badgr-cli 1.1.3 → 1.1.5

package/README.md

@@ -13,7 +13,7 @@ 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)
+**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) · [`badgr diagnose`](#diagnose-a-gpu-issue-badgr-diagnose) · [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)
 
 ---
 
@@ -159,21 +159,78 @@ Run `badgr doctor --help` for the full flag list. Details in
 
 ---
 
+## Badgr Smoke Test: `badgr diagnose`
+
+Paste a GitHub issue, a Docker image, a repo URL, a log file, a ComfyUI
+workflow, or a raw conversation — Badgr auto-detects the input, redacts
+secrets, and runs free static checks as part of a Badgr Smoke Test.
+Nothing runs on a GPU without explicit `--approve`.
+
+```bash
+# badgr diagnose IS the Badgr Smoke Test — free, no login, no GPU.
+# Applicable free structural checks run automatically, every time.
+badgr diagnose "https://github.com/org/repo/issues/123"
+badgr diagnose ajayrajtp/vllm_gemma412b:latest
+badgr diagnose ./vllm-error.log
+badgr diagnose "https://github.com/org/repo"
+badgr diagnose workflow.json
+
+# Start a real Badgr Run (paid GPU execution) after diagnosis (login required)
+badgr diagnose "https://github.com/org/repo/issues/123" --approve
+
+# Resume an existing case, e.g. one shared via a case link
+badgr diagnose repro_xxxxxxxx --approve
+badgr diagnose "https://aibadgr.com/repro/repro_xxxxxxxx" --approve
+
+# Machine-readable output
+badgr diagnose "https://github.com/org/repo/issues/123" --json
+```
+
+| Flag | Description |
+|------|-------------|
+| `--approve` | Start a real Badgr Run after diagnosis — actual GPU execution, capped at a hard maximum spend (opens browser sign-in automatically if not logged in) |
+| `--smoke` | Deprecated, no-op. The free mechanical checks this used to gate (syntax, CLI-entrypoint corroboration, referenced-file presence, Docker `ENTRYPOINT`/`CMD` consistency, required env vars, plus a client-side local-file check) now always run as part of plain `badgr diagnose`. Kept only so existing scripts that pass it don't break. Not the same as `badgr run --smoke`, which launches a real, billable GPU job |
+| `--docker <image>` | Force Docker-image intake (override auto-detect) |
+| `--repo <url>` | Force repository intake (override auto-detect) |
+| `--comfyui <path>` | Force ComfyUI workflow intake (override auto-detect) |
+| `--github <url>` | Include a GitHub issue URL found inside pasted text as additional context (opt-in, never fetched automatically) |
+| `--json` | Machine-readable JSON output |
+
+Every run prints one status: `NEEDS INFO` (fields still missing) →
+`READY` (complete evidence-backed command, no applicable checks to run) →
+`SMOKE CHECKED` (applicable checks ran, all passed or were skipped) /
+`INVALID` (an applicable check actually failed) → `VERIFIED` (reserved for
+an actual successful Badgr Run — never assigned from diagnosis alone).
+`READY`/`SMOKE CHECKED` results also print the canonical `badgr
+run`/`badgr serve` command `--approve` would run, plus a shareable case
+link — pass that case ID or URL back into `badgr diagnose
+<case_id_or_url> --approve` to resume the same case without re-diagnosing.
+
+`badgr run-issue` is an alias for `badgr diagnose`, matching the
+[aibadgr.com/run-issue](https://aibadgr.com/run-issue) Badgr Smoke Test
+web flow.
+
+---
+
 ## Commands
 
 ```text
 login
 connect
 doctor
+diagnose
 run
 launch
-task
+job
 serve
 status
 logs
 pull
 artifacts
 down
+restart
+rerun
+heartbeat
 receipts
 test
 ```
@@ -183,6 +240,7 @@ test
 | `badgr login` | Save API key to `~/.badgr/config.json` |
 | `badgr connect <provider>` | Store a provider credential (`anthropic`, `openai`) for `badgr launch` |
 | `badgr doctor` | Diagnose a GPU workload failure — read-only, no login needed |
+| `badgr diagnose "<input>"` | Run a Badgr Smoke Test on a GitHub issue, Docker image, repo, log, or workflow — free, no GPU until `--approve` |
 | `badgr run <command>` | Run a one-off GPU job (any container command) |
 | `badgr launch cline\|claude\|codex\|playwright "<task>"` | Run a coding/testing agent on a CPU VM — image + command auto-selected |
 | `badgr job <agent> "<instruction>" --check "<cmd>"` | Tracked coding-agent job via `POST /v1/jobs` (type: agent) |
@@ -192,10 +250,13 @@ test
 | `badgr pull <id>` | Pull a code-editing agent's patch as a local git diff/branch |
 | `badgr artifacts <id>` | Download non-patch outputs (test reports, screenshots, traces) |
 | `badgr down <id>` | Terminate a deployment — stops billing immediately |
+| `badgr restart <id>` | Relaunch an endpoint with the same config, on a new deployment ID, keeping its API key |
+| `badgr rerun <id>` | Replay a past job or endpoint with its exact original spec, on a new deployment ID |
+| `badgr heartbeat <id>` | Reset an endpoint's idle-timeout clock (see `--idle-timeout` under [`badgr serve` options](#badgr-serve-options)) |
 | `badgr receipts [n]` | Cost, route, and retry receipts (default 10) |
 | `badgr test` | Run an end-to-end test (provision → run → teardown) |
 
