 @@ describe.skipIf(!isDashScopeE2EReady())("e2e: finetune (offline)", () => {
     expect(data.action).toBe("finetune.create");
     expect(data.body.training_type).toBe("efficient_sft");
   });
+
+  test("finetune video create --help 暴露视频超参且不含文本超参", async () => {
+    // Video exposes --n-epochs / --batch-size / --learning-rate; the text-only
+    // --training-type / --max-length surface is not offered.
+    const { stderr, exitCode } = await runCommandE2e(FINETUNE_ROUTES, [
+      "finetune",
+      "video",
+      "create",
+      "--help",
+    ]);
+    expect(exitCode, stderr).toBe(0);
+    expect(stderr).toMatch(/--base-model/);
+    expect(stderr).toMatch(/--n-epochs/);
+    expect(stderr).toMatch(/--batch-size/);
+    expect(stderr).toMatch(/--learning-rate/);
+    expect(stderr).not.toMatch(/--training-type|--max-length/);
+  });
+
+  test("finetune video create --datasets 缺失时退出为用法错误 (2)", async () => {
+    const { stderr, exitCode } = await runCommandE2e(FINETUNE_ROUTES, [
+      "finetune",
+      "video",
+      "create",
+      "--base-model",
+      "wan2.7-i2v",
+      "--quiet",
+    ]);
+    expect(exitCode).toBe(2);
+    expect(stderr).toMatch(/--datasets|Missing required/i);
+  });
+
+  test.each([
+    // Model-family-specific defaults resolved by the sft-lora video profile.
+    ["wan2.7-i2v", 1, 102400],
+    ["wan2.5-i2v-preview", 4, 36864],
+    ["wan2.2-kf2v-flash", 4, 262144],
+  ])(
+    "finetune video create --dry-run %s 解析 batch_size=%i / max_pixels=%i",
+    async (baseModel, batchSize, maxPixels) => {
+      const { stdout, stderr, exitCode } = await runCommandE2e(FINETUNE_ROUTES, [
+        "finetune",
+        "video",
+        "create",
+        "--base-model",
+        baseModel,
+        "--datasets",
+        "file-video",
+        "--dry-run",
+        "--output",
+        "json",
+      ]);
+      expect(exitCode, stderr).toBe(0);
+      const data = parseStdoutJson<{
+        action: string;
+        body: {
+          model: string;
+          training_type: string;
+          hyper_parameters: Record<string, unknown>;
+        };
+      }>(stdout);
+      expect(data.action).toBe("finetune.create");
+      expect(data.body.model).toBe(baseModel);
+      expect(data.body.training_type).toBe("efficient_sft");
+      expect(data.body.hyper_parameters.batch_size).toBe(batchSize);
+      expect(data.body.hyper_parameters.max_pixels).toBe(maxPixels);
+      expect(data.body.hyper_parameters.learning_rate).toBe("2e-5");
+      expect(data.body.hyper_parameters.lora_rank).toBe(32);
+    },
+  );
+
+  test("finetune video create --dry-run 转发超参覆盖且不做 clamp", async () => {
+    const { stdout, stderr, exitCode } = await runCommandE2e(FINETUNE_ROUTES, [
+      "finetune",
+      "video",
+      "create",
+      "--base-model",
+      "wan2.7-i2v",
+      "--datasets",
+      "file-video",
+      "--n-epochs",
+      "100",
+      "--batch-size",
+      "2",
+      "--learning-rate",
+      "1e-5",
+      "--dry-run",
+      "--output",
+      "json",
+    ]);
+    expect(exitCode, stderr).toBe(0);
+    const data = parseStdoutJson<{
+      body: { hyper_parameters: Record<string, unknown> };
+    }>(stdout);
+    // Video overrides are forwarded verbatim (no [8, 1024] text clamp).
+    expect(data.body.hyper_parameters.n_epochs).toBe(100);
+    expect(data.body.hyper_parameters.batch_size).toBe(2);
+    expect(data.body.hyper_parameters.learning_rate).toBe("1e-5");
+  });
 });
 
 describe.skipIf(!isDashScopeE2EReady())("e2e: finetune (DashScope)", () => {

packages/commands/tests/e2e/topic-routes.ts

@@ -135,6 +135,7 @@ export const FINETUNE_ROUTES: E2eRouteExports = {
   "finetune text create": "finetuneTextCreate",
   "finetune audio create": "finetuneAudioCreate",
   "finetune image create": "finetuneImageCreate",
+  "finetune video create": "finetuneVideoCreate",
   "finetune list": "finetuneList",
   "finetune get": "finetuneGet",
   "finetune cancel": "finetuneCancel",

packages/commands/tests/e2e/video-generate-i2v.e2e.test.ts

@@ -112,6 +112,62 @@ describe("e2e: video generate (i2v)", () => {
     }>(stdout);
     expect(data.request?.input?.media?.[0]?.url).toBe("data:image/png;base64,<omitted>");
   });
+
+  test.each([
+    // wan2.1~2.6 (legacy) use flat img_url; wan2.7+ and happyhorse use media[].
+    ["wan2.5-i2v-preview", "img_url"],
+    ["wan2.6-i2v", "img_url"],
+    ["wan2.7-i2v", "media"],
+    ["happyhorse-1.1-i2v", "media"],
+  ])("video generate --dry-run %s 首帧走 %s 字段", async (model, field) => {
+    const configDir = makeE2eOutputDir(`video-i2v-input-shape-${model}`);
+    writeFileSync(
+      join(configDir, "config.json"),
+      JSON.stringify({
+        "token-plan": {
+          api_key: "sk-sp-e2e-placeholder",
+          base_url: "https://token-plan.cn-beijing.maas.aliyuncs.com",
+        },
+      }),
+    );
+
+    const { stdout, stderr, exitCode } = await runCommandE2e(
+      VIDEO_ROUTES,
+      [
+        "video",
+        "generate",
+        "--config",
+        "token-plan",
+        "--dry-run",
+        "--model",
+        model,
+        "--image",
+        "https://example.com/placeholder.png",
+        "--prompt",
+        "干跑校验",
+        "--output",
+        "json",
+      ],
+      {
+        BAILIAN_CONFIG_DIR: configDir,
+        DASHSCOPE_API_KEY: "",
+        DASHSCOPE_BASE_URL: "",
+      },
+    );
+    expect(exitCode, stderr).toBe(0);
+    const data = parseStdoutJson<{
+      request?: {
+        input?: { img_url?: string; media?: Array<{ type?: string; url?: string }> };
+      };
+    }>(stdout);
+    if (field === "img_url") {
+      expect(data.request?.input?.img_url).toBe("https://example.com/placeholder.png");
+      expect(data.request?.input?.media).toBeUndefined();
+    } else {
+      expect(data.request?.input?.media?.[0]?.type).toBe("first_frame");
+      expect(data.request?.input?.img_url).toBeUndefined();
+    }
+  });
 });
 
 describe.skipIf(!isBailianE2EVideoEnabled() || !isDashScopeE2EReady())(

packages/core/src/client/endpoints.ts

@@ -32,6 +32,11 @@ export function videoGeneratePath(): string {
   return "/api/v1/services/aigc/video-generation/video-synthesis";
 }
 
+/** POST /api/v1/services/aigc/image2video/video-synthesis — kf2v (first+last frame). */
+export function image2videoPath(): string {
+  return "/api/v1/services/aigc/image2video/video-synthesis";
+}
+
 // ---- Async Task Query ----
 export function taskPath(taskId: string): string {
   return `/api/v1/tasks/${encodeURIComponent(taskId)}`;

packages/core/src/client/index.ts

@@ -19,6 +19,7 @@ export {
   taskPath,
   userProfilePath,
   videoGeneratePath,
+  image2videoPath,
 } from "./endpoints.ts";
 export {
   isLegacyImage2ImageModel,

packages/core/src/deploy/index.ts

@@ -2,3 +2,4 @@ export * from "./api.ts";
 export * from "./types.ts";
 export * from "./constants.ts";
 export * from "./plans.ts";
+export * from "./lifecycle.ts";

