badgr-cli 1.0.30 → 1.0.32

package/README.md

@@ -14,16 +14,19 @@ npm install -g badgr-cli
 # 1. Authenticate once
 badgr login
 
-# 2. Serve an OpenAI-compatible inference endpoint
-badgr serve meta-llama/Llama-3.1-8B-Instruct --gpu L40S
+# 2. Verify the stack end-to-end
+badgr test
 
-# 3. Use the endpoint with any OpenAI SDK client
-#    client = OpenAI(api_key="sk-...", base_url="https://dep-a1b2c3.api.badgr.ai/v1")
+# 3. Serve an OpenAI-compatible inference endpoint
+badgr serve meta-llama/Llama-3.1-8B-Instruct
 
-# 4. View cost, route, and retry receipts
+# 4. Use the endpoint with any OpenAI SDK client
+#    client = OpenAI(api_key="sk-...", base_url="https://dep-a1b2c3.aibadgr.com/v1")
+
+# 5. View cost, route, and retry receipts
 badgr receipts
 
-# 5. Stop billing
+# 6. Stop billing
 badgr down <deployment-id>
 ```
 
@@ -36,9 +39,13 @@ badgr down <deployment-id>
 | `badgr login` | Save API key to `~/.badgr/config.json` |
 | `badgr serve <model>` | Start a persistent OpenAI-compatible endpoint |
 | `badgr run <command>` | Run a one-off GPU job (any container command) |
+| `badgr status` | Show what's running and what's billing |
 | `badgr down <id>` | Terminate a deployment — stops billing immediately |
 | `badgr logs <id>` | Fetch log output from a deployment |
 | `badgr receipts [n]` | Cost, route, and retry receipts (default 10) |
+| `badgr capacity` | Check available GPU capacity right now |
+| `badgr billing` | Show balance and add funds |
+| `badgr test` | Run an end-to-end test (provision → run → teardown) |
 
 `badgr serve` — for anything that needs a persistent endpoint: LLM serving, embeddings, image generation APIs, transcription APIs.
 
@@ -54,37 +61,49 @@ badgr serve meta-llama/Llama-3.1-8B-Instruct --gpu L40S --region EU
 
 | Flag | Default | Description |
 |------|---------|-------------|
-| `--gpu <type>` | RTX_4090 | GPU: RTX_4090, L40S, A6000, A100, H100 |
-| `--region <region>` | — | Optional region preference. If omitted, Badgr chooses best available capacity. |
+| `--gpu <type>` | auto | GPU type — Badgr infers from model size if omitted. Options: RTX_4090, L40S, A6000, A100, H100 |
+| `--image <img>` | — | Serve a custom container instead of a HuggingFace model |
+| `--task <task>` | — | vLLM task override, e.g. `embed` for embedding models |
+| `--env KEY=VALUE` | — | Environment variable (repeatable) |
+| `--tier 1\|2` | 1 | `1` = managed provider routing (default); `2` = marketplace routing, lower cost |
 | `--count <n>` | 1 | Number of GPUs (1–8) |
+| `--region US\|EU\|AU` | — | Optional region preference. If omitted, Badgr chooses best available capacity. |
 | `--max-price <$/hr>` | — | Hard spend cap per GPU-hour |
-| `--dry-run` | — | Preview routing without provisioning |
+| `--max-cost <$>` | — | Auto-stop when total spend reaches this amount |
+| `--health-path <path>` | auto | Readiness path to poll (auto-detected for ComfyUI → `/system_stats`) |
+| `--no-wait` | — | Skip endpoint health check and return immediately |
 
 ---
 
 ## `badgr run` options
 