-More commands below, under [Advanced](#advanced): `comfyui`, `train`, `transcribe`, `embed`, `workload`, `workspace`, `batch`, `sbatch`, `capacity`, `billing`.
+More commands below, under [Advanced](#advanced): `comfyui`, `train`, `transcribe`, `embed`, `workload`, `workspace`, `batch`, `sbatch`, `capacity`, `billing`, `models`, `template`.
 
 `badgr serve` — for anything that needs a persistent endpoint: LLM serving, embeddings, image generation APIs, transcription APIs.
 
@@ -228,16 +289,38 @@ Each command section below lists only its own extra flags.
 badgr serve meta-llama/Llama-3.1-8B-Instruct --gpu L40S --region EU
 ```
 
+Endpoints bill continuously, so `serve` requires either `--max-cost` or `--persistent` (or `--dry-run` to just preview) — it refuses to start otherwise.
+
 | Flag | Default | Description |
 |------|---------|-------------|
 | `--image <img>` | — | Serve a custom container instead of a HuggingFace model |
 | `--task <task>` | — | vLLM task override, e.g. `embed` for embedding models |
-| `--health-path <path>` | auto | Readiness path to poll (auto-detected for ComfyUI → `/system_stats`) |
+| `--runtime llama.cpp\|ollama` | vLLM | Serve via a different runtime instead of vLLM |
+| `--hf-repo <repo>` | — | HuggingFace repo for a GGUF file (with `--runtime llama.cpp`), e.g. `org/model-repo` |
+| `--hf-file <file>` | — | GGUF filename within that repo, e.g. `model.gguf` (required with `--runtime llama.cpp`) |
+| `--idle-timeout <min>` | — | Auto-stop after N minutes with no `badgr heartbeat` call — see [`badgr heartbeat`](#badgr-heartbeat) |
+| `--persistent` | off | Run until manually stopped — satisfies the cost-control requirement in place of `--max-cost` |
+| `--check-nodes <n1,n2>` | — | For ComfyUI-shaped images: verify custom nodes are installed after startup |
+| `--health-path <path>` | auto | Readiness path to poll (auto-detected: ComfyUI → `/system_stats`, llama.cpp → `/health`) |
 | `--no-wait` | off | Skip endpoint health check and return immediately |
+| `--yes` / `-y` | off | Skip duplicate-deployment warning |
+| `--dry-run` | — | Preview the plan (GPU, price) without provisioning |
 | `--list-aliases` | — | List blessed vLLM model aliases (`qwen-7b`, `llama-8b`, `qwen-coder-7b`) and exit — no provisioning, no API key required |
 
 Blessed aliases expand to a full model ID + preset GPU, e.g. `badgr serve qwen-7b` → `Qwen/Qwen2.5-7B-Instruct` on an RTX 4090. Run `badgr serve --list-aliases` to see the current list.
 
+```bash
+# Serve a Hugging Face GGUF file via llama.cpp instead of vLLM
+badgr serve --runtime llama.cpp --hf-repo org/model-repo --hf-file model.gguf --max-cost 10
+
+# Serve Open WebUI, a chat UI, pointed at a model endpoint
+badgr serve openwebui --model qwen-7b --max-cost 10
+badgr serve openwebui --connect <existing-endpoint-url>   # connect to an endpoint you already have
+
+# Auto-stop only when idle — requires periodic badgr heartbeat calls to stay up
+badgr serve qwen-7b --idle-timeout 30 --max-cost 10
+```
+
 ### Model support levels
 
 `badgr serve qwen-7b` is the happy path — a tested route with no extra setup. `badgr serve` also accepts any other model ID or a custom container:
@@ -269,10 +352,21 @@ badgr run . --image mycompany/custom:latest --cmd "python train.py" --max-cost 5
 
 Badgr zips and uploads the folder (Flow 1) or clones the repo (Flow 2), picks a generic runner, installs deps, runs the command, stores outputs for 48 hours, and tears down the GPU. `--max-cost` is required.
 
+```bash
+# No GPU needed — run on a plain CPU VM instead
+badgr run . --cmd "npm test" --no-gpu --max-cost 1
+
+# Describe basic compute needs instead of a GPU model — Badgr finds a compatible machine
+badgr run . --cpu 16 --memory 64GB --gpu-memory 24GB --max-cost 5
+```
+
 | Flag | Default | Description |
 |------|---------|-------------|
 | `--cmd <command>` | — | Command to run inside the uploaded project or cloned repo (required for folder/GitHub flows) |
-| `--min-vram <GB>` | — | Minimum VRAM in GB — optional constraint for Auto routing |
+| `--min-vram <GB>` | — | Minimum VRAM in GB — optional constraint for Auto routing (alias: `--gpu-memory`) |
