skills/modelstudioai__cli
1
0
Fork 0
mirror of https://github.com/modelstudioai/cli.git synced 2026-09-14 19:49:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(deploy): add pause/resume commands; JSON-only output for dataset/finetune/deploy

Browse Source 
- Add `bl deploy pause` and `bl deploy resume` (console domain, first
  console-auth commands in deploy group) via modelInstance start/stop APIs
- Add core deploy/lifecycle.ts with input-wrapped console gateway calls
- Switch all dataset/finetune/deploy commands to JSON-only output, removing
  text formatting logic
- Expose usage/charge_type in finetune get, model_name/expire_time in
  finetune checkpoints with near-expiry warning
- Update deploy delete hint to suggest `bl deploy pause`
This commit is contained in:
故璃
2026-08-06 11:34:48 +08:00
parent 262681484b
commit a7245c0f62
31 changed files with 584 additions and 571 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/cli/src/commands.ts
+4
View File
@@ -80,6 +80,8 @@ import {
deployScale,
deployUpdate,
deployDelete,
deployPause,
deployResume,
tokenPlanListSeats,
tokenPlanCreateKey,
tokenPlanAssignSeats,
@@ -198,6 +200,8 @@ 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
+6 -8
View File
@@ -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
+7 -17
View File
@@ -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
+7 -19
View File
@@ -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
+3 -8
View File
@@ -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
+3 -39
View File
@@ -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
+3 -14
View File
@@ -1,6 +1,5 @@
import {
defineCommand,
detectOutputFormat,
createDeployment,
pickPlanStrategy,
STRATEGIES,
@@ -11,7 +10,7 @@ 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: {
@@ -122,7 +121,6 @@ async function runCreate(
const model = flags.model as string;
const name = flags.name 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 +144,7 @@ async function runCreate(
};
if (settings.dryRun) {
emitResult({ action: "deploy.create", body }, format);
emitResult({ action: "deploy.create", body }, "json");
return;
}
@@ -155,17 +153,8 @@ 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");
}
}
packages/commands/src/commands/deploy/delete.ts
+5 -9
View File
@@ -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
+5 -18
View File
@@ -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
+4 -31
View File
@@ -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
+49 -102
View File
@@ -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
+85
View File
@@ -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
+84
View File
@@ -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 ${status}. Only STOPPED deployments can be resumed. ` +
`Pass --skip-precheck to attempt the resume anyway.`,
ExitCode.USAGE,
);
}
}
// If entry not found in list, proceed — the server will surface the real error.
} catch (error) {
if (error instanceof BailianError) throw error;
// If the list call itself failed, proceed and let the API call surface the error.
}
}
const response = await startModelService(ctx.client, deployedModel);
if (settings.quiet) {
emitBare(deployedModel);
} else {
emitResult({ deployed_model: deployedModel, action: "resume", ...response }, "json");
}
},
});
packages/commands/src/commands/deploy/scale.ts
+4 -15
View File
@@ -1,10 +1,5 @@
import {
defineCommand,
detectOutputFormat,
scaleDeployment,
type FlagsDef,
} from "bailian-cli-core";
import { emitResult, emitBare, emitRequestId } from "bailian-cli-runtime";
import { defineCommand, scaleDeployment, type FlagsDef } from "bailian-cli-core";
import { emitResult, emitBare } from "bailian-cli-runtime";
const SCALE_FLAGS = {
deployedModel: {
@@ -52,7 +47,6 @@ export default defineCommand({
async run(ctx) {
const { settings, flags } = ctx;
const deployedModel = flags.deployedModel;
const format = detectOutputFormat(settings.output);
const body: Record<string, unknown> = {};
if (flags.capacity !== undefined) body.capacity = flags.capacity;
@@ -60,21 +54,16 @@ export default defineCommand({
if (flags.outputTpm !== undefined) body.output_tpm = flags.outputTpm;
if (settings.dryRun) {
emitResult({ action: "deploy.scale", deployed_model: deployedModel, body }, format);
emitResult({ action: "deploy.scale", deployed_model: deployedModel, body }, "json");
return;
}
const response = await scaleDeployment(ctx.client, deployedModel, body);
const deployment = response.output ?? response.data;
if (settings.quiet) {
emitBare(deployedModel);
} else if (format === "text") {
const cap = deployment?.capacity !== undefined ? ` (capacity=${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
+4 -18
View File
@@ -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
+4 -10
View File
@@ -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
+21 -47
View File
@@ -1,6 +1,5 @@
import {
defineCommand,
detectOutputFormat,
fetchModelList,
fetchModelCapability,
listSupportedTrainingTypes,
@@ -43,17 +42,6 @@ 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} ${method.toUpperCase()}`;
}
const CAPABILITY_FLAGS = {
model: {
type: "string",
@@ -95,7 +83,6 @@ export default defineCommand({
const { settings, flags } = ctx;
const model = flags.model || undefined;
const trainingType = flags.trainingType || undefined;
const format = detectOutputFormat(settings.output);
if (settings.dryRun) {
emitResult(
@@ -104,7 +91,7 @@ export default defineCommand({
model,
training_type: trainingType,
},
format,
"json",
);
return;
}
@@ -113,7 +100,7 @@ export default defineCommand({
if (model) {
const capability = await fetchModelCapability(settings, model);
if (!capability) {
emitBare(`No foundation model found matching "${model}".`);