packages/core/src/deploy/lifecycle.ts

@@ -0,0 +1,99 @@
+/**
+ * Deployment lifecycle operations via the **console gateway**.
+ *
+ * Unlike the DashScope REST endpoints in `api.ts`, start/stop/list-independent
+ * are console-domain APIs (`zeldaEasy.broadscope-platform.modelInstance.*`).
+ * Commands using these must declare `auth: "console"`.
+ */
+import type { Client } from "../client/client.ts";
+import { unwrapResponse } from "../console/models.ts";
+
+// ---------------------------------------------------------------------------
+// API names
+// ---------------------------------------------------------------------------
+
+export const DEPLOY_START_API = "zeldaEasy.broadscope-platform.modelInstance.startModelService";
+export const DEPLOY_STOP_API = "zeldaEasy.broadscope-platform.modelInstance.stopModelService";
+export const DEPLOY_LIST_INDEPENDENT_API =
+  "zeldaEasy.broadscope-platform.modelInstance.listIndependentDeployedModel";
+
+// ---------------------------------------------------------------------------
+// Types
+// ---------------------------------------------------------------------------
+
+export interface ModelServiceEntry {
+  modelServiceId?: string;
+  deployedModel?: string;
+  deployed_model?: string;
+  status?: string;
+  modelName?: string;
+  model_name?: string;
+  plan?: string;
+  [key: string]: unknown;
+}
+
+// ---------------------------------------------------------------------------
+// API wrappers
+// ---------------------------------------------------------------------------
+
+/** Start (bring online) a stopped deployment. */
+export async function startModelService(
+  client: Client,
+  modelServiceId: string,
+): Promise<Record<string, unknown>> {
+  const raw = await client.console<Record<string, unknown>>(DEPLOY_START_API, {
+    input: { modelServiceId },
+  });
+  return unwrapResponse(raw);
+}
+
+/** Stop (take offline) a running deployment. Stops billing for mu/ptu plans. */
+export async function stopModelService(
+  client: Client,
+  modelServiceId: string,
+): Promise<Record<string, unknown>> {
+  const raw = await client.console<Record<string, unknown>>(DEPLOY_STOP_API, {
+    input: { modelServiceId },
+  });
+  return unwrapResponse(raw);
+}
+
+/**
+ * List independently deployed models (console domain).
+ * Used for precheck status verification and ID mapping.
+ * Paginates internally to return all entries.
+ */
+export async function listIndependentDeployedModels(client: Client): Promise<ModelServiceEntry[]> {
+  const allEntries: ModelServiceEntry[] = [];
+  let page = 1;
+
+  while (true) {
+    const raw = await client.console<Record<string, unknown>>(DEPLOY_LIST_INDEPENDENT_API, {
+      input: { pageNo: page, pageSize: 50 },
+    });
+    const resp = unwrapResponse(raw);
+    const records = (resp.records ?? []) as ModelServiceEntry[];
+    allEntries.push(...records);
+    const pageCount = (resp.pageCount as number) ?? 1;
+    if (page >= pageCount || records.length === 0) break;
+    page++;
+  }
+
+  return allEntries;
+}
+
+/**
+ * Find a deployment entry by its identifier in the console-domain list.
+ * Matches against `modelServiceId`, `deployedModel`, or `deployed_model`.
+ */
+export function findDeploymentEntry(
+  entries: ModelServiceEntry[],
+  deployedModel: string,
+): ModelServiceEntry | undefined {
+  return entries.find(
+    (entry) =>
+      entry.modelServiceId === deployedModel ||
+      entry.deployedModel === deployedModel ||
+      entry.deployed_model === deployedModel,
+  );
+}

packages/core/src/finetune/api.ts

@@ -43,6 +43,8 @@ export interface ListFineTunesParams {
   pageNo?: number;
   pageSize?: number;
   status?: string;
+  /** Filter by base model ID (server-side). */
+  model?: string;
   signal?: AbortSignal;
 }
 
@@ -55,6 +57,7 @@ export async function listFineTunes(
   if (params.pageNo !== undefined) qs.set("page_no", String(params.pageNo));
   if (params.pageSize !== undefined) qs.set("page_size", String(params.pageSize));
   if (params.status) qs.set("status", params.status);
+  if (params.model) qs.set("model", params.model);
   const base = finetuneJobsPath();
   const path = qs.toString() ? `${base}?${qs.toString()}` : base;
   return client.requestJson<ListFineTunesResponse>({

packages/core/src/finetune/index.ts

@@ -3,3 +3,4 @@ export * from "./api.ts";
 export * from "./capability.ts";
 export * from "./preflight.ts";
 export * from "./profiles/index.ts";
+export * from "./price.ts";

packages/core/src/finetune/price.ts

@@ -0,0 +1,121 @@
+/**
+ * Training price estimation via the **console gateway**.
+ *
+ * These are console-domain APIs (`zeldaEasy.broadscope-platform.*`); commands
+ * using them must declare `auth: "console"`. Two different argument wrappers
+ * exist: `getModelPrice` takes a top-level `query`, while the token-estimation
+ * APIs take a top-level `input`.
+ */
+import type { Client } from "../client/client.ts";
+import { unwrapResponse } from "../console/models.ts";
+
+// ---------------------------------------------------------------------------
+// API names
+// ---------------------------------------------------------------------------
+
+export const TRAINING_MODEL_PRICE_API = "zeldaEasy.broadscope-platform.modelCenter.getModelPrice";
+export const CALC_DATASETS_TOKENS_API =
+  "zeldaEasy.broadscope-platform.modelInstance.calculateDatasetsTotalTokens";
+export const ESTIMATE_FINETUNE_TOKENS_API =
+  "zeldaEasy.broadscope-platform.modelInstance.estimateFinetuneTokens";
+
+// ---------------------------------------------------------------------------
+// Types
+// ---------------------------------------------------------------------------
+
+export interface TrainingModelPrice {
+  price?: string;
+  priceUnit?: string;
+  modelId?: string;
+  [key: string]: unknown;
+}
+
+export interface TokenEstimate {
+  estimatedDatasetConsumedTokensMinPerEpoch?: number;
+  estimatedDatasetConsumedTokensMaxPerEpoch?: number;
+  estimatedMixedConsumedTokensMinPerEpoch?: number;
+  estimatedMixedConsumedTokensMaxPerEpoch?: number;
+  [key: string]: unknown;
+}
+
+// ---------------------------------------------------------------------------
+// API wrappers
+// ---------------------------------------------------------------------------
+
+/**
+ * Training unit price for a model. `price` is denominated in `priceUnit`
+ * (typically "千Token" — yuan per 1000 tokens).
+ */
+export async function fetchTrainingModelPrice(
+  client: Client,
+  modelId: string,
+): Promise<TrainingModelPrice> {
+  const raw = await client.console<Record<string, unknown>>(TRAINING_MODEL_PRICE_API, {
+    query: { type: 0, modelId },
+  });
+  return unwrapResponse(raw) as TrainingModelPrice;
+}
+
+/**
+ * Estimate training tokens for SFT / DPO jobs.
+ * Returns a per-epoch min/max range; multiply by `n_epochs` for the total.
+ */
+export async function estimateSftDpoTokens(
+  client: Client,
+  datasetIds: string[],
+  hyperParams: { nEpochs: number; batchSize: number; maxLength: number },
+): Promise<TokenEstimate> {
+  const raw = await client.console<Record<string, unknown>>(CALC_DATASETS_TOKENS_API, {
+    input: { trainDatasetIds: datasetIds, hyperParams },
+  });
+  return unwrapResponse(raw) as TokenEstimate;
+}
+
+/**
+ * Estimate training tokens for CPT jobs.
+ *
+ * The console API requires `hyperParams` as a **JSON string** with a full
+ * `userDefinedObj` payload (captured from the console frontend), plus several
+ * top-level fields (`algorithmType`, `bizType`, `priority`, …). Only
+ * `n_epochs` / `max_length` materially affect the estimate; the remaining
+ * hyper-parameters are fixed defaults.
+ */
+export async function estimateCptTokens(
+  client: Client,
+  model: string,
+  datasetIdsCsv: string,
+  nEpochs: number,
+): Promise<TokenEstimate> {
+  const userDefinedObj = {
+    batch_size: 16,
+    eval_steps: 50,
+    learning_rate: "7e-6",
+    lr_scheduler_type: "linear",
+    max_length: 8192,
+    n_epochs: nEpochs,
+    split: 0.9,
+    save_total_limit: "3",
+    resume_from_checkpoint: false,
+    save_strategy: "epoch",
+  };
+  const hyperParams = JSON.stringify({
+    useDefault: false,
+    userDefinedObj,
+    useQwenMixedStrategy: false,
+  });
+  const raw = await client.console<Record<string, unknown>>(ESTIMATE_FINETUNE_TOKENS_API, {
+    input: {
+      trainingType: "cpt",
+      instanceName: `${model}_cli_estimate`,
+      algorithmType: 100,
+      bizType: 100,
+      trainDatasetIds: datasetIdsCsv,
+      hyperParams,
+      bailianTrainModel: model,
+      validationDatasetIds: "",
+      jobName: `${model}_cli_estimate`,
+      priority: "L0",
+    },
+  });
+  return unwrapResponse(raw) as TokenEstimate;
+}

packages/core/src/finetune/profiles/sft-lora.ts

@@ -75,20 +75,24 @@ const IMAGE_HYPER_PARAMS_I2I: Record<string, unknown> = {
  *
  * Shared across all video models; `batch_size` and `max_pixels` differ by model
  * family (resolved per model in `resolveHyperParameters`):
- *   - wan2.5 (e.g. wan2.5-i2v-preview): batch_size 2, max_pixels 36864
- *   - wan2.2 (i2v-flash / kf2v-flash):  batch_size 4, max_pixels 262144
+ *   - wan2.7 (e.g. wan2.7-i2v):           batch_size 1, max_pixels 102400
+ *   - wan2.5 (e.g. wan2.5-i2v-preview):   batch_size 4, max_pixels 36864
+ *   - wan2.2 (i2v-flash / kf2v-flash):    batch_size 4, max_pixels 262144
  *
  * `learning_rate` is a string to avoid JSON-number precision loss (consistent
  * with the image defaults). `split` (0.9) + `max_split_val_dataset_sample`
  * (5) drive the automatic train/validation split when no explicit
  * validation_file_ids are provided.
+ *
+ * Values aligned with the official user guide (2026-07):
+ *   n_epochs 50, eval_epochs 20 (≥ n_epochs/10).
  */
 const VIDEO_HYPER_PARAMS_BASE: Record<string, unknown> = {
-  n_epochs: 400,
+  n_epochs: 50,
   learning_rate: "2e-5",
-  split: 0.9,
+  split: 0.5,
   max_split_val_dataset_sample: 5,
-  eval_epochs: 50,
+  eval_epochs: 20,
   save_total_limit: 10,
   lora_rank: 32,
   lora_alpha: 32,
@@ -109,6 +113,11 @@ function isWan25(model: string | undefined): boolean {
   return typeof model === "string" && /wan2\.5/i.test(model);
 }
 