+| `--cpu <cores>` | — | Minimum CPU cores (for a CPU-only run) |
+| `--memory <size>` | — | Minimum RAM, e.g. `64GB` |
+| `--no-gpu` | off | Run on a CPU-only VM — no GPU is provisioned (conflicts with `--gpu`/`--min-vram`) |
 | `--image <img>` | — | Custom Docker image — bypasses the runner |
 | `--max-runtime <min>` | — | Auto-stop after N minutes |
 | `--save <name>` | — | Save this job as a named workload after it completes |
@@ -320,13 +414,14 @@ Productized batch image generation — runs a list of prompts through a **blesse
 ```bash
 badgr comfyui batch --workflow sdxl-basic --prompts prompts.txt --max-cost 10
 badgr comfyui batch --workflow sdxl-basic --prompt "a cat on a beach" --prompt "a dog in the park" --max-cost 5
+badgr comfyui batch --workflow flux-basic --prompt "a neon city at night" --max-cost 5
 ```
 
-Blessed workflows: `sdxl-basic` (SDXL text-to-image, default sampler settings). Max 20 prompts per batch.
+Blessed workflows: `sdxl-basic` (SDXL text-to-image, default sampler settings), `flux-basic` (FLUX.1-schnell text-to-image). Max 20 prompts per batch.
 
 | Flag | Default | Description |
 |------|---------|-------------|
-| `--workflow <name>` | — | Blessed workflow ID (required) — currently `sdxl-basic` |
+| `--workflow <name>` | — | Blessed workflow ID (required) — `sdxl-basic` or `flux-basic` |
 | `--prompts <file>` | — | Text file, one prompt per line |
 | `--prompt <text>` | — | Inline prompt (repeatable) — combine with `--prompts` if needed |
 | `--max-runtime <min>` | 60 | Auto-stop after N minutes |
@@ -350,6 +445,37 @@ Each receipt includes runtime, estimated/settled cost, status, retries, teardown
 
 ---
 
+## Managing a deployment
+
+```bash
+badgr status                          # what's running and billing
+badgr logs dep-abc123                 # fetch current log output
+badgr logs dep-abc123 --follow        # stream logs until the deployment reaches a terminal state
+badgr pull dep-abc123                 # pull a coding agent's patch as a local git diff
+badgr pull dep-abc123 --branch        # ...as a new local branch instead of a diff
+badgr pull dep-abc123 --diff-only     # print the diff, don't touch the working tree
+badgr artifacts dep-abc123            # download non-patch outputs (test reports, screenshots, traces)
+badgr down dep-abc123                 # terminate one deployment, stop billing
+badgr down --all                      # terminate everything running, with a confirmation prompt
+badgr down --all --yes                # ...skip the confirmation prompt
+badgr restart dep-abc123              # relaunch an endpoint with the same config — new ID, same API key
+badgr rerun dep-abc123                # replay a past job/endpoint with its exact original spec — new ID
+badgr heartbeat dep-abc123            # reset an endpoint's idle-timeout clock (see --idle-timeout on badgr serve)
+```
+
+| Command | Flag | Description |
+|---------|------|-------------|
+| `badgr logs <id>` | `--follow` / `-f` | Stream/poll logs until the deployment reaches a terminal state instead of a one-shot fetch |
+| `badgr pull <id>` | `--branch` | Create a new local git branch from the patch instead of leaving it as an unstaged diff |
+| `badgr pull <id>` | `--diff-only` | Print the raw diff, don't touch the local working tree at all |
+| `badgr pull <id>` | `--yes` / `-y` | Skip the confirmation prompt before applying |
+| `badgr down <id\|--all>` | `--all` | Terminate every running deployment instead of one by ID |
+| `badgr down <id\|--all>` | `--yes` / `-y` | Skip the confirmation prompt |
+
+`badgr restart` is endpoint-only (it tears down the current pod and relaunches with the same GPU/model/price/runtime caps and endpoint API key, so existing clients keep working against a new URL). `badgr rerun` works for both one-off jobs and endpoints, replaying the exact original image/command/env/GPU/caps, and never tears down the source deployment.
+
+---
+
 ## OpenAI compatibility
 
 `badgr serve` provisions a vLLM endpoint that is fully OpenAI-compatible:
@@ -417,22 +543,26 @@ Less common commands — training, transcription, embeddings, and the workload/w
 badgr train config.yaml --gpu A100 --max-runtime 240 --env HF_TOKEN=$HF_TOKEN
 ```
 
