badgr-cli 1.1.0 → 1.1.2
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/LICENSE +207 -0
- package/README.md +135 -3
- package/package.json +44 -2
- package/src/api.js +16 -0
- package/src/badgr.js +2 -2
- package/src/commands/batch.js +11 -0
- package/src/commands/comfyui.js +31 -15
- package/src/commands/embed.js +13 -10
- package/src/commands/launch.js +8 -1
- package/src/commands/login.js +75 -20
- package/src/commands/run.js +45 -13
- package/src/commands/sbatch.js +6 -1
- package/src/commands/serve.js +44 -30
- package/src/commands/train.js +8 -12
- package/src/commands/transcribe.js +13 -10
- package/src/envFlag.js +10 -0
- package/src/onboarding.js +8 -1
- package/src/progress.js +48 -0
- package/tests/agent-images.test.js +0 -17
- package/tests/api.test.js +0 -168
- package/tests/artifactDownload.test.js +0 -113
- package/tests/artifacts.test.js +0 -168
- package/tests/batch.test.js +0 -641
- package/tests/browser.test.js +0 -51
- package/tests/capacity.test.js +0 -68
- package/tests/commands.test.js +0 -417
- package/tests/config.test.js +0 -96
- package/tests/connect.test.js +0 -83
- package/tests/detect.test.js +0 -191
- package/tests/down.test.js +0 -150
- package/tests/errors.test.js +0 -130
- package/tests/fallback-timeout.test.js +0 -41
- package/tests/fanout.test.js +0 -124
- package/tests/gpu-doctor-classifiers.test.js +0 -402
- package/tests/gpu-doctor-doctor.test.js +0 -304
- package/tests/gpu-doctor-probe-cache.test.js +0 -110
- package/tests/gpu-doctor-probes.test.js +0 -257
- package/tests/heartbeat.test.js +0 -70
- package/tests/job-progress-poll.test.js +0 -136
- package/tests/launch-command-argv.test.js +0 -93
- package/tests/launch-readiness.test.js +0 -403
- package/tests/launch.test.js +0 -440
- package/tests/onboarding.test.js +0 -134
- package/tests/productized-dry-run.test.js +0 -141
- package/tests/productized-runners.test.js +0 -237
- package/tests/pull.test.js +0 -266
- package/tests/rerun.test.js +0 -94
- package/tests/restart.test.js +0 -88
- package/tests/router.test.js +0 -98
- package/tests/run-lifecycle.test.js +0 -1054
- package/tests/sbatch.test.js +0 -190
- package/tests/secrets.test.js +0 -16
- package/tests/serve-apps.test.js +0 -189
- package/tests/serve-lifecycle.test.js +0 -931
- package/tests/slurm.test.js +0 -77
- package/tests/spec.test.js +0 -201
- package/tests/status.test.js +0 -73
- package/tests/store.test.js +0 -187
- package/tests/task.test.js +0 -109
- package/tests/template.test.js +0 -556
- package/tests/train-lora-dataset.test.js +0 -176
- package/tests/upload.test.js +0 -79
- package/tests/workload-rerun.test.js +0 -56
- package/tests/workload-spec.test.js +0 -180
- package/tests/workload-templates.test.js +0 -865
- package/tests/workload-workspace-paths.test.js +0 -46
package/LICENSE
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship made available under
|
|
36
|
+
the License, as indicated by a copyright notice that is included in
|
|
37
|
+
or attached to the work (an example is provided in the Appendix below).
|
|
38
|
+
|
|
39
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
40
|
+
form, that is based on (or derived from) the Work and for which the
|
|
41
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
42
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
43
|
+
of this License, Derivative Works shall not include works that remain
|
|
44
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
45
|
+
the Work and Derivative Works thereof.
|
|
46
|
+
|
|
47
|
+
"Contribution" shall mean, as submitted to the Licensor for inclusion
|
|
48
|
+
in the Work by the copyright owner or by an individual or Legal Entity
|
|
49
|
+
authorized to submit on behalf of the copyright owner. For the purposes
|
|
50
|
+
of this definition, "submitted" means any form of electronic, verbal,
|
|
51
|
+
or written communication sent to the Licensor or its representatives,
|
|
52
|
+
including but not limited to communication on electronic mailing lists,
|
|
53
|
+
source code control systems, and issue tracking systems that are managed
|
|
54
|
+
by, or on behalf of, the Licensor for the purpose of discussing and
|
|
55
|
+
improving the Work, but excluding communication that is conspicuously
|
|
56
|
+
marked or designated in writing by the copyright owner as "Not a
|
|
57
|
+
Contribution."