+/** wan2.7 family uses batch_size 1 and max_pixels 102400. */
+function isWan27(model: string | undefined): boolean {
+  return typeof model === "string" && /wan2\.7/i.test(model);
+}
+
 export const sftLoraProfile: TrainingProfile = {
   clientTrainingType: "sft-lora",
   serverTrainingType: "efficient_sft",
@@ -195,15 +204,18 @@ export const sftLoraProfile: TrainingProfile = {
     }
     if (isVideo(modality)) {
       // Video: shared defaults + model-family-specific batch_size / max_pixels.
-      // wan2.5 uses batch_size 2 / max_pixels 36864; wan2.2 uses 4 / 262144.
-      const wan25 = isWan25(flags.model as string | undefined);
+      //   wan2.7: batch_size 1, max_pixels 102400
+      //   wan2.5: batch_size 4, max_pixels 36864
+      //   wan2.2: batch_size 4, max_pixels 262144
+      const model = (flags.model ?? flags.baseModel) as string | undefined;
       const hp: Record<string, unknown> = {
         ...VIDEO_HYPER_PARAMS_BASE,
-        batch_size: 4,
-        max_pixels: wan25 ? 36864 : 262144,
+        batch_size: isWan27(model) ? 1 : 4,
+        max_pixels: isWan27(model) ? 102400 : isWan25(model) ? 36864 : 262144,
       };
       // Optional overrides (no clamping — video batch_size is intentionally small).
       if (flags.nEpochs !== undefined) hp.n_epochs = flags.nEpochs as number;
+      if (flags.batchSize !== undefined) hp.batch_size = flags.batchSize as number;
       if (flags.learningRate !== undefined) hp.learning_rate = flags.learningRate as string;
       return hp;
     }

packages/core/src/types/api.ts

@@ -168,6 +168,8 @@ export interface DashScopeVideoRequest {
     prompt: string;
     negative_prompt?: string;
     img_url?: string;
+    first_frame_url?: string;
+    last_frame_url?: string;
     media?: Array<{
       type: "image" | "video" | "first_frame" | "last_frame" | "driving_audio" | "first_clip";
       url: string;

skills/bailian-finetune/SKILL.md

@@ -23,14 +23,14 @@ description: >-
 ```
 1. Validate data   bl dataset validate --file train.jsonl [--schema chatml|dpo|cpt|tts|image]
 2. Upload data     bl dataset upload --file train.jsonl          # returns a file-id
-3. Create job      bl finetune text|audio|image create --model <base> --datasets <file-id|path>
+3. Create job      bl finetune text|audio|image create --base-model <base> --datasets <file-id|path>
 4. Watch progress  bl finetune watch --job-id ft-xxx             # or get / logs
 5. Pick artifact   bl finetune checkpoints --job-id ft-xxx
 6. Export model    bl finetune export --job-id ft-xxx --checkpoint ckpt-N --model-name my-model
-7. Deploy service  bl deploy text|audio|image create --model my-model --name my-svc
+7. Deploy service  bl deploy text|audio|image create --model-name my-model --display-name my-svc
 ```
 
-- Unsure which training methods a base model supports → `bl finetune capability --model <base>` or `--training-type sft|sft-lora|dpo|cpt`.
+- Unsure which training methods a base model supports → `bl finetune capability --base-model <base>` or `--training-type sft|sft-lora|dpo|cpt`.
 - Text `--training-type` values: `sft` / `sft-lora` / `dpo` / `dpo-lora` / `cpt`. Audio bases include `cosyvoice-v3-flash`; image bases include `wan2.7-image-pro`.
 - Deployment plans: audio defaults to `--plan mu`; text/image default to `lora`.
 - Preview write operations (create / delete / cancel / scale) with `--dry-run` first, and confirm with the user before deleting a job or dataset.
@@ -55,10 +55,10 @@ Flags, usage, and examples: see [`reference/`](reference/index.md) or `bl <comma
 ```bash
 bl dataset validate --file train.jsonl
 bl dataset upload --file train.jsonl
-bl finetune text create --model qwen3-8b --training-type sft-lora --datasets file-xxx
+bl finetune text create --base-model qwen3-8b --training-type sft-lora --datasets file-xxx
 bl finetune watch --job-id ft-xxx
 bl finetune export --job-id ft-xxx --checkpoint ckpt-3 --model-name my-qwen-sft
-bl deploy text create --model my-qwen-sft --name my-svc
+bl deploy text create --model-name my-qwen-sft --display-name my-svc
 ```
 
 ## Common hand-offs

skills/bailian-finetune/reference/deploy.md

@@ -7,43 +7,45 @@ Index: [index.md](index.md)
 
 ## Commands in this group
 
-| Command                  | Description                                               |
-| ------------------------ | --------------------------------------------------------- |
-| `bl deploy audio create` | Create an audio (TTS) model deployment                    |
-| `bl deploy delete`       | Delete a model deployment (must be STOPPED or FAILED)     |
-| `bl deploy get`          | Get details of a single model deployment                  |
-| `bl deploy image create` | Create an image generation model deployment               |
-| `bl deploy list`         | List model deployments                                    |
-| `bl deploy models`       | List models available for deployment                      |
-| `bl deploy scale`        | Scale a deployment's capacity                             |
-| `bl deploy text create`  | Create a text model deployment                            |
-| `bl deploy update`       | Update a deployment's rate limits (rpm_limit / tpm_limit) |
+| Command                  | Description                                                   |
+| ------------------------ | ------------------------------------------------------------- |
+| `bl deploy audio create` | Create an audio (TTS) model deployment                        |
+| `bl deploy delete`       | Delete a model deployment (must be STOPPED or FAILED)         |
+| `bl deploy get`          | Get details of a single model deployment                      |
+| `bl deploy image create` | Create an image generation model deployment                   |
+| `bl deploy list`         | List model deployments                                        |
+| `bl deploy models`       | List models available for deployment                          |
+| `bl deploy pause`        | Pause a running model deployment (stops billing for mu/ptu)   |
+| `bl deploy resume`       | Resume a paused model deployment (brings service back online) |
+| `bl deploy scale`        | Scale a deployment's capacity                                 |
+| `bl deploy text create`  | Create a text model deployment                                |
+| `bl deploy update`       | Update a deployment's rate limits (rpm_limit / tpm_limit)     |
 
 ## Command details
 
 ### `bl deploy audio create`
 
-| Field           | Value                                                                                                                                                                                                             |
-| --------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **Name**        | `deploy audio create`                                                                                                                                                                                             |
-| **Description** | Create an audio (TTS) model deployment                                                                                                                                                                            |
-| **Usage**       | `bl deploy audio create --model <model_name> --name <display_name> [--plan <plan>] [--deploy-spec <id>] [--capacity <n>] [--billing-method <m>] [--input-tpm <n>] [--output-tpm <n>] [--thinking-output-tpm <n>]` |
+| Field           | Value                                                                                                                                                                                                                          |
+| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| **Name**        | `deploy audio create`                                                                                                                                                                                                          |
+| **Description** | Create an audio (TTS) model deployment                                                                                                                                                                                         |
+| **Usage**       | `bl deploy audio create --model-name <model_name> --display-name <display_name> [--plan <plan>] [--deploy-spec <id>] [--capacity <n>] [--billing-method <m>] [--input-tpm <n>] [--output-tpm <n>] [--thinking-output-tpm <n>]` |
 