 ```bash
-badgr run python train.py --gpu A100 --env HF_TOKEN=$HF_TOKEN
+badgr run python train.py --gpu A100 --env HF_TOKEN=$HF_TOKEN --max-runtime 60
 ```
 
 | Flag | Default | Description |
 |------|---------|-------------|
-| `--gpu <type>` | RTX_4090 | GPU type |
+| `--gpu <type>` | auto | GPU type — Badgr picks best available if omitted |
 | `--image <img>` | python:3.11-slim | Docker image |
 | `--env KEY=VALUE` | — | Environment variable (repeatable) |
-| `--region <region>` | — | Optional region preference. If omitted, Badgr chooses best available capacity. |
+| `--tier 1\|2` | 1 | `1` = managed provider routing (default); `2` = marketplace routing, lower cost |
+| `--count <n>` | 1 | Number of GPUs |
+| `--region US\|EU\|AU` | — | Optional region preference. If omitted, Badgr chooses best available capacity. |
 | `--max-price <$/hr>` | — | Hard spend cap per GPU-hour |
-| `--detach` | — | Launch and return immediately |
+| `--max-runtime <min>` | — | Auto-stop after N minutes (recommended) |
+| `--max-cost <$>` | — | Auto-stop when total spend reaches this amount |
+| `--detach` | — | Launch and return immediately, don't stream logs |
 
 ---
 
 ## Routing
 
-Badgr automatically searches available GPU capacity across its verified compute network.
-
 Badgr automatically searches verified GPU capacity and chooses the best eligible route for your GPU type, workload, price cap, and optional region preference.
 
+**Tier 1** (default) — managed provider routing with guaranteed SLAs.
+
+**Tier 2** — marketplace routing for lower-cost options when Tier 1 capacity is constrained.
+
 Preview before provisioning:
 
