badgr-cli 1.1.1 → 1.1.2

package/LICENSE

@@ -0,0 +1,207 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship made available under
+      the License, as indicated by a copyright notice that is included in
+      or attached to the work (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean, as submitted to the Licensor for inclusion
+      in the Work by the copyright owner or by an individual or Legal Entity
+      authorized to submit on behalf of the copyright owner. For the purposes
+      of this definition, "submitted" means any form of electronic, verbal,
+      or written communication sent to the Licensor or its representatives,
+      including but not limited to communication on electronic mailing lists,
+      source code control systems, and issue tracking systems that are managed
+      by, or on behalf of, the Licensor for the purpose of discussing and
+      improving the Work, but excluding communication that is conspicuously
+      marked or designated in writing by the copyright owner as "Not a
+      Contribution."
+
+      "Contributor" shall mean Licensor and any Legal Entity on behalf of
+      whom a Contribution has been received by the Licensor and included
+      within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by the combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a cross-claim
+      or counterclaim in a lawsuit) alleging that the Work or any
+      Contribution embodied within the Work constitutes direct or
+      contributory patent infringement, then any patent licenses granted to
+      You under this License for that Work shall terminate as of the date
+      such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or Derivative
+          Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, You must include a readable copy of the
+          attribution notices contained within such NOTICE file, in
+          at least one of the following places: within a NOTICE text
+          file distributed as part of the Derivative Works; within
+          the Source form or documentation, if provided along with the
+          Derivative Works; or, within a display generated by the
+          Derivative Works, if and wherever such third-party notices
+          normally appear. The contents of the NOTICE file are for
+          informational purposes only and do not modify the License.
+          You may add Your own attribution notices within Derivative
+          Works that You distribute, alongside or as an addendum to
+          the NOTICE text from the Work, provided that such additional
+          attribution notices cannot be construed as modifying the License.
+
+      You may add Your own license statement for Your modifications and
+      may provide additional grant of rights to use, copy, modify, merge,
+      publish, distribute, sublicense, and/or sell copies of the Work,
+      and to permit persons to whom the Work is furnished to do so,
+      subject to the following conditions:
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or reproducing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or exemplary damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or all other
+      commercial damages or losses), even if such Contributor has been
+      advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may offer such
+      conditions only on Your own behalf and on Your sole responsibility,
+      not on behalf of any other Contributor, and only if You agree to
+      indemnify, defend, and hold each Contributor harmless for any
+      liability incurred by, or claims asserted against, such Contributor
+      by reason of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the format in use. Please also include a
+      "NOTICE" file as part of the distribution with the contents:
+
+         Copyright [yyyy] [name of copyright owner]
+
+         Licensed under the Apache License, Version 2.0 (the "License");
+         you may not use this file except in compliance with the License.
+         You may obtain a copy of the License at
+
+             http://www.apache.org/licenses/LICENSE-2.0
+
+         Unless required by applicable law or agreed to in writing, software
+         distributed under the License is distributed on an "AS IS" BASIS,
+         WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+         See the License for the specific language governing permissions and
+         limitations under the License.
+
+   Copyright 2024 AI Badgr
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

package/README.md

@@ -1,5 +1,10 @@
 # badgr-cli
 
+[![npm version](https://img.shields.io/npm/v/badgr-cli.svg)](https://www.npmjs.com/package/badgr-cli)
+[![npm downloads](https://img.shields.io/npm/dm/badgr-cli.svg)](https://www.npmjs.com/package/badgr-cli)
+[![license](https://img.shields.io/npm/l/badgr-cli.svg)](https://github.com/michaelmanly/badgr-cli/blob/main/LICENSE)
+[![node](https://img.shields.io/node/v/badgr-cli.svg)](https://www.npmjs.com/package/badgr-cli)
+
 Badgr supports many GPU workloads through two commands: `serve` for persistent endpoints, `run` for jobs.
 