 #### Flags
 
-| Flag                        | Type   | Required | Description                                                                     |
-| --------------------------- | ------ | -------- | ------------------------------------------------------------------------------- |
-| `--model <name>`            | string | yes      | Model name (catalog model or fine-tuned output) (required)                      |
-| `--name <display_name>`     | string | yes      | Console display name for the deployment (required)                              |
-| `--plan <plan>`             | string | no       | Billing plan: lora (default, Token-billed) \| ptu (Token-billed) \| mu          |
-| `--deploy-spec <id>`        | string | no       | Deploy spec (only used by plan=mu; auto-picked if omitted)                      |
-| `--capacity <n>`            | number | no       | Resource units (plan=mu only; required by API; defaults to the template's unit) |
-| `--billing-method <m>`      | string | no       | Billing method (plan=mu only; default "POST_PAY", the only supported value)     |
-| `--input-tpm <n>`           | number | no       | PTU max input tokens/min (required for plan=ptu)                                |
-| `--output-tpm <n>`          | number | no       | PTU max output tokens/min (required for plan=ptu)                               |
-| `--thinking-output-tpm <n>` | number | no       | PTU max thinking-output tokens/min (optional, some models)                      |
-| `--api-key <key>`           | string | no       | API key                                                                         |
-| `--base-url <url>`          | string | no       | API base URL                                                                    |
+| Flag                            | Type   | Required | Description                                                                     |
+| ------------------------------- | ------ | -------- | ------------------------------------------------------------------------------- |
+| `--model-name <model_name>`     | string | yes      | Model to deploy — fine-tuned output name or catalog model (required)            |
+| `--display-name <display_name>` | string | yes      | Console display name for the deployment (required)                              |
+| `--plan <plan>`                 | string | no       | Billing plan: lora (default, Token-billed) \| ptu (Token-billed) \| mu          |
+| `--deploy-spec <id>`            | string | no       | Deploy spec (only used by plan=mu; auto-picked if omitted)                      |
+| `--capacity <n>`                | number | no       | Resource units (plan=mu only; required by API; defaults to the template's unit) |
+| `--billing-method <m>`          | string | no       | Billing method (plan=mu only; default "POST_PAY", the only supported value)     |
+| `--input-tpm <n>`               | number | no       | PTU max input tokens/min (required for plan=ptu)                                |
+| `--output-tpm <n>`              | number | no       | PTU max output tokens/min (required for plan=ptu)                               |
+| `--thinking-output-tpm <n>`     | number | no       | PTU max thinking-output tokens/min (optional, some models)                      |
+| `--api-key <key>`               | string | no       | API key                                                                         |
+| `--base-url <url>`              | string | no       | API base URL                                                                    |
 
 #### Notes
 
@@ -58,27 +60,24 @@ Index: [index.md](index.md)
 - Use `bl deploy models --source base` to inspect available templates.
 - After creation, status starts at PENDING and transitions to RUNNING.
 - Invoke the deployed model with: bl text chat --model <deployed_model>
-- WARNING: --model is overloaded across commands and refers to DIFFERENT
-- values. `bl deploy <modality> create --model` takes the exported model_name
-- (e.g. `qwen3-8b-ft-...`), but the create response also returns a
-- `deployed_model` field (the deployment instance id, e.g.
-- `qwen3-8b-5ecb5f068d79`). The inference call `bl text chat --model` must use
-- the `deployed_model` from the create response — NOT the `model_name` you
-- passed to `deploy <modality> create`. Do not reuse the value across the two
-- commands.
+- NOTE: --model-name is the model being deployed (e.g. `qwen3-8b-ft-...`).
+- The create response also returns a `deployed_model` field — the deployment
+- instance id (e.g. `qwen3-8b-5ecb5f068d79`). Use that id for inference
+- (`bl text chat --model <deployed_model>`) and lifecycle commands
+- (`deploy get/scale/pause/resume/delete --deployed-model <id>`).
 
 #### Examples
 
 ```bash
-bl deploy audio create --model my-cosyvoice-ft --name my-tts
+bl deploy audio create --model-name my-cosyvoice-ft --display-name my-tts
 ```
 
 ```bash
-bl deploy audio create --model my-cosyvoice-ft --name my-tts --deploy-spec dps-xxxx --capacity 1
+bl deploy audio create --model-name my-cosyvoice-ft --display-name my-tts --deploy-spec dps-xxxx --capacity 1
 ```
 
 ```bash
-bl deploy audio create --model my-cosyvoice-ft --name my-tts --dry-run
+bl deploy audio create --model-name my-cosyvoice-ft --display-name my-tts --dry-run
 ```
 
 ### `bl deploy delete`
@@ -136,27 +135,27 @@ bl deploy get --deployed-model qwen-plus-2025-12-01-b6d61c71 --output json
 
 ### `bl deploy image create`
 
-| Field           | Value                                                                                                                                                                                                             |
-| --------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **Name**        | `deploy image create`                                                                                                                                                                                             |
-| **Description** | Create an image generation model deployment                                                                                                                                                                       |
-| **Usage**       | `bl deploy image create --model <model_name> --name <display_name> [--plan <plan>] [--deploy-spec <id>] [--capacity <n>] [--billing-method <m>] [--input-tpm <n>] [--output-tpm <n>] [--thinking-output-tpm <n>]` |
+| Field           | Value                                                                                                                                                                                                                          |
+| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| **Name**        | `deploy image create`                                                                                                                                                                                                          |
+| **Description** | Create an image generation model deployment                                                                                                                                                                                    |
+| **Usage**       | `bl deploy image create --model-name <model_name> --display-name <display_name> [--plan <plan>] [--deploy-spec <id>] [--capacity <n>] [--billing-method <m>] [--input-tpm <n>] [--output-tpm <n>] [--thinking-output-tpm <n>]` |
 
 #### Flags
 
-| Flag                        | Type   | Required | Description                                                                     |
-| --------------------------- | ------ | -------- | ------------------------------------------------------------------------------- |
-| `--model <name>`            | string | yes      | Model name (catalog model or fine-tuned output) (required)                      |
-| `--name <display_name>`     | string | yes      | Console display name for the deployment (required)                              |
-| `--plan <plan>`             | string | no       | Billing plan: lora (default, Token-billed) \| ptu (Token-billed) \| mu          |
-| `--deploy-spec <id>`        | string | no       | Deploy spec (only used by plan=mu; auto-picked if omitted)                      |
-| `--capacity <n>`            | number | no       | Resource units (plan=mu only; required by API; defaults to the template's unit) |
-| `--billing-method <m>`      | string | no       | Billing method (plan=mu only; default "POST_PAY", the only supported value)     |
-| `--input-tpm <n>`           | number | no       | PTU max input tokens/min (required for plan=ptu)                                |
-| `--output-tpm <n>`          | number | no       | PTU max output tokens/min (required for plan=ptu)                               |
-| `--thinking-output-tpm <n>` | number | no       | PTU max thinking-output tokens/min (optional, some models)                      |
-| `--api-key <key>`           | string | no       | API key                                                                         |
-| `--base-url <url>`          | string | no       | API base URL                                                                    |
+| Flag                            | Type   | Required | Description                                                                     |
+| ------------------------------- | ------ | -------- | ------------------------------------------------------------------------------- |
+| `--model-name <model_name>`     | string | yes      | Model to deploy — fine-tuned output name or catalog model (required)            |
+| `--display-name <display_name>` | string | yes      | Console display name for the deployment (required)                              |
+| `--plan <plan>`                 | string | no       | Billing plan: lora (default, Token-billed) \| ptu (Token-billed) \| mu          |
+| `--deploy-spec <id>`            | string | no       | Deploy spec (only used by plan=mu; auto-picked if omitted)                      |
+| `--capacity <n>`                | number | no       | Resource units (plan=mu only; required by API; defaults to the template's unit) |
+| `--billing-method <m>`          | string | no       | Billing method (plan=mu only; default "POST_PAY", the only supported value)     |
+| `--input-tpm <n>`               | number | no       | PTU max input tokens/min (required for plan=ptu)                                |
+| `--output-tpm <n>`              | number | no       | PTU max output tokens/min (required for plan=ptu)                               |
+| `--thinking-output-tpm <n>`     | number | no       | PTU max thinking-output tokens/min (optional, some models)                      |
+| `--api-key <key>`               | string | no       | API key                                                                         |
+| `--base-url <url>`              | string | no       | API base URL                                                                    |
 
 #### Notes
 
@@ -171,27 +170,24 @@ bl deploy get --deployed-model qwen-plus-2025-12-01-b6d61c71 --output json
 - Use `bl deploy models --source base` to inspect available templates.
 - After creation, status starts at PENDING and transitions to RUNNING.
 - Invoke the deployed model with: bl text chat --model <deployed_model>
-- WARNING: --model is overloaded across commands and refers to DIFFERENT
-- values. `bl deploy <modality> create --model` takes the exported model_name
-- (e.g. `qwen3-8b-ft-...`), but the create response also returns a
-- `deployed_model` field (the deployment instance id, e.g.
-- `qwen3-8b-5ecb5f068d79`). The inference call `bl text chat --model` must use
-- the `deployed_model` from the create response — NOT the `model_name` you
-- passed to `deploy <modality> create`. Do not reuse the value across the two
-- commands.
+- NOTE: --model-name is the model being deployed (e.g. `qwen3-8b-ft-...`).
+- The create response also returns a `deployed_model` field — the deployment
+- instance id (e.g. `qwen3-8b-5ecb5f068d79`). Use that id for inference
+- (`bl text chat --model <deployed_model>`) and lifecycle commands
+- (`deploy get/scale/pause/resume/delete --deployed-model <id>`).
 