 ```bash
@@ -115,7 +134,7 @@ from openai import OpenAI
 
 client = OpenAI(
     api_key="your-badgr-api-key",
-    base_url="https://dep-a1b2c3.api.badgr.ai/v1",  # from badgr serve output
+    base_url="https://dep-a1b2c3.aibadgr.com/v1",  # from badgr serve output
 )
 resp = client.chat.completions.create(
     model="meta-llama/Llama-3.1-8B-Instruct",
@@ -127,7 +146,7 @@ resp = client.chat.completions.create(
 import OpenAI from "openai";
 const client = new OpenAI({
   apiKey: process.env.BADGR_API_KEY,
-  baseURL: "https://dep-a1b2c3.api.badgr.ai/v1",
+  baseURL: "https://dep-a1b2c3.aibadgr.com/v1",
 });
 ```
 
@@ -150,4 +169,4 @@ Prices shown are estimated Badgr rates. Final $/GPU-hour is confirmed before pro
 ## Requirements
 
 - Node.js 18+
-- A Badgr account — sign up at [badgr.ai](https://badgr.ai)
+- A Badgr account — sign up at [aibadgr.com](https://aibadgr.com)

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "badgr-cli",
-  "version": "1.0.30",
+  "version": "1.0.32",
   "description": "Badgr, run or serve GPU workloads from one command",
   "type": "module",
   "bin": {

package/src/api.js

@@ -4,13 +4,19 @@ function dbg(...args) {
   if (DEBUG) console.error('[badgr:debug]', ...args);
 }
 
-export async function callApi(path, { method = 'GET', apiKey, baseUrl, body } = {}) {
+// Redact env values so secrets never appear in debug output.
+function redactBody(body) {
+  if (!body || !body.env || typeof body.env !== 'object') return body;
+  return { ...body, env: Object.fromEntries(Object.keys(body.env).map(k => [k, '***'])) };
+}
+
+export async function callApi(path, { method = 'GET', apiKey, baseUrl, body, timeoutMs = 15_000 } = {}) {
   const url = `${baseUrl}${path}`;
-  const keyPreview = apiKey ? `${apiKey.slice(0, 8)}…` : '(not set)';
+  const keyPreview = apiKey ? `${apiKey.slice(0, 4)}…` : '(not set)';
 
   dbg(`${method} ${url}`);
   dbg(`API key: ${keyPreview}`);
-  if (body !== undefined) dbg('Request body:', JSON.stringify(body));
+  if (body !== undefined) dbg('Request body:', JSON.stringify(redactBody(body)));
 
   let res;
   const startMs = Date.now();
@@ -22,11 +28,11 @@ export async function callApi(path, { method = 'GET', apiKey, baseUrl, body } =
         'Authorization': `Bearer ${apiKey}`,
       },
       body: body !== undefined ? JSON.stringify(body) : undefined,
+      signal: AbortSignal.timeout(timeoutMs),
     });
   } catch (cause) {
     const elapsed = Date.now() - startMs;
     dbg(`Fetch threw after ${elapsed}ms:`, cause);
-    // Network-level failure: DNS, connection refused, timeout, etc.
     const msg = cause?.message ?? String(cause);
     const code = cause?.cause?.code ?? cause?.code ?? '';
     const hint =
@@ -34,7 +40,7 @@ export async function callApi(path, { method = 'GET', apiKey, baseUrl, body } =
         ? `\n  Hint: Connection refused — is the server running at ${baseUrl}?` :
       (code === 'ENOTFOUND' || msg.includes('ENOTFOUND'))
         ? `\n  Hint: DNS lookup failed for ${baseUrl}\n  Check your internet or set BADGR_API_URL to the correct host` :
-      (code === 'ETIMEDOUT' || msg.includes('ETIMEDOUT'))
+      (code === 'ETIMEDOUT' || msg.includes('ETIMEDOUT') || cause?.name === 'TimeoutError')
         ? `\n  Hint: Request timed out — server may be overloaded` :
       (msg.includes('fetch failed') || msg === 'fetch failed')
         ? `\n  Hint: Network error reaching ${url}\n  • Check internet connection\n  • Run: badgr config  (verify baseUrl)\n  • Try: BADGR_DEBUG=1 badgr run … for full details\n  • Test: curl -v ${baseUrl}/models` :
@@ -60,7 +66,6 @@ export async function callApi(path, { method = 'GET', apiKey, baseUrl, body } =
     }
     const isCapacityError = errorData?.code === 'NO_CAPACITY_MATCH';
     if (res.status === 402) {
-      // Payment required — format a clear, actionable error
       const d = errorData?.detail ?? errorData ?? {};
       const detailObj = typeof d === 'object' ? d : {};
       const balanceUsd = typeof detailObj.balance_usd === 'number' ? detailObj.balance_usd : null;
@@ -100,6 +105,7 @@ export function runJob(config, body) {
     apiKey: config.apiKey,
     baseUrl: config.baseUrl,
     body,
+    timeoutMs: 30_000,
   });
 }
 
@@ -109,6 +115,7 @@ export function serveModel(config, body) {
     apiKey: config.apiKey,
     baseUrl: config.baseUrl,
     body,
+    timeoutMs: 30_000,
   });
 }
 
@@ -120,27 +127,53 @@ export function createDeployment(config, spec) {
     apiKey: config.apiKey,
     baseUrl: config.baseUrl,
     body: spec,
+    timeoutMs: 30_000,
   });
 }
 
 export function listDeployments(config) {
-  return callApi('/deployments', { apiKey: config.apiKey, baseUrl: config.baseUrl });
+  return callApi('/deployments', { apiKey: config.apiKey, baseUrl: config.baseUrl, timeoutMs: 10_000 });
 }
 
 export function getDeployment(config, deploymentId) {
-  return callApi(`/deployments/${deploymentId}`, { apiKey: config.apiKey, baseUrl: config.baseUrl });