 > **Safety promise:** every run has `--max-cost`, live logs, automatic teardown, and a receipt. Run `badgr down <id>` any time to stop billing immediately.
@@ -8,6 +13,8 @@ Badgr supports many GPU workloads through two commands: `serve` for persistent e
 npm install -g badgr-cli
 ```
 
+**Jump to:** [Quick start](#quick-start) · [Coding agents (`badgr launch`)](#coding--testing-agents-badgr-launch) · [Image generation](#also-try-image-generation) · [`badgr doctor`](#something-not-working-badgr-doctor) · [Commands](#commands) · [`serve` options](#badgr-serve-options) · [`run` options](#badgr-run-options) · [Receipts](#receipts) · [OpenAI compatibility](#openai-compatibility) · [GPU options](#gpu-options) · [Advanced](#advanced) · [Requirements](#requirements)
+
 ---
 
 ## Quick start
@@ -148,7 +155,7 @@ badgr doctor --json
 ```
 
 Run `badgr doctor --help` for the full flag list. Details in
-[`docs/gpu-doctor.md`](../../docs/gpu-doctor.md).
+[`docs/gpu-doctor.md`](https://github.com/michaelmanly/gpu-ai/blob/main/docs/gpu-doctor.md).
 
 ---
 
@@ -384,7 +391,7 @@ Badgr Auto selects the best eligible GPU for your workload. Add `--gpu <type>` o
 | A100 | NVIDIA A100 | 40–80 GB | Training, inference |
 | H100 | NVIDIA H100 | 80 GB | Large model training |
 
-Additional GPU types may be routable depending on current capacity — check with `badgr capacity`. Pricing is confirmed before provisioning; use `--dry-run` to see it first. Full GPU support details: see [NOTES.md](../../NOTES.md#gpu-support) in the repo root.
+Additional GPU types may be routable depending on current capacity — check with `badgr capacity`. Pricing is confirmed before provisioning; use `--dry-run` to see it first. Full GPU support details: see [NOTES.md](https://github.com/michaelmanly/gpu-ai/blob/main/NOTES.md#gpu-support).
 
 ---
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "badgr-cli",
-  "version": "1.1.1",
+  "version": "1.1.2",
   "description": "Badgr — run or serve GPU workloads from one command",
   "type": "module",
   "bin": {
@@ -24,6 +24,14 @@
   "engines": {
     "node": ">=20.10.0"
   },
+  "homepage": "https://aibadgr.com",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/michaelmanly/badgr-cli.git"
+  },
+  "bugs": {
+    "url": "https://github.com/michaelmanly/badgr-cli/issues"
+  },
   "keywords": [
     "gpu",
     "cli",
@@ -31,11 +39,45 @@
     "compute",
     "gateway",
     "openai",
+    "openai-compatible",
     "workload",
     "workspace",
     "llm",
     "inference",
-    "fine-tuning"
+    "fine-tuning",
+    "lora",
+    "vllm",
+    "gpu-cloud",
+    "cloud-gpu",
+    "gpu-rental",
+    "on-demand-gpu",
+    "serverless-gpu",
+    "gpu-provisioning",
+    "machine-learning",
+    "deep-learning",
+    "model-serving",
+    "model-training",
+    "training",
+    "huggingface",
+    "cuda",
+    "h100",
+    "a100",
+    "rtx-4090",
+    "coding-agent",
+    "ai-agent",
+    "claude-code",
+    "codex",
+    "playwright",
+    "comfyui",
+    "stable-diffusion",
+    "image-generation",
+    "transcription",
+    "whisper",
+    "embeddings",
+    "slurm",
+    "batch-jobs",
+    "devops",
+    "mlops"
   ],
   "license": "Apache-2.0"
 }

package/src/api.js

@@ -153,6 +153,22 @@ export function quoteRun(config, body) {
   });
 }
 
+// Live, no-provisioning price/capacity check for a GPU dry-run preview (see
+// backend run_serve_routes.py's GET /v1/capacity/suggestions). Used by every
+// GPU-provisioning command's --dry-run to show a real observed rate instead
+// of just the requested config — callers must treat a failure here as
+// non-fatal (best-effort) and never let it block or delay the dry-run.
+export function getCapacityPreview(config, { gpu, region, maxPrice } = {}) {
+  const params = new URLSearchParams({ gpu: gpu || 'RTX_4090' });
+  if (region) params.set('region', region);
+  if (maxPrice != null) params.set('max_price', String(maxPrice));
+  return callApi(`/capacity/suggestions?${params}`, {
+    apiKey: config.apiKey,
+    baseUrl: config.baseUrl,
+    timeoutMs: 8_000,
+  });
+}
+
 export function serveModel(config, body) {
   return callApi('/serve', {
     method: 'POST',

package/src/badgr.js

@@ -37,7 +37,7 @@ const HELP = `
 ${chalk.bold('badgr')} — run or serve GPU workloads from one command
 