 #### Examples
 
 ```bash
-bl deploy image create --model my-wan-ft --name my-wan
+bl deploy image create --model-name my-wan-ft --display-name my-wan
 ```
 
 ```bash
-bl deploy image create --model my-wan-ft --name my-wan-mu --plan mu
+bl deploy image create --model-name my-wan-ft --display-name my-wan-mu --plan mu
 ```
 
 ```bash
-bl deploy image create --model my-wan-ft --name my-wan --dry-run
+bl deploy image create --model-name my-wan-ft --display-name my-wan --dry-run
 ```
 
 ### `bl deploy list`
@@ -263,6 +259,82 @@ bl deploy models --source custom --page-size 50
 bl deploy models --catalog-version v1.0 --output json
 ```
 
+### `bl deploy pause`
+
+| Field           | Value                                                       |
+| --------------- | ----------------------------------------------------------- |
+| **Name**        | `deploy pause`                                              |
+| **Description** | Pause a running model deployment (stops billing for mu/ptu) |
+| **Usage**       | `bl deploy pause --deployed-model <id> [--skip-precheck]`   |
+
+#### Flags
+
+| Flag                           | Type   | Required | Description                                              |
+| ------------------------------ | ------ | -------- | -------------------------------------------------------- |
+| `--deployed-model <id>`        | string | yes      | Deployed model identifier (required)                     |
+| `--skip-precheck`              | switch | no       | Skip the local RUNNING/PENDING status precheck           |
+| `--console-region <region>`    | string | no       | Console gateway region (e.g. cn-beijing, ap-southeast-1) |
+| `--console-site <site>`        | string | no       | Console site: domestic, international                    |
+| `--console-switch-agent <uid>` | number | no       | Switch agent UID for delegated access                    |
+| `--workspace-id <id>`          | string | no       | Workspace ID (env: BAILIAN_WORKSPACE_ID)                 |
+
+#### Notes
+
+- While paused, billing ceases for mu/ptu plans. Use `deploy resume` to bring it back online or `deploy delete` to remove.
+- Precheck verifies status is RUNNING/PENDING before issuing the pause; pass --skip-precheck to bypass.
+
+#### Examples
+
+```bash
+bl deploy pause --deployed-model dep-...
+```
+
+```bash
+bl deploy pause --deployed-model dep-... --skip-precheck
+```
+
+```bash
+bl deploy pause --deployed-model dep-... --dry-run
+```
+
+### `bl deploy resume`
+
+| Field           | Value                                                         |
+| --------------- | ------------------------------------------------------------- |
+| **Name**        | `deploy resume`                                               |
+| **Description** | Resume a paused model deployment (brings service back online) |
+| **Usage**       | `bl deploy resume --deployed-model <id> [--skip-precheck]`    |
+
+#### Flags
+
+| Flag                           | Type   | Required | Description                                              |
+| ------------------------------ | ------ | -------- | -------------------------------------------------------- |
+| `--deployed-model <id>`        | string | yes      | Deployed model identifier (required)                     |
+| `--skip-precheck`              | switch | no       | Skip the local STOPPED status precheck                   |
+| `--console-region <region>`    | string | no       | Console gateway region (e.g. cn-beijing, ap-southeast-1) |
+| `--console-site <site>`        | string | no       | Console site: domestic, international                    |
+| `--console-switch-agent <uid>` | number | no       | Switch agent UID for delegated access                    |
+| `--workspace-id <id>`          | string | no       | Workspace ID (env: BAILIAN_WORKSPACE_ID)                 |
+
+#### Notes
+
+- Precheck verifies status is STOPPED before issuing the resume; pass --skip-precheck to bypass.
+- For mu/ptu plans, billing resumes once the service is back online.
+
+#### Examples
+
+```bash
+bl deploy resume --deployed-model dep-...
+```
+
+```bash
+bl deploy resume --deployed-model dep-... --skip-precheck
+```
+
+```bash
+bl deploy resume --deployed-model dep-... --dry-run
+```
+
 ### `bl deploy scale`
 
 | Field           | Value                                                                                       |
@@ -294,27 +366,27 @@ bl deploy scale --deployed-model dep-... --capacity 2
 
 ### `bl deploy text create`
 
-| Field           | Value                                                                                                                                                                                                            |
-| --------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **Name**        | `deploy text create`                                                                                                                                                                                             |
-| **Description** | Create a text model deployment                                                                                                                                                                                   |
-| **Usage**       | `bl deploy text create --model <model_name> --name <display_name> [--plan <plan>] [--deploy-spec <id>] [--capacity <n>] [--billing-method <m>] [--input-tpm <n>] [--output-tpm <n>] [--thinking-output-tpm <n>]` |
+| Field           | Value                                                                                                                                                                                                                         |
+| --------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| **Name**        | `deploy text create`                                                                                                                                                                                                          |
+| **Description** | Create a text model deployment                                                                                                                                                                                                |
+| **Usage**       | `bl deploy text create --model-name <model_name> --display-name <display_name> [--plan <plan>] [--deploy-spec <id>] [--capacity <n>] [--billing-method <m>] [--input-tpm <n>] [--output-tpm <n>] [--thinking-output-tpm <n>]` |
 
 #### Flags
 
-| Flag                        | Type   | Required | Description                                                                     |
-| --------------------------- | ------ | -------- | ------------------------------------------------------------------------------- |
-| `--model <name>`            | string | yes      | Model name (catalog model or fine-tuned output) (required)                      |
-| `--name <display_name>`     | string | yes      | Console display name for the deployment (required)                              |
-| `--plan <plan>`             | string | no       | Billing plan: lora (default, Token-billed) \| ptu (Token-billed) \| mu          |
-| `--deploy-spec <id>`        | string | no       | Deploy spec (only used by plan=mu; auto-picked if omitted)                      |
-| `--capacity <n>`            | number | no       | Resource units (plan=mu only; required by API; defaults to the template's unit) |
-| `--billing-method <m>`      | string | no       | Billing method (plan=mu only; default "POST_PAY", the only supported value)     |
-| `--input-tpm <n>`           | number | no       | PTU max input tokens/min (required for plan=ptu)                                |
-| `--output-tpm <n>`          | number | no       | PTU max output tokens/min (required for plan=ptu)                               |
-| `--thinking-output-tpm <n>` | number | no       | PTU max thinking-output tokens/min (optional, some models)                      |
-| `--api-key <key>`           | string | no       | API key                                                                         |
-| `--base-url <url>`          | string | no       | API base URL                                                                    |
+| Flag                            | Type   | Required | Description                                                                     |
+| ------------------------------- | ------ | -------- | ------------------------------------------------------------------------------- |
+| `--model-name <model_name>`     | string | yes      | Model to deploy — fine-tuned output name or catalog model (required)            |
+| `--display-name <display_name>` | string | yes      | Console display name for the deployment (required)                              |
+| `--plan <plan>`                 | string | no       | Billing plan: lora (default, Token-billed) \| ptu (Token-billed) \| mu          |
+| `--deploy-spec <id>`            | string | no       | Deploy spec (only used by plan=mu; auto-picked if omitted)                      |
+| `--capacity <n>`                | number | no       | Resource units (plan=mu only; required by API; defaults to the template's unit) |
+| `--billing-method <m>`          | string | no       | Billing method (plan=mu only; default "POST_PAY", the only supported value)     |
+| `--input-tpm <n>`               | number | no       | PTU max input tokens/min (required for plan=ptu)                                |
+| `--output-tpm <n>`              | number | no       | PTU max output tokens/min (required for plan=ptu)                               |
+| `--thinking-output-tpm <n>`     | number | no       | PTU max thinking-output tokens/min (optional, some models)                      |
+| `--api-key <key>`               | string | no       | API key                                                                         |
+| `--base-url <url>`              | string | no       | API base URL                                                                    |
 
 #### Notes
 
@@ -329,31 +401,28 @@ bl deploy scale --deployed-model dep-... --capacity 2
 - Use `bl deploy models --source base` to inspect available templates.
 - After creation, status starts at PENDING and transitions to RUNNING.
 - Invoke the deployed model with: bl text chat --model <deployed_model>
-- WARNING: --model is overloaded across commands and refers to DIFFERENT
-- values. `bl deploy <modality> create --model` takes the exported model_name
-- (e.g. `qwen3-8b-ft-...`), but the create response also returns a
-- `deployed_model` field (the deployment instance id, e.g.
-- `qwen3-8b-5ecb5f068d79`). The inference call `bl text chat --model` must use
-- the `deployed_model` from the create response — NOT the `model_name` you
-- passed to `deploy <modality> create`. Do not reuse the value across the two
-- commands.
+- NOTE: --model-name is the model being deployed (e.g. `qwen3-8b-ft-...`).
+- The create response also returns a `deployed_model` field — the deployment
+- instance id (e.g. `qwen3-8b-5ecb5f068d79`). Use that id for inference
+- (`bl text chat --model <deployed_model>`) and lifecycle commands
+- (`deploy get/scale/pause/resume/delete --deployed-model <id>`).
 
 #### Examples
 