-Detects framework (axolotl, unsloth, trl) from the config file, but **only Axolotl configs run today** — `unsloth`/`trl`/unrecognized configs are blocked before provisioning rather than billing a GPU that's guaranteed to fail. Default max-runtime is 120 min.
+Detects framework (axolotl, unsloth, trl) from the config file. **Axolotl and TRL configs run today** — `unsloth`/unrecognized configs are blocked before provisioning rather than billing a GPU that's guaranteed to fail. Default max-runtime is 120 min.
 
 ```bash
 badgr train lora --base-model mistralai/Mistral-7B-v0.1 --dataset ./train.jsonl --preset small --max-cost 20
+
+# Resume from a prior job's checkpoint instead of starting over
+badgr train lora --base-model mistralai/Mistral-7B-v0.1 --dataset ./train.jsonl --resume https://.../checkpoint --max-cost 20
 ```
 
 Productized LoRA training — pass a base model and dataset, no Axolotl config file needed. Badgr generates the config from a preset and returns a downloadable adapter.
 
 | Flag | Default | Description |
 |------|---------|-------------|
-| `--framework <name>` | auto-detect | Force framework: `axolotl`, `unsloth`, `trl` (only `axolotl` currently runs) |
+| `--framework <name>` | auto-detect | Force framework: `axolotl`, `unsloth`, `trl` (`axolotl`/`trl` currently run; `unsloth` is blocked pre-provisioning) |
 | `--base-model <id>` | — | HuggingFace model ID (required for `train lora`) — validated to exist before provisioning |
 | `--dataset <path\|url>` | — | Local file, direct URL, or `s3://` URI |
 | `--file-id <id>` | — | Badgr upload ID instead of `--dataset` |
 | `--preset small\|medium` | `small` | `small` = RTX 4090, rank 16, 3 epochs. `medium` = A100, rank 32, 5 epochs |
 | `--gpu-type <type>` | preset default | GPU type override for `train lora` |
+| `--resume <checkpoint-url>` | — | Continue training from a prior job's checkpoint instead of starting fresh |
 | `--dry-run` | — | Preview the job without provisioning |
 