 ${chalk.bold('COMMANDS')}
-  ${chalk.cyan('badgr login')}               Authenticate with your API key
+  ${chalk.cyan('badgr login')}               Open a browser to log in (or: badgr login --key <value>)
   ${chalk.cyan('badgr connect <provider>')}  Credential setup (badgr connect anthropic/openai) — also prompted inline by badgr launch if missing
   ${chalk.cyan('badgr detect <path>')}       Inspect a project and report the GPU job Badgr would run
   ${chalk.cyan('badgr run <command>')}       Run a one-off GPU job
@@ -265,7 +265,7 @@ async function main() {
   }
 
   switch (cmd) {
-    case 'login':    return loginCommand(chalk, saveConfig);
+    case 'login':    return loginCommand(chalk, saveConfig, rest);
     case 'connect':  return connectCommand(rest, chalk);
     case 'detect':   return detectCommand(config, rest, chalk);
     case 'run':      return runCommand(config, rest, chalk);

package/src/commands/batch.js

@@ -25,6 +25,7 @@ import { monitorBatchJob, fmtRuntime } from '../batch.js';
 import { runFanOut, DEFAULT_CONCURRENCY } from '../fanout.js';
 import { uploadBlob } from '../api.js';
 import { downloadAndExtractArtifact } from '../artifactDownload.js';
+import { printCapacityPreview, formatTierLabel } from '../progress.js';
 import { logsCommand } from './logs.js';
 
 // Server-side watchdog / batch.js reason strings, mapped to the vocabulary
@@ -240,17 +241,21 @@ async function runFanOutSubcommand(config, spec, flags, chalk, yamlPath) {
   const [{ containerPath }] = spec.inputs;
   const effectiveTier = normalizeTier(flags.tier);
   const concurrency = flags.maxConcurrency ?? DEFAULT_CONCURRENCY;
+  const resolvedGpu = flags.gpu ? flags.gpu.toUpperCase().replace(/-/g, '_') : 'AUTO';
 
   console.log(chalk.bold(`\n📦 Batch fan-out: ${spec.name}\n`));
   console.log(`  ${chalk.bold('Image:')}        ${spec.image}`);
   console.log(`  ${chalk.bold('Command:')}      ${spec.command.join(' ')}`);
   console.log(`  ${chalk.bold('Inputs dir:')}   ${fanOutDir} (${files.length} task(s), max ${Math.min(concurrency, files.length)} concurrent)`);
+  console.log(`  ${chalk.bold('GPU:')}          ${resolvedGpu}`);
+  console.log(`  ${chalk.bold('Tier:')}         ${formatTierLabel(effectiveTier)}`);
   console.log(`  ${chalk.bold('Max cost:')}     $${spec.maxCost.toFixed(2)} per task`);
   console.log(`  ${chalk.bold('Max runtime:')}  ${spec.maxRuntimeMinutes}min per task`);
   console.log();
 
   if (flags.dryRun) {
     console.log(chalk.bold(`⚡ Dry run — no GPU will be provisioned (${files.length} task(s) would be submitted)\n`));
+    await printCapacityPreview(chalk, config, { gpu: resolvedGpu, region: flags.region?.toUpperCase() });
     return;
   }
 
@@ -402,9 +407,14 @@ async function runSubcommand(config, args, chalk) {
     return runFanOutSubcommand(config, spec, flags, chalk, yamlPath);
   }
 
+  const resolvedGpu = flags.gpu ? flags.gpu.toUpperCase().replace(/-/g, '_') : 'AUTO';
+  const previewTier = normalizeTier(flags.tier);
+
   console.log(chalk.bold(`\n📦 Batch: ${spec.name}\n`));
   console.log(`  ${chalk.bold('Image:')}        ${spec.image}`);
   console.log(`  ${chalk.bold('Command:')}      ${spec.command.join(' ')}`);
+  console.log(`  ${chalk.bold('GPU:')}          ${resolvedGpu}`);
+  console.log(`  ${chalk.bold('Tier:')}         ${formatTierLabel(previewTier)}`);
   console.log(`  ${chalk.bold('Max cost:')}     $${spec.maxCost.toFixed(2)}`);
   console.log(`  ${chalk.bold('Max runtime:')}  ${spec.maxRuntimeMinutes}min`);
   if (spec.inputs.length)  console.log(`  ${chalk.bold('Inputs:')}       ${spec.inputs.length} path(s)`);
@@ -413,6 +423,7 @@ async function runSubcommand(config, args, chalk) {
 