-}
-
-export function terminateDeployment(config, deploymentId) {
   return callApi(`/deployments/${deploymentId}`, {
-    method: 'DELETE',
     apiKey: config.apiKey,
     baseUrl: config.baseUrl,
+    timeoutMs: 10_000,
   });
 }
 
+/**
+ * Terminate a deployment with up to 3 retries on transient failures.
+ * Throws on final failure so callers can decide whether to continue.
+ */
+export async function terminateDeployment(config, deploymentId) {
+  const MAX_ATTEMPTS = 3;
+  let lastErr;
+  for (let attempt = 1; attempt <= MAX_ATTEMPTS; attempt++) {
+    try {
+      return await callApi(`/deployments/${deploymentId}`, {
+        method: 'DELETE',
+        apiKey: config.apiKey,
+        baseUrl: config.baseUrl,
+        timeoutMs: 20_000,
+      });
+    } catch (err) {
+      lastErr = err;
+      if (attempt < MAX_ATTEMPTS) {
+        await new Promise(r => setTimeout(r, attempt * 1000));
+      }
+    }
+  }
+  throw lastErr;
+}
+
 export function getDeploymentLogs(config, deploymentId) {
-  return callApi(`/deployments/${deploymentId}/logs`, { apiKey: config.apiKey, baseUrl: config.baseUrl });
+  return callApi(`/deployments/${deploymentId}/logs`, {
+    apiKey: config.apiKey,
+    baseUrl: config.baseUrl,
+    timeoutMs: 10_000,
+  });
 }
 
 // ---- Receipts ---------------------------------------------------------------
@@ -155,6 +188,7 @@ export function listReceipts(config, { limit = 20, status, fromTs, toTs } = {})
   return callApi(`/receipts${qs ? `?${qs}` : ''}`, {
     apiKey: config.apiKey,
     baseUrl: config.baseUrl,
+    timeoutMs: 10_000,
   });
 }
 
@@ -162,13 +196,14 @@ export function getReceipt(config, receiptId) {
   return callApi(`/receipts/${receiptId}`, {
     apiKey: config.apiKey,
     baseUrl: config.baseUrl,
+    timeoutMs: 10_000,
   });
 }
 
 // ---- Inference --------------------------------------------------------------
 
 export function listModels(config) {
-  return callApi('/models', { apiKey: config.apiKey, baseUrl: config.baseUrl });
+  return callApi('/models', { apiKey: config.apiKey, baseUrl: config.baseUrl, timeoutMs: 10_000 });
 }
 
 export function chatCompletion(config, messages, options = {}) {
@@ -178,6 +213,7 @@ export function chatCompletion(config, messages, options = {}) {
     apiKey: config.apiKey,
     baseUrl: config.baseUrl,
     body: { model: model ?? config.defaultModel, messages, stream },
+    timeoutMs: 30_000,
   });
 }
 
@@ -189,9 +225,14 @@ export function submitJob(config, job) {
     apiKey: config.apiKey,
     baseUrl: config.baseUrl,
     body: job,
+    timeoutMs: 30_000,
   });
 }
 
 export function getJobStatus(config, jobId) {
-  return callApi(`/jobs/${jobId}`, { apiKey: config.apiKey, baseUrl: config.baseUrl });
+  return callApi(`/jobs/${jobId}`, {
+    apiKey: config.apiKey,
+    baseUrl: config.baseUrl,
+    timeoutMs: 10_000,
+  });
 }

package/src/badgr.js

@@ -45,6 +45,15 @@ ${chalk.bold('EXAMPLES')}
   badgr run python train.py --gpu A100
   badgr serve meta-llama/Llama-3.1-8B-Instruct --gpu L40S
 
+  ${chalk.dim('# Pass environment variables:')}
+  badgr run python train.py --env HF_TOKEN=$HF_TOKEN --env DATASET=my/data
+
+  ${chalk.dim('# Serve an embedding model:')}
+  badgr serve BAAI/bge-large-en-v1.5 --task embed
+
+  ${chalk.dim('# Serve a custom container (Diffusers, Whisper, etc.):')}
+  badgr serve --image ghcr.io/my-org/diffusers-api:latest --gpu L40S --env MODEL_ID=flux
+
   ${chalk.dim('# Add safety caps:')}
   badgr run python train.py --max-runtime 60 --max-cost 5
 
@@ -59,6 +68,7 @@ ${chalk.bold('badgr run OPTIONS')}
   --tier 1               Managed provider routing (default)
   --tier 2               Marketplace provider routing, lower-cost options
   --image <image>        Docker image (default: python:3.11-slim)
+  --env KEY=VALUE        Set an environment variable (repeatable)
   --count <n>            Number of GPUs (default: 1)
   --region US|EU|AU      Region preference
   --max-price <$/hr>     Hard spend cap per GPU-hour
@@ -68,11 +78,15 @@ ${chalk.bold('badgr run OPTIONS')}
 
 ${chalk.bold('badgr serve OPTIONS')}
   --gpu <type>           GPU type (default: auto — inferred from model size)
+  --image <image>        Serve a custom container instead of a HuggingFace model
+  --task <task>          vLLM task override, e.g. embed for embedding models
+  --env KEY=VALUE        Set an environment variable (repeatable)
   --tier 1               Managed provider routing (default)
   --tier 2               Marketplace provider routing, lower-cost options
   --count <n>            Number of GPUs (default: 1)
   --region US|EU|AU      Region preference
   --max-price <$/hr>     Hard spend cap per GPU-hour
+  --health-path <path>   Readiness path to poll (auto-detected for comfyui → /system_stats)
   --no-wait              Skip endpoint health check
 
 ${chalk.bold('AFTER SERVING')}