 On completion, `train lora` prints an `adapter_url` — download with `GET /v1/jobs/{job_id}/adapter`, or via `badgr workload info` if saved.
@@ -502,8 +632,11 @@ badgr batch status dep-abc123
 badgr batch artifacts dep-abc123
 badgr batch receipt dep-abc123
 badgr batch compare dep-abc123 dep-def456
+badgr batch compare dep-abc123 dep-def456 --key accuracy --higher-is-better
 ```
 
+`batch compare` reads each run's `success_metric` by default; `--key <metric>` compares a different field from the receipt instead, and `--higher-is-better` (default) / `--higher-is-better false` controls which run is reported as the winner.
+
 For CV/video/scientific batch, simulation, and physical-AI eval workloads — runs a container from a `workload.yml` spec and captures output artifacts automatically.
 
 **Fan-out** — run the same program once per file in a directory, one deployment per input, in parallel:
@@ -539,14 +672,44 @@ Translates `--cpus-per-task`/`--mem`/`--gres`/`--time`/`--export` from a real `.
 | `--max-concurrency <n>` | 5 | Cap in-flight array tasks |
 | `--dry-run` | — | Preview the translated job without provisioning |
 
-### Other commands
+### `badgr models` — GPU catalog and pricing
+
+```bash
+badgr models
+```
+
+Lists available GPU types cheapest-first, with VRAM and hourly rate — pulled live from your account when logged in, falling back to the local catalog otherwise. No flags.
+
+### `badgr template` — pre-built workload templates
 
-- `badgr capacity [--gpu <type>]` — check available GPU capacity right now
-- `badgr billing status` / `badgr billing add <amount>` — check balance / add funds
+```bash
+badgr template list
+badgr template info axolotl
+badgr serve template vllm --model meta-llama/Llama-3.1-8B-Instruct --max-cost 10
+badgr run template axolotl --config ./config.yaml --max-cost 10
+```
+
+Provider-neutral templates for common frameworks (`vllm`, `invokeai`, `comfyui`, `axolotl`, `unsloth`, …). `template list`/`template info <name>` just browse the catalog; launching always goes through `badgr serve template <name>` or `badgr run template <name>`, which apply the template's default flags before handing off to the normal `serve`/`run` path.
+
+### `badgr capacity` — check live availability
+
+```bash
+badgr capacity                              # cheapest runnable GPU across all types
+badgr capacity --gpu A100                   # a specific GPU type
+badgr capacity --gpu A100 --region EU       # region-filtered
+badgr capacity --gpu A100 --max-price 2.50  # price-capped
+```
+
+### `badgr billing`
+
+```bash
+badgr billing status         # current balance
+badgr billing add 20         # add funds — $5 minimum top-up
+```
 
 ---
 
 ## Requirements
 
-- Node.js 18+
+- Node.js 20.10+
 - A Badgr account — sign up at [aibadgr.com](https://aibadgr.com)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "badgr-cli",
-  "version": "1.1.3",
+  "version": "1.1.5",
   "description": "Badgr — run or serve GPU workloads from one command",
   "type": "module",
   "bin": {
@@ -14,6 +14,7 @@
   "dependencies": {
     "@inquirer/prompts": "^8.5.2",
     "archiver": "^7.0.1",
+    "badgr-shared": "^0.1.2",
     "chalk": "^5.3.0",
     "js-yaml": "^4.1.0",
     "tar": "^7.4.3"

package/src/api.js

@@ -228,6 +228,34 @@ export async function terminateDeployment(config, deploymentId) {
   throw lastErr;
 }
 
+// ---- Admin (michaelhireitem@gmail.com only) ---------------------------------
+// CLI counterparts to the web admin dashboard's own /admin/api/deployments/*
+// routes (main.py) -- those are gated by a browser session cookie the CLI's
+// Authorization: Bearer <api_key> auth can never satisfy, so
+// deployment_routes.py exposes these two under /v1/admin/deployments/*
+// instead, gated by the same is_admin_email() check via API key. A non-admin
+// caller gets a plain 403 from callApi, same as any other access-denied route.
+