 ```bash
-bl deploy text create --model my-qwen-sft --name my-sft-test
+bl deploy text create --model-name my-qwen-sft --display-name my-sft-test
 ```
 
 ```bash
-bl deploy text create --model qwen3.6-flash-2026-04-16 --name my-flash --plan ptu --input-tpm 10000 --output-tpm 1000
+bl deploy text create --model-name qwen3.6-flash-2026-04-16 --display-name my-flash --plan ptu --input-tpm 10000 --output-tpm 1000
 ```
 
 ```bash
-bl deploy text create --model qwen3-8b --name my-qwen3-mu --plan mu
+bl deploy text create --model-name qwen3-8b --display-name my-qwen3-mu --plan mu
 ```
 
 ```bash
-bl deploy text create --model qwen3-8b --name my-qwen3 --plan mu --deploy-spec MU1 --capacity 2
+bl deploy text create --model-name qwen3-8b --display-name my-qwen3 --plan mu --deploy-spec MU1 --capacity 2
 ```
 
 ### `bl deploy update`

skills/bailian-finetune/reference/finetune.md

@@ -19,24 +19,26 @@ Index: [index.md](index.md)
 | `bl finetune image create` | Create an image generation model fine-tune job (sft-lora)                                                                       |
 | `bl finetune list`         | List fine-tune jobs                                                                                                             |
 | `bl finetune logs`         | Fetch training logs for a fine-tune job                                                                                         |
+| `bl finetune price`        | Estimate the training cost for a fine-tune job (token billing)                                                                  |
 | `bl finetune text create`  | Create a text model fine-tune job (sft \| sft-lora \| dpo \| dpo-lora \| cpt)                                                   |
+| `bl finetune video create` | Create a video generation model fine-tune job (Wan i2v/kf2v, efficient_sft)                                                     |
 | `bl finetune watch`        | Probe a fine-tune job's status (default: single non-blocking fetch). Pass --follow to poll until terminal.                      |
 
 ## Command details
 
 ### `bl finetune audio create`
 
-| Field           | Value                                                                                                                               |
-| --------------- | ----------------------------------------------------------------------------------------------------------------------------------- |
-| **Name**        | `finetune audio create`                                                                                                             |
-| **Description** | Create an audio TTS model fine-tune job (sft-lora)                                                                                  |
-| **Usage**       | `bl finetune audio create --model <model> --datasets <id\|path> [--validations <id\|path>] [--model-name <name>] [--suffix <text>]` |
+| Field           | Value                                                                                                                                    |
+| --------------- | ---------------------------------------------------------------------------------------------------------------------------------------- |
+| **Name**        | `finetune audio create`                                                                                                                  |
+| **Description** | Create an audio TTS model fine-tune job (sft-lora)                                                                                       |
+| **Usage**       | `bl finetune audio create --base-model <model> --datasets <id\|path> [--validations <id\|path>] [--model-name <name>] [--suffix <text>]` |
 
 #### Flags
 
 | Flag                         | Type   | Required | Description                                                                                                                                                        |
 | ---------------------------- | ------ | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| `--model <model>`            | string | yes      | Base model to fine-tune                                                                                                                                            |
+| `--base-model <model>`       | string | yes      | Base model to fine-tune (e.g. qwen3-8b; not the output model name)                                                                                                 |
 | `--datasets <ids\|paths>`    | string | yes      | Comma-separated dataset file IDs or local paths (.jsonl for text, .zip for audio/image). Local paths are uploaded (validated) first, then their file-ids are used. |
 | `--validations <ids\|paths>` | string | no       | Comma-separated validation dataset file IDs or local paths (auto-uploaded like --datasets).                                                                        |
 | `--model-name <name>`        | string | no       | Output model name (after training)                                                                                                                                 |
@@ -58,23 +60,23 @@ Index: [index.md](index.md)
 #### Examples
 
 ```bash
-bl finetune audio create --model cosyvoice-v3-flash --datasets ./audio.zip
+bl finetune audio create --base-model cosyvoice-v3-flash --datasets ./audio.zip
 ```
 
 ```bash
-bl finetune audio create --model cosyvoice-v3-flash --datasets file-xxx
+bl finetune audio create --base-model cosyvoice-v3-flash --datasets file-xxx
 ```
 
 ```bash
-bl finetune audio create --model cosyvoice-v3-flash --datasets ./audio.zip --model-name my-tts
+bl finetune audio create --base-model cosyvoice-v3-flash --datasets ./audio.zip --model-name my-tts
 ```
 
 ```bash
-bl finetune audio create --model cosyvoice-v3-flash --datasets file-xxx --output json
+bl finetune audio create --base-model cosyvoice-v3-flash --datasets file-xxx --output json
 ```
 
 ```bash
-bl finetune audio create --model cosyvoice-v3-flash --datasets ./audio.zip --dry-run
+bl finetune audio create --base-model cosyvoice-v3-flash --datasets ./audio.zip --dry-run
 ```
 
 ### `bl finetune cancel`
@@ -114,18 +116,18 @@ bl finetune cancel --job-id ft-xxx --dry-run
 | --------------- | ------------------------------------------------------------------------------------------------------------------------------- |
 | **Name**        | `finetune capability`                                                                                                           |
 | **Description** | Query fine-tune training capability — by model (which training types it supports) or by training type (which models support it) |
-| **Usage**       | `bl finetune capability --model <m> \| --training-type <t>`                                                                     |
+| **Usage**       | `bl finetune capability --base-model <m> \| --training-type <t>`                                                                |
 
 #### Flags
 
 | Flag                  | Type   | Required | Description                                                                           |
 | --------------------- | ------ | -------- | ------------------------------------------------------------------------------------- |
-| `--model <m>`         | string | no       | List training types supported by this base model.                                     |
+| `--base-model <m>`    | string | no       | List training types supported by this base model.                                     |
 | `--training-type <t>` | string | no       | List models supporting this training type: sft \| sft-lora \| dpo \| dpo-lora \| cpt. |
 
 #### Notes
 
-- Exactly one of --model / --training-type is required.
+- Exactly one of --base-model / --training-type is required.
 - Training-type values use the `<method>` / `<method>-lora` convention:
 - sft | sft-lora | dpo | dpo-lora | cpt. (cpt has no -lora variant server-side.)
 - Queries listFoundationModels, a public API — no console login needed.
@@ -133,7 +135,7 @@ bl finetune cancel --job-id ft-xxx --dry-run
 #### Examples
 
 ```bash
-bl finetune capability --model qwen3-8b
+bl finetune capability --base-model qwen3-8b
 ```
 
 ```bash
@@ -166,8 +168,8 @@ bl finetune capability --training-type sft --quiet
 
 #### Notes
 
-- Use the returned `checkpoint` value with `finetune export` to publish
-- a deployable model.
+- `model_name` (shown for SUCCEEDED checkpoints) is the direct input for `deploy create --model-name`.
+- Checkpoints expire ~15 days after creation; `expire_time` shows the deadline. Export or deploy before expiry.
 
 #### Examples
 
@@ -268,17 +270,17 @@ bl finetune get --job-id ft-xxx --output json
 
 ### `bl finetune image create`
 
-| Field           | Value                                                                                                                                                                                      |
-| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| **Name**        | `finetune image create`                                                                                                                                                                    |
-| **Description** | Create an image generation model fine-tune job (sft-lora)                                                                                                                                  |
-| **Usage**       | `bl finetune image create --model <model> --datasets <id\|path> [--validations <id\|path>] [--model-name <name>] [--suffix <text>] [--generation-type <t2i\|i2i>] [--learning-rate <str>]` |
+| Field           | Value                                                                                                                                                                                           |
+| --------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| **Name**        | `finetune image create`                                                                                                                                                                         |
+| **Description** | Create an image generation model fine-tune job (sft-lora)                                                                                                                                       |
+| **Usage**       | `bl finetune image create --base-model <model> --datasets <id\|path> [--validations <id\|path>] [--model-name <name>] [--suffix <text>] [--generation-type <t2i\|i2i>] [--learning-rate <str>]` |
 