   if (flags.dryRun) {
     console.log(chalk.bold('⚡ Dry run — no GPU will be provisioned\n'));
+    await printCapacityPreview(chalk, config, { gpu: resolvedGpu, region: flags.region?.toUpperCase() });
     return;
   }
 

package/src/commands/comfyui.js

@@ -7,12 +7,14 @@
  */
 import { readFileSync, existsSync } from 'fs';
 import { ensureBadgrReady } from '../onboarding.js';
+import { requireApiKey } from '../config.js';
 import { callApi, listDeployments } from '../api.js';
 import { addDeployment, addReceipt, updateReceipt, generateReceiptId } from '../store.js';
 import { normalizeTier, callWithFallback } from '../fallback.js';
 import { formatCliError } from '../errors.js';
 import { BLESSED_COMFY_WORKFLOWS } from '../catalog.js';
-import { pollJobUntilTerminal, renderJobClosingBlock, stage as _stage, stageDone as _stageDone, writeBlock as _writeBlock, clearBlock as _clearBlock, renderLiveBlock as _renderLiveBlock, printFailureClass as _printFailureClass } from '../progress.js';
+import { parseEnvFlag } from '../envFlag.js';
+import { pollJobUntilTerminal, renderJobClosingBlock, stage as _stage, stageDone as _stageDone, writeBlock as _writeBlock, clearBlock as _clearBlock, renderLiveBlock as _renderLiveBlock, printFailureClass as _printFailureClass, printCapacityPreview, formatTierLabel } from '../progress.js';
 
 const COMFYUI_IMAGE   = process.env.COMFYUI_IMAGE || 'yanwk/comfyui-boot:cu126-megapak';
 const HEALTH_PATH     = '/system_stats';
@@ -35,6 +37,7 @@ export function parseComfyuiArgs(args) {
     if (a === '--check-nodes') { flags.checkNodes = args[++i]; i++; continue; }
     if (a === '--persistent')  { flags.persistent = true; i++; continue; }
     if (a === '--yes' || a === '-y') { flags.yes = true; i++; continue; }
+    if (a === '--dry-run')     { flags.dryRun = true; i++; continue; }
     if (a === '--env') {
       const kv = args[++i]; i++;
       if (!flags.env) flags.env = [];
@@ -46,15 +49,6 @@ export function parseComfyuiArgs(args) {
   return { workflow: positional[0] || null, flags };
 }
 
-function parseEnvFlag(envList) {
-  const obj = {};
-  for (const kv of (envList || [])) {
-    const idx = kv.indexOf('=');
-    if (idx > 0) obj[kv.slice(0, idx)] = kv.slice(idx + 1);
-  }
-  return obj;
-}
-
 // Live block while ComfyUI comes up — same generic "Checking health" stage
 // line and status block as every other launch path (see serve.js's
 // waitForEndpoint), so ComfyUI doesn't read as a different UX than vLLM.
@@ -179,16 +173,20 @@ export async function comfyBatchCommand(config, args, chalk) {
 
   if (flags.dryRun) {
     const workflowSpec = BLESSED_COMFY_WORKFLOWS[flags.workflow];
+    const resolvedGpu = flags.gpuType || workflowSpec?.gpu_type;
     console.log(chalk.bold('\n⚡ Dry run — no GPU will be provisioned\n'));
     console.log(`  ${chalk.bold('Workflow:')}     ${flags.workflow}${workflowSpec ? '' : chalk.yellow(' (unknown — server will reject this)')}`);
     if (workflowSpec) {
-      console.log(`  ${chalk.bold('GPU:')}          ${flags.gpuType || workflowSpec.gpu_type}`);
+      console.log(`  ${chalk.bold('GPU:')}          ${resolvedGpu}`);
       console.log(`  ${chalk.dim(workflowSpec.description)}`);
     }
     console.log(`  ${chalk.bold('Prompts:')}      ${prompts.length}${prompts.length > 20 ? chalk.yellow(' (exceeds the 20-prompt limit — server will reject this)') : ''}`);
+    console.log(`  ${chalk.bold('Tier:')}         ${formatTierLabel(normalizeTier(flags.tier))}`);
     if (flags.maxCost)    console.log(`  ${chalk.bold('Max cost:')}     $${flags.maxCost}`);
     console.log(`  ${chalk.bold('Max runtime:')}  ${flags.maxRuntime ?? 60}min`);
-    console.log(chalk.dim('\n  Remove --dry-run to submit.\n'));
+    console.log();
+    if (resolvedGpu) await printCapacityPreview(chalk, config, { gpu: resolvedGpu });
+    console.log(chalk.dim('  Remove --dry-run to submit.\n'));
     return;
   }
 