+// Every non-terminal deployment across every user (not just the caller's
+// own), each carrying its owner's user_email/username so a stuck or
+// forgotten GPU can be identified without logging into that customer's
+// account. Backs `badgr status --admin`.
+export function listAllActiveDeploymentsAdmin(config) {
+  return callApi('/admin/deployments/active', { apiKey: config.apiKey, baseUrl: config.baseUrl, timeoutMs: 15_000 });
+}
+
+// Force-terminate any deployment regardless of owner -- bypasses the
+// per-user ownership check DELETE /deployments/{id} enforces. Backs
+// `badgr down <id> --admin`.
+export function adminTerminateDeployment(config, deploymentId) {
+  return callApi(`/admin/deployments/${deploymentId}`, {
+    method: 'DELETE',
+    apiKey: config.apiKey,
+    baseUrl: config.baseUrl,
+    timeoutMs: 20_000,
+  });
+}
+
 export function restartDeployment(config, deploymentId) {
   return callApi(`/deployments/${deploymentId}/restart`, {
     method: 'POST',

package/src/badgr.js

@@ -47,7 +47,7 @@ ${chalk.bold('COMMANDS')}
   ${chalk.cyan('badgr job <agent> "<instruction>" --check "<command>"')}  Bounded coding-agent job, tracked at /jobs (POST /v1/jobs, type: agent)
   ${chalk.cyan('badgr serve <model>')}       Serve a model with an OpenAI-compatible endpoint
   ${chalk.cyan('badgr serve openwebui')}     Serve Open WebUI — chat UI, connects to a model endpoint
-  ${chalk.cyan('badgr diagnose "<input>"')}   Diagnose any GPU issue for free — GitHub issue, Docker image, log, repo, or text
+  ${chalk.cyan('badgr diagnose "<input>"')}   Run a free Badgr Smoke Test on any GPU issue — GitHub issue, Docker image, log, repo, or text
   ${chalk.cyan('badgr doctor')}              Local GPU / model-fit diagnosis (read-only, no login needed)
   ${chalk.cyan('badgr status')}              Show what's running and what's billing
   ${chalk.cyan('badgr logs <id>')}           Stream logs for a running job or endpoint
@@ -113,13 +113,13 @@ ${chalk.bold('EXAMPLES')}
   ${chalk.dim('# badgr job — bounded coding-agent job with a pass/fail check, tracked at /jobs:')}
   badgr job cline "Run the Chromium tests and tell me what failed" --check "npm run test:chromium" --max-cost 1
 
-  ${chalk.dim('# Diagnose any GPU issue for free (no login needed):')}
+  ${chalk.dim('# Run a free Badgr Smoke Test on any GPU issue (no login needed):')}
   badgr diagnose "https://github.com/org/repo/issues/123"
   badgr diagnose ./error.log
   badgr diagnose --docker ajayrajtp/vllm_gemma412b:latest
   badgr diagnose --repo https://github.com/org/repo
   badgr diagnose --comfyui workflow.json
-  badgr diagnose "https://github.com/org/repo/issues/123" --approve ${chalk.dim('# approve a capped smoke test')}
+  badgr diagnose "https://github.com/org/repo/issues/123" --approve ${chalk.dim('# start a real Badgr Run')}
 
   ${chalk.dim('# Local model-fit and workload diagnosis (no network):')}
   badgr doctor

package/src/commands/artifacts.js

@@ -1,6 +1,7 @@
 import fs from 'fs';
 import path from 'path';
-import { requireApiKey, CONFIG_DIR } from '../config.js';
+import { CONFIG_DIR } from '../config.js';
+import { ensureLoggedInReady, withReauthRetry } from '../onboarding.js';
 import { downloadAndExtractArtifact } from '../artifactDownload.js';
 
 /**
@@ -37,7 +38,7 @@ export function listFilesRecursive(dir, prefix = '') {
 }
 
 export async function artifactsCommand(config, args, chalk) {
-  requireApiKey(config);
+  config = await ensureLoggedInReady(config, chalk);
   const { deploymentId, flags } = parseArtifactsArgs(args);
   if (!deploymentId) {
     console.error(chalk.red('\n  Usage: badgr artifacts <deployment-id> [--output <dir>]\n'));
@@ -49,7 +50,8 @@ export async function artifactsCommand(config, args, chalk) {
   const destDir = flags.output ? path.resolve(flags.output) : defaultDestDir(deploymentId);
 
   try {
-    await downloadAndExtractArtifact(config, deploymentId, destDir);