 #### Flags
 
 | Flag                           | Type   | Required | Description                                                                                                                                                         |
 | ------------------------------ | ------ | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `--model <model>`              | string | yes      | Base model to fine-tune                                                                                                                                             |
+| `--base-model <model>`         | string | yes      | Base model to fine-tune (e.g. qwen3-8b; not the output model name)                                                                                                  |
 | `--datasets <ids\|paths>`      | string | yes      | Comma-separated dataset file IDs or local paths (.jsonl for text, .zip for audio/image). Local paths are uploaded (validated) first, then their file-ids are used.  |
 | `--validations <ids\|paths>`   | string | no       | Comma-separated validation dataset file IDs or local paths (auto-uploaded like --datasets).                                                                         |
 | `--model-name <name>`          | string | no       | Output model name (after training)                                                                                                                                  |
@@ -304,46 +306,47 @@ bl finetune get --job-id ft-xxx --output json
 #### Examples
 
 ```bash
-bl finetune image create --model wan2.7-image-pro --datasets ./images.zip
+bl finetune image create --base-model wan2.7-image-pro --datasets ./images.zip
 ```
 
 ```bash
-bl finetune image create --model wan2.7-image-pro --datasets file-xxx
+bl finetune image create --base-model wan2.7-image-pro --datasets file-xxx
 ```
 
 ```bash
-bl finetune image create --model wan2.7-image-pro --datasets file-xxx --generation-type i2i
+bl finetune image create --base-model wan2.7-image-pro --datasets file-xxx --generation-type i2i
 ```
 
 ```bash
-bl finetune image create --model wan2.7-image-pro --datasets ./images.zip --model-name my-wan
+bl finetune image create --base-model wan2.7-image-pro --datasets ./images.zip --model-name my-wan
 ```
 
 ```bash
-bl finetune image create --model wan2.7-image-pro --datasets file-xxx --output json
+bl finetune image create --base-model wan2.7-image-pro --datasets file-xxx --output json
 ```
 
 ```bash
-bl finetune image create --model wan2.7-image-pro --datasets ./images.zip --dry-run
+bl finetune image create --base-model wan2.7-image-pro --datasets ./images.zip --dry-run
 ```
 
 ### `bl finetune list`
 
-| Field           | Value                                                            |
-| --------------- | ---------------------------------------------------------------- |
-| **Name**        | `finetune list`                                                  |
-| **Description** | List fine-tune jobs                                              |
-| **Usage**       | `bl finetune list [--page <n>] [--page-size <n>] [--status <s>]` |
+| Field           | Value                                                                                   |
+| --------------- | --------------------------------------------------------------------------------------- |
+| **Name**        | `finetune list`                                                                         |
+| **Description** | List fine-tune jobs                                                                     |
+| **Usage**       | `bl finetune list [--page <n>] [--page-size <n>] [--status <s>] [--base-model <model>]` |
 
 #### Flags
 
-| Flag               | Type   | Required | Description                                                          |
-| ------------------ | ------ | -------- | -------------------------------------------------------------------- |
-| `--page <n>`       | number | no       | Page number (default: 1)                                             |
-| `--page-size <n>`  | number | no       | Results per page (default: 10, max 100)                              |
-| `--status <s>`     | string | no       | Filter by status (PENDING / RUNNING / SUCCEEDED / FAILED / CANCELED) |
-| `--api-key <key>`  | string | no       | API key                                                              |
-| `--base-url <url>` | string | no       | API base URL                                                         |
+| Flag                   | Type   | Required | Description                                                          |
+| ---------------------- | ------ | -------- | -------------------------------------------------------------------- |
+| `--page <n>`           | number | no       | Page number (default: 1)                                             |
+| `--page-size <n>`      | number | no       | Results per page (default: 10, max 100)                              |
+| `--status <s>`         | string | no       | Filter by status (PENDING / RUNNING / SUCCEEDED / FAILED / CANCELED) |
+| `--base-model <model>` | string | no       | Filter by base model ID (server-side)                                |
+| `--api-key <key>`      | string | no       | API key                                                              |
+| `--base-url <url>`     | string | no       | API base URL                                                         |
 
 #### Examples
 
@@ -356,7 +359,11 @@ bl finetune list --status RUNNING
 ```
 
 ```bash
-bl finetune list --page-size 20 --output json
+bl finetune list --base-model qwen3-8b
+```
+
+```bash
+bl finetune list --page-size 20
 ```
 
 ### `bl finetune logs`
@@ -405,19 +412,60 @@ bl finetune logs --job-id ft-xxx --tail 20
 bl finetune logs --job-id ft-xxx --search checkpoint --tail 5
 ```
 
+### `bl finetune price`
+
+| Field           | Value                                                                                               |
+| --------------- | --------------------------------------------------------------------------------------------------- |
+| **Name**        | `finetune price`                                                                                    |
+| **Description** | Estimate the training cost for a fine-tune job (token billing)                                      |
+| **Usage**       | `bl finetune price --base-model <model> --datasets <ids> [--training-type <type>] [--n-epochs <n>]` |
+
+#### Flags
+
+| Flag                           | Type   | Required | Description                                                        |
+| ------------------------------ | ------ | -------- | ------------------------------------------------------------------ |
+| `--base-model <model>`         | string | yes      | Base model to fine-tune (e.g. qwen3-8b; not the output model name) |
+| `--datasets <ids>`             | string | yes      | Training dataset file IDs, comma-separated (required)              |
+| `--training-type <type>`       | string | no       | Training type: sft \| dpo \| cpt (default: sft)                    |
+| `--n-epochs <n>`               | number | no       | Number of training epochs (default: 3)                             |
+| `--console-region <region>`    | string | no       | Console gateway region (e.g. cn-beijing, ap-southeast-1)           |
+| `--console-site <site>`        | string | no       | Console site: domestic, international                              |
+| `--console-switch-agent <uid>` | number | no       | Switch agent UID for delegated access                              |
+| `--workspace-id <id>`          | string | no       | Workspace ID (env: BAILIAN_WORKSPACE_ID)                           |
+
+#### Notes
+
+- Estimate only — the server computes token usage from the datasets; final cost is subject to the bill.
+- Covers token billing for sft / dpo / cpt. Training-unit (MTU) billing is not supported by this command.
+- Hyper-parameters other than --n-epochs are fixed at representative defaults for estimation.
+
+#### Examples
+
+```bash
+bl finetune price --base-model qwen3-8b --datasets file-ft-xxx
+```
+
+```bash
+bl finetune price --base-model qwen3-8b --datasets file-ft-xxx,file-ft-yyy --n-epochs 2
+```
+
+```bash
+bl finetune price --base-model qwen3-8b --datasets file-ft-xxx --training-type cpt
+```
+
 ### `bl finetune text create`
 
-| Field           | Value                                                                                                                                                                                                                                                                           |
-| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **Name**        | `finetune text create`                                                                                                                                                                                                                                                          |
-| **Description** | Create a text model fine-tune job (sft \| sft-lora \| dpo \| dpo-lora \| cpt)                                                                                                                                                                                                   |
-| **Usage**       | `bl finetune text create --model <model> --datasets <id\|path,...> [--validations <id\|path,...>] [--model-name <name>] [--suffix <text>] [--n-epochs <n>] [--batch-size <n>] [--learning-rate <str>] [--max-length <n>] [--training-type <sft\|sft-lora\|dpo\|dpo-lora\|cpt>]` |
+| Field           | Value                                                                                                                                                                                                                                                                                |
+| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| **Name**        | `finetune text create`                                                                                                                                                                                                                                                               |
+| **Description** | Create a text model fine-tune job (sft \| sft-lora \| dpo \| dpo-lora \| cpt)                                                                                                                                                                                                        |
+| **Usage**       | `bl finetune text create --base-model <model> --datasets <id\|path,...> [--validations <id\|path,...>] [--model-name <name>] [--suffix <text>] [--n-epochs <n>] [--batch-size <n>] [--learning-rate <str>] [--max-length <n>] [--training-type <sft\|sft-lora\|dpo\|dpo-lora\|cpt>]` |
 