@@ -282,9 +280,15 @@ export async function comfyuiCommand(config, args, chalk) {
     return;
   }
 
-  config = await ensureBadgrReady(config, chalk);
+  // A dry run previews the plan only and never provisions or spends anything,
+  // so it doesn't need the interactive browser login — just a stored key.
+  if (flags.dryRun) {
+    requireApiKey(config);
+  } else {
+    config = await ensureBadgrReady(config, chalk);
+  }
 
-  if (!flags.maxCost && !flags.persistent) {
+  if (!flags.maxCost && !flags.persistent && !flags.dryRun) {
     console.error(chalk.red('\n  ✗ ComfyUI endpoints bill continuously. Specify a spending limit:\n'));
     console.error(chalk.dim('    --max-cost 5           auto-stop when $5 is reached'));
     console.error(chalk.dim('    --persistent           run until you stop it manually\n'));
@@ -328,17 +332,29 @@ export async function comfyuiCommand(config, args, chalk) {
   const STAGE_TOTAL = 4;
   let stageN = 1;
 
-  console.log(chalk.bold('\n⚡ Running ComfyUI\n'));
+  console.log(chalk.bold(flags.dryRun
+    ? '\n⚡ Dry run — no GPU will be provisioned — ComfyUI\n'
+    : '\n⚡ Running ComfyUI\n'));
   console.log(`  ${chalk.bold('Workflow:')} ${workflow} (${nodeCount} nodes)`);
   console.log(`  ${chalk.bold('Image:')}    ${COMFYUI_IMAGE}`);
   console.log(`  ${chalk.bold('GPU:')}      ${gpu === 'AUTO' ? chalk.dim('auto (16+ GB VRAM)') : gpu}`);
+  if (flags.env?.length) console.log(`  ${chalk.bold('Env:')}      ${flags.env.join(', ')}`);
+  if (flags.dryRun) console.log(`  ${chalk.bold('Tier:')}     ${formatTierLabel(effectiveTier)}`);
   if (flags.maxCost) {
     console.log(`  ${chalk.bold('Max cost:')} $${flags.maxCost.toFixed(2)} (auto-stop)`);
+  } else if (flags.dryRun) {
+    console.log(`  ${chalk.bold('Max cost:')} ${chalk.dim('none')}`);
   } else {
     console.log(chalk.yellow('  ⚠  Persistent — billing until: badgr down <id>'));
   }
   console.log();
 
+  if (flags.dryRun) {
+    await printCapacityPreview(chalk, config, { gpu, region: flags.region?.toUpperCase(), maxPrice: flags.maxPrice });
+    console.log(chalk.dim('  Remove --dry-run to provision.\n'));
+    return;
+  }
+
   // Duplicate check
   if (config.apiKey) {
     try {

package/src/commands/embed.js

@@ -14,6 +14,8 @@ import { requireApiKey } from '../config.js';
 import { addReceipt, generateReceiptId } from '../store.js';
 import { normalizeTier, callWithFallback } from '../fallback.js';
 import { monitorBatchJob, fmtRuntime } from '../batch.js';
+import { parseEnvFlag } from '../envFlag.js';
+import { printCapacityPreview, formatTierLabel } from '../progress.js';
 
 const EMBED_IMAGE          = 'vllm/vllm-openai:latest';
 const DEFAULT_EMBED_MODEL  = 'BAAI/bge-large-en-v1.5';
@@ -35,6 +37,7 @@ export function parseEmbedArgs(args) {
     if (a === '--region')      { flags.region = args[++i]; i++; continue; }
     if (a === '--batch-size')  { flags.batchSize = parseInt(args[++i], 10); i++; continue; }
     if (a === '--detach')      { flags.detach = true; i++; continue; }
+    if (a === '--dry-run')     { flags.dryRun = true; i++; continue; }
     if (a === '--env') {
       const kv = args[++i]; i++;
       if (!flags.env) flags.env = [];
@@ -49,15 +52,6 @@ export function parseEmbedArgs(args) {
   return { model, input, flags };
 }
 