+    const refreshed = await withReauthRetry(config, chalk, cfg => downloadAndExtractArtifact(cfg, deploymentId, destDir));
+    config = refreshed.config;
   } catch (err) {
     if (err.httpStatus === 404) {
       console.error(chalk.red(`\n  ✗ No artifact found for ${deploymentId}.\n`));

package/src/commands/batch.js

@@ -17,7 +17,8 @@ import { existsSync, readFileSync, unlinkSync, statSync, readdirSync } from 'fs'
 import { join, resolve } from 'path';
 import os from 'os';
 
-import { requireApiKey, CONFIG_DIR } from '../config.js';
+import { CONFIG_DIR } from '../config.js';
+import { ensureBadgrReady, ensureLoggedInReady } from '../onboarding.js';
 import { parseWorkloadYaml } from '../workloadSpec.js';
 import { addReceipt, updateReceipt, generateReceiptId, loadStore, selectedComputeFromDeployment } from '../store.js';
 import { normalizeTier, callWithFallback } from '../fallback.js';
@@ -392,7 +393,7 @@ async function runSubcommand(config, args, chalk) {
     return;
   }
 
-  requireApiKey(config);
+  config = await ensureBadgrReady(config, chalk);
 
   let spec;
   try {
@@ -593,7 +594,7 @@ async function statusSubcommand(config, args, chalk) {
     process.exitCode = 1;
     return;
   }
-  requireApiKey(config);
+  config = await ensureLoggedInReady(config, chalk);
 
   let dep;
   try {
@@ -628,7 +629,7 @@ async function artifactsSubcommand(config, args, chalk) {
     process.exitCode = 1;
     return;
   }
-  requireApiKey(config);
+  config = await ensureLoggedInReady(config, chalk);
 
   let destDir;
   try {
@@ -676,7 +677,7 @@ async function receiptSubcommand(config, args, chalk) {
     process.exitCode = 1;
     return;
   }
-  requireApiKey(config);
+  config = await ensureLoggedInReady(config, chalk);
 
   const local = findBatchRun(runId);
   let dep = null;

package/src/commands/billing.js

@@ -1,4 +1,4 @@
-import { requireApiKey } from '../config.js';
+import { ensureLoggedInReady } from '../onboarding.js';
 import { callApi } from '../api.js';
 import { openBrowser } from '../browser.js';
 
@@ -17,7 +17,7 @@ EXAMPLES
 `;
 
 async function billingStatus(config, chalk) {
-  requireApiKey(config);
+  config = await ensureLoggedInReady(config, chalk);
   try {
     const apiUrl = config.baseUrl.replace('/v1', '').replace('/api/v1', '');
     const data = await callApi('/api/me', {
@@ -47,7 +47,7 @@ async function billingStatus(config, chalk) {
 }
 
 async function billingAdd(config, amount, chalk) {
-  requireApiKey(config);
+  config = await ensureLoggedInReady(config, chalk);
   const amountInt = parseInt(amount, 10);
   if (!amountInt || amountInt < 5) {
     console.error(chalk.red('  Minimum top-up is $5. Example: badgr billing add 5'));

package/src/commands/capacity.js

@@ -1,4 +1,4 @@
-import { requireApiKey } from '../config.js';
+import { ensureLoggedInReady } from '../onboarding.js';
 import { callApi } from '../api.js';
 
 /**
@@ -19,7 +19,7 @@ function parseCapacityArgs(args) {
 
 export async function capacityCommand(config, args, chalk) {
   const flags = parseCapacityArgs(args);
-  requireApiKey(config);
+  config = await ensureLoggedInReady(config, chalk);
 
   // No --max-price: no cap. Availability browsing shouldn't silently hide
   // real capacity behind an unrequested price ceiling.

package/src/commands/deploy.js

@@ -1,6 +1,6 @@
 import { randomUUID } from 'crypto';
 import { findCheapest, findById } from '../router.js';
-import { requireApiKey } from '../config.js';
+import { ensureBadgrReady } from '../onboarding.js';
 
 export function parseDeployArgs(args) {
   const nameFlag = args.indexOf('--name');
@@ -24,7 +24,7 @@ export async function deployCommand(config, args, chalk) {
     return;
   }
 
-  requireApiKey(config);
+  config = await ensureBadgrReady(config, chalk);
 
   const deployId = randomUUID().split('-')[0];
   const name = rawName ?? script.replace(/[^a-z0-9]/gi, '-').replace(/-+/g, '-').toLowerCase();