 #### Flags
 
 | Flag                         | Type   | Required | Description                                                                                                                                                                              |
 | ---------------------------- | ------ | -------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `--model <model>`            | string | yes      | Base model to fine-tune                                                                                                                                                                  |
+| `--base-model <model>`       | string | yes      | Base model to fine-tune (e.g. qwen3-8b; not the output model name)                                                                                                                       |
 | `--datasets <ids\|paths>`    | string | yes      | Comma-separated dataset file IDs or local paths (.jsonl for text, .zip for audio/image). Local paths are uploaded (validated) first, then their file-ids are used.                       |
 | `--validations <ids\|paths>` | string | no       | Comma-separated validation dataset file IDs or local paths (auto-uploaded like --datasets).                                                                                              |
 | `--model-name <name>`        | string | no       | Output model name (after training)                                                                                                                                                       |
@@ -453,35 +501,89 @@ bl finetune logs --job-id ft-xxx --search checkpoint --tail 5
 #### Examples
 
 ```bash
-bl finetune text create --model qwen3-8b --datasets file-xxx
+bl finetune text create --base-model qwen3-8b --datasets file-xxx
 ```
 
 ```bash
-bl finetune text create --model qwen3-8b --datasets ./train.jsonl
+bl finetune text create --base-model qwen3-8b --datasets ./train.jsonl
 ```
 
 ```bash
-bl finetune text create --model qwen3-8b --datasets ./train.jsonl --validations ./eval.jsonl
+bl finetune text create --base-model qwen3-8b --datasets ./train.jsonl --validations ./eval.jsonl
 ```
 
 ```bash
-bl finetune text create --model qwen3-8b --datasets file-aaa,./extra.jsonl
+bl finetune text create --base-model qwen3-8b --datasets file-aaa,./extra.jsonl
 ```
 
 ```bash
-bl finetune text create --model qwen3-8b --datasets ./train.jsonl --training-type sft
+bl finetune text create --base-model qwen3-8b --datasets ./train.jsonl --training-type sft
 ```
 
 ```bash
-bl finetune text create --model qwen3-8b --datasets file-xxx --learning-rate "1.6e-5" --n-epochs 4
+bl finetune text create --base-model qwen3-8b --datasets file-xxx --learning-rate "1.6e-5" --n-epochs 4
 ```
 
 ```bash
-bl finetune text create --model qwen3-8b --datasets file-xxx --output json
+bl finetune text create --base-model qwen3-8b --datasets file-xxx --output json
 ```
 
 ```bash
-bl finetune text create --model qwen3-8b --datasets file-xxx --dry-run
+bl finetune text create --base-model qwen3-8b --datasets file-xxx --dry-run
+```
+
+### `bl finetune video create`
+
+| Field           | Value                                                                                                                                                                                                |
+| --------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| **Name**        | `finetune video create`                                                                                                                                                                              |
+| **Description** | Create a video generation model fine-tune job (Wan i2v/kf2v, efficient_sft)                                                                                                                          |
+| **Usage**       | `bl finetune video create --base-model <model> --datasets <id\|path> [--validations <id\|path>] [--model-name <name>] [--suffix <text>] [--n-epochs <n>] [--batch-size <n>] [--learning-rate <str>]` |
+
+#### Flags
+
+| Flag                         | Type   | Required | Description                                                                                                                                                        |
+| ---------------------------- | ------ | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| `--base-model <model>`       | string | yes      | Base model to fine-tune (e.g. qwen3-8b; not the output model name)                                                                                                 |
+| `--datasets <ids\|paths>`    | string | yes      | Comma-separated dataset file IDs or local paths (.jsonl for text, .zip for audio/image). Local paths are uploaded (validated) first, then their file-ids are used. |
+| `--validations <ids\|paths>` | string | no       | Comma-separated validation dataset file IDs or local paths (auto-uploaded like --datasets).                                                                        |
+| `--model-name <name>`        | string | no       | Output model name (after training)                                                                                                                                 |
+| `--suffix <text>`            | string | no       | Output suffix appended by the platform (finetuned_output_suffix)                                                                                                   |
+| `--n-epochs <n>`             | number | no       | Training epochs (default: 50)                                                                                                                                      |
+| `--batch-size <n>`           | number | no       | Batch size (default: model-specific, 1 for wan2.7, 4 for wan2.5/2.2)                                                                                               |
+| `--learning-rate <str>`      | string | no       | Learning rate as a string to preserve precision (default: "2e-5")                                                                                                  |
+| `--api-key <key>`            | string | no       | API key                                                                                                                                                            |
+| `--base-url <url>`           | string | no       | API base URL                                                                                                                                                       |
+
+#### Notes
+
+- Creating a job uploads any local datasets and consumes training quota.
+- Use --dry-run to preview the request body without submitting.
+- --datasets / --validations accept either file-ids (from `dataset upload`)
+- or local paths. Local paths are validated and uploaded first, then their
+- file-ids are submitted — a one-step upload-and-train.
+- Video generation training (Wan i2v/kf2v) runs efficient_sft with model-
+- specific defaults: wan2.7 (batch_size=1, max_pixels=102400), wan2.5/2.2
+- (batch_size=4, max_pixels per model). Override with --batch-size/--n-epochs.
+- Datasets are .zip archives with data.jsonl + frame images + videos.
+- Recommended: ≥10 training samples, 20-100 for stable results.
+
+#### Examples
+
+```bash
+bl finetune video create --base-model wan2.7-i2v --datasets file-xxx
+```
+
+```bash
+bl finetune video create --base-model wan2.7-i2v --datasets ./i2v-data.zip
+```
+
+```bash
+bl finetune video create --base-model wan2.2-kf2v-flash --datasets file-xxx --n-epochs 100
+```
+
+```bash
+bl finetune video create --base-model wan2.7-i2v --datasets file-xxx --dry-run
 ```
 
 ### `bl finetune watch`

skills/bailian-finetune/reference/index.md

@@ -22,6 +22,8 @@ Use this index for the skill-scoped quick index and global flags.
 | `bl deploy image create`   | Create an image generation model deployment                                                                                     | [deploy.md](deploy.md)     |
 | `bl deploy list`           | List model deployments                                                                                                          | [deploy.md](deploy.md)     |
 | `bl deploy models`         | List models available for deployment                                                                                            | [deploy.md](deploy.md)     |
+| `bl deploy pause`          | Pause a running model deployment (stops billing for mu/ptu)                                                                     | [deploy.md](deploy.md)     |
+| `bl deploy resume`         | Resume a paused model deployment (brings service back online)                                                                   | [deploy.md](deploy.md)     |
 | `bl deploy scale`          | Scale a deployment's capacity                                                                                                   | [deploy.md](deploy.md)     |
 | `bl deploy text create`    | Create a text model deployment                                                                                                  | [deploy.md](deploy.md)     |
 | `bl deploy update`         | Update a deployment's rate limits (rpm_limit / tpm_limit)                                                                       | [deploy.md](deploy.md)     |
@@ -35,16 +37,18 @@ Use this index for the skill-scoped quick index and global flags.
 | `bl finetune image create` | Create an image generation model fine-tune job (sft-lora)                                                                       | [finetune.md](finetune.md) |
 | `bl finetune list`         | List fine-tune jobs                                                                                                             | [finetune.md](finetune.md) |
 | `bl finetune logs`         | Fetch training logs for a fine-tune job                                                                                         | [finetune.md](finetune.md) |
+| `bl finetune price`        | Estimate the training cost for a fine-tune job (token billing)                                                                  | [finetune.md](finetune.md) |
 | `bl finetune text create`  | Create a text model fine-tune job (sft \| sft-lora \| dpo \| dpo-lora \| cpt)                                                   | [finetune.md](finetune.md) |
+| `bl finetune video create` | Create a video generation model fine-tune job (Wan i2v/kf2v, efficient_sft)                                                     | [finetune.md](finetune.md) |
 | `bl finetune watch`        | Probe a fine-tune job's status (default: single non-blocking fetch). Pass --follow to poll until terminal.                      | [finetune.md](finetune.md) |
 
 ## By group
 
-| Group      | Commands                                                                                                                                 | Reference                  |
-| ---------- | ---------------------------------------------------------------------------------------------------------------------------------------- | -------------------------- |
-| `dataset`  | `delete`, `get`, `list`, `upload`, `validate`                                                                                            | [dataset.md](dataset.md)   |
-| `deploy`   | `audio create`, `delete`, `get`, `image create`, `list`, `models`, `scale`, `text create`, `update`                                      | [deploy.md](deploy.md)     |
-| `finetune` | `audio create`, `cancel`, `capability`, `checkpoints`, `delete`, `export`, `get`, `image create`, `list`, `logs`, `text create`, `watch` | [finetune.md](finetune.md) |
+| Group      | Commands                                                                                                                                                          | Reference                  |
+| ---------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------- |
+| `dataset`  | `delete`, `get`, `list`, `upload`, `validate`                                                                                                                     | [dataset.md](dataset.md)   |
+| `deploy`   | `audio create`, `delete`, `get`, `image create`, `list`, `models`, `pause`, `resume`, `scale`, `text create`, `update`                                            | [deploy.md](deploy.md)     |
+| `finetune` | `audio create`, `cancel`, `capability`, `checkpoints`, `delete`, `export`, `get`, `image create`, `list`, `logs`, `price`, `text create`, `video create`, `watch` | [finetune.md](finetune.md) |
 
 ## Global flags
 

skills/bailian-gen/reference/video.md

@@ -108,6 +108,7 @@ bl video edit --video https://example.com/input.mp4 --prompt "Put clothes on the
 | `--model <model>`           | string  | no       | Model ID (default: happyhorse-1.1-t2v, or happyhorse-1.1-i2v with --image)              |
 | `--prompt <text>`           | string  | yes      | Video description                                                                       |
 | `--image <url>`             | string  | no       | Input image URL for image-to-video generation                                           |
+| `--last-frame <url>`        | string  | no       | Last frame image URL (with --image, enables kf2v first+last frame mode)                 |
 | `--negative-prompt <text>`  | string  | no       | Negative prompt to exclude unwanted content                                             |
 | `--resolution <res>`        | string  | no       | Resolution: 720P or 1080P (default: 1080P)                                              |
 | `--ratio <ratio>`           | string  | no       | Aspect ratio (e.g. 16:9, 9:16, 1:1)                                                     |