-function parseEnvFlag(envList) {
-  const obj = {};
-  for (const kv of (envList || [])) {
-    const idx = kv.indexOf('=');
-    if (idx > 0) obj[kv.slice(0, idx)] = kv.slice(idx + 1);
-  }
-  return obj;
-}
-
 function isUrl(s) {
   return /^(https?|s3|gs|hf):\/\//i.test(s);
 }
@@ -120,14 +114,23 @@ export async function embedCommand(config, args, chalk) {
     ...(flags.batchSize    ? { EMBED_BATCH_SIZE: String(flags.batchSize) } : {}),
   };
 
-  console.log(chalk.bold('\n📐 Embeddings\n'));
+  console.log(chalk.bold(flags.dryRun ? '\n📐 Dry run — no GPU will be provisioned — Embeddings\n' : '\n📐 Embeddings\n'));
   console.log(`  ${chalk.bold('Input:')}       ${resolved.inputLabel}`);
   console.log(`  ${chalk.bold('Model:')}       ${model}`);
   console.log(`  ${chalk.bold('Image:')}       ${EMBED_IMAGE}`);
   console.log(`  ${chalk.bold('GPU:')}         ${gpu === 'AUTO' ? chalk.dim('auto (8+ GB VRAM)') : gpu}`);
+  if (flags.dryRun) console.log(`  ${chalk.bold('Tier:')}        ${formatTierLabel(effectiveTier)}`);
   console.log(`  ${chalk.bold('Max runtime:')} ${maxRuntimeMin}min`);
   if (maxCost) console.log(`  ${chalk.bold('Max cost:')}    $${maxCost.toFixed(2)}`);
+  if (flags.env?.length) console.log(`  ${chalk.bold('Env:')}         ${flags.env.join(', ')}`);
   console.log();
+
+  if (flags.dryRun) {
+    await printCapacityPreview(chalk, config, { gpu, region: flags.region?.toUpperCase(), maxPrice: flags.maxPrice });
+    console.log(chalk.dim('  Remove --dry-run to submit.\n'));
+    return;
+  }
+
   process.stdout.write(chalk.dim('  Finding suitable capacity...\n'));
 
   function buildBody(tierOverride) {

package/src/commands/launch.js

@@ -286,15 +286,20 @@ async function launchAgentWorkload(config, agentName, rawArgs, chalk) {
     const envKey = PROVIDER_ENV_KEYS[spec.provider];
     const userSuppliedKey = flags.env?.some(kv => kv.startsWith(`${envKey}=`));
     let credential = userSuppliedKey ? null : getCredential(spec.provider);
+    flags.authRequired = { provider: spec.provider, status: credential || userSuppliedKey ? 'connected' : 'missing' };
     if (!credential && !userSuppliedKey) {
       // Missing credential no longer forces a separate `badgr connect` +
       // rerun in an interactive terminal — prompt inline and continue the
-      // same launch. Non-interactive contexts still hard-fail as before.
+      // same launch (including under --dry-run, so the dry-run preview
+      // reflects the connected state the real launch will actually use, and
+      // a follow-up real launch never needs a second prompt). Non-interactive
+      // contexts still hard-fail as before.
       credential = await resolveMissingCredential(spec.provider, chalk);
       if (!credential) {
         process.exitCode = 1;
         return;
       }
+      flags.authRequired.status = 'connected';
     }
     // An explicit --env always wins over the stored credential — never
     // append the injected default alongside a user-supplied value for the
@@ -304,6 +309,8 @@ async function launchAgentWorkload(config, agentName, rawArgs, chalk) {
       if (!flags.env) flags.env = [];
       flags.env.push(`${envKey}=${credential}`);
     }
+  } else {
+    flags.authRequired = { provider: null, status: 'none' };
   }
   // cline has no `provider` — Badgr mints and injects its own short-lived
   // job-scoped model token server-side (see backend jobs_routes.py); the