emitResult({ model, error: `No foundation model found matching "${model}".` }, "json");
return;
}
const supported = listSupportedTrainingTypes(capability);
@@ -121,23 +108,15 @@ export default defineCommand({
for (const value of supported) emitBare(value);
return;
}
if (format !== "text") {
emitResult(
{
model: capability.model ?? model,
supported,
supports: capability.supports,
trainingTypes: capability.trainingTypes,
},
format,
);
return;
}
emitBare(`${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 +141,15 @@ 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
+24 -24
View File
@@ -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`.",
"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
+3 -14
View File
@@ -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
@@ -606,8 +605,6 @@ 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 +614,7 @@ 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 +624,8 @@ 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");
}
}
packages/commands/src/commands/finetune/delete.ts
+4 -8
View File
@@ -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
+5 -17
View File
@@ -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/get.ts
+17 -33
View File
@@ -1,5 +1,5 @@
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";
const GET_FLAGS = {
jobId: {
@@ -17,12 +17,11 @@ 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;
}
@@ -30,16 +29,20 @@ 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 = {
job_id: job.job_id ?? jobId,
@@ -53,29 +56,10 @@ 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: typeof job.usage === "number" ? String(job.usage) : "",
charge_type: typeof job.charge_type === "string" ? job.charge_type : "",
};
if (format === "json") {
emitResult({ ...item, request_id: response.request_id }, format);
return;
}
// 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
+12 -44
View File
@@ -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)" },
@@ -22,14 +22,13 @@ export default defineCommand({
flags: LIST_FLAGS,
exampleArgs: ["", "--status RUNNING", "--page-size 20 --output json"],
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;
if (settings.dryRun) {
emitResult({ action: "finetune.list", page: pageNo, page_size: pageSize, status }, format);
emitResult({ action: "finetune.list", page: pageNo, page_size: pageSize, status }, "json");
return;
}
@@ -38,46 +37,15 @@ export default defineCommand({
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
+15 -44
View File
@@ -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: ${payload.total}`);
emitRequestId(response.request_id, settings.quiet);
} else {
emitResult(response, format);
}
emitResult(response, "json");
},
});
packages/commands/src/commands/finetune/watch.ts
+10 -18
View File
@@ -1,12 +1,11 @@
import {
defineCommand,
detectOutputFormat,
getFineTune,
BailianError,
ExitCode,
type FlagsDef,
} from "bailian-cli-core";
import { emitResult, emitBare, emitRequestId } from "bailian-cli-runtime";
import { emitResult, emitBare } from "bailian-cli-runtime";
const DEFAULT_INTERVAL_SEC = 10;
const MIN_INTERVAL_SEC = 1;
@@ -103,7 +102,6 @@ export default defineCommand({
const follow = flags.follow;
const intervalSec = Math.max(MIN_INTERVAL_SEC, flags.interval ?? DEFAULT_INTERVAL_SEC);
const pollTimeoutSec = flags.pollTimeout;
const format = detectOutputFormat(settings.output);
if (settings.dryRun) {
emitResult(
@@ -114,7 +112,7 @@ export default defineCommand({
interval: intervalSec,
timeout: pollTimeoutSec,
},
format,
"json",
);
return;
}
@@ -132,15 +130,10 @@ export default defineCommand({
if (settings.quiet) {
// Just the status word — ideal for `status=$(... finetune watch ... --quiet)`.
emitBare(status || "UNKNOWN");
} else if (format === "text") {
emitBare(`${nowStamp()} ${jobId} ${status || "UNKNOWN"}`);
if (status === "SUCCEEDED") emitBare(`✓ ${jobId} ${status}`);
emitRequestId(response.request_id, settings.quiet);
} else {
// json: a compact, purpose-built status probe.
emitResult(
{ job_id: jobId, status: status || "UNKNOWN", terminal, request_id: response.request_id },
format,
"json",
);
}
@@ -168,18 +161,17 @@ export default defineCommand({
const job = response.output ?? response.data;
const status = String(job?.status ?? "").toUpperCase();
if (format === "text" && !settings.quiet && status !== lastStatus) {
emitBare(`${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 {
emitResult(response, "json");
}
if (status !== "SUCCEEDED") {
throw new BailianError(
@@ -205,7 +197,7 @@ 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/index.ts
+2
View File
@@ -87,6 +87,8 @@ 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/core/src/deploy/index.ts
+1
View File
@@ -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
+99
View File
@@ -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,
);
}
skills/bailian-finetune/reference/deploy.md
+89 -11
View File
@@ -7,17 +7,19 @@ 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
@@ -263,6 +265,82 @@ 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 |
skills/bailian-finetune/reference/finetune.md
+2 -2
View File
@@ -166,8 +166,8 @@ 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`.
- Checkpoints expire ~15 days after creation; `expire_time` shows the deadline. Export or deploy before expiry.
#### Examples
skills/bailian-finetune/reference/index.md
+3 -1
View File
@@ -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) |
@@ -43,7 +45,7 @@ Use this index for the skill-scoped quick index and global flags.
| 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) |
| `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`, `text create`, `watch` | [finetune.md](finetune.md) |
## Global flags