|
|
58
|
+
|
|
59
|
+
"Contributor" shall mean Licensor and any Legal Entity on behalf of
|
|
60
|
+
whom a Contribution has been received by the Licensor and included
|
|
61
|
+
within the Work.
|
|
62
|
+
|
|
63
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
64
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
65
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
66
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
67
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
68
|
+
Work and such Derivative Works in Source or Object form.
|
|
69
|
+
|
|
70
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
71
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
72
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
73
|
+
(except as stated in this section) patent license to make, have made,
|
|
74
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
75
|
+
where such license applies only to those patent claims licensable
|
|
76
|
+
by such Contributor that are necessarily infringed by their
|
|
77
|
+
Contribution(s) alone or by the combination of their Contribution(s)
|
|
78
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
79
|
+
institute patent litigation against any entity (including a cross-claim
|
|
80
|
+
or counterclaim in a lawsuit) alleging that the Work or any
|
|
81
|
+
Contribution embodied within the Work constitutes direct or
|
|
82
|
+
contributory patent infringement, then any patent licenses granted to
|
|
83
|
+
You under this License for that Work shall terminate as of the date
|
|
84
|
+
such litigation is filed.
|
|
85
|
+
|
|
86
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
87
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
88
|
+
modifications, and in Source or Object form, provided that You
|
|
89
|
+
meet the following conditions:
|
|
90
|
+
|
|
91
|
+
(a) You must give any other recipients of the Work or Derivative
|
|
92
|
+
Works a copy of this License; and
|
|
93
|
+
|
|
94
|
+
(b) You must cause any modified files to carry prominent notices
|
|
95
|
+
stating that You changed the files; and
|
|
96
|
+
|
|
97
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
98
|
+
that You distribute, all copyright, patent, trademark, and
|
|
99
|
+
attribution notices from the Source form of the Work,
|
|
100
|
+
excluding those notices that do not pertain to any part of
|
|
101
|
+
the Derivative Works; and
|
|
102
|
+
|
|
103
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
104
|
+
distribution, You must include a readable copy of the
|
|
105
|
+
attribution notices contained within such NOTICE file, in
|
|
106
|
+
at least one of the following places: within a NOTICE text
|
|
107
|
+
file distributed as part of the Derivative Works; within
|
|
108
|
+
the Source form or documentation, if provided along with the
|
|
109
|
+
Derivative Works; or, within a display generated by the
|
|
110
|
+
Derivative Works, if and wherever such third-party notices
|
|
111
|
+
normally appear. The contents of the NOTICE file are for
|
|
112
|
+
informational purposes only and do not modify the License.
|
|
113
|
+
You may add Your own attribution notices within Derivative
|
|
114
|
+
Works that You distribute, alongside or as an addendum to
|
|
115
|
+
the NOTICE text from the Work, provided that such additional
|
|
116
|
+
attribution notices cannot be construed as modifying the License.
|
|
117
|
+
|
|
118
|
+
You may add Your own license statement for Your modifications and
|
|
119
|
+
may provide additional grant of rights to use, copy, modify, merge,
|
|
120
|
+
publish, distribute, sublicense, and/or sell copies of the Work,
|
|
121
|
+
and to permit persons to whom the Work is furnished to do so,
|
|
122
|
+
subject to the following conditions:
|
|
123
|
+
|
|
124
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
125
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
126
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
127
|
+
this License, without any additional terms or conditions.
|
|
128
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
129
|
+
the terms of any separate license agreement you may have executed
|
|
130
|
+
with Licensor regarding such Contributions.
|
|
131
|
+
|
|
132
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
133
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
134
|
+
except as required for reasonable and customary use in describing the
|
|
135
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
136
|
+
|
|
137
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
138
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
139
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
140
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
141
|
+
implied, including, without limitation, any warranties or conditions
|
|
142
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
143
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
144
|
+
appropriateness of using or reproducing the Work and assume any
|
|
145
|
+
risks associated with Your exercise of permissions under this License.
|
|
146
|
+
|
|
147
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
148
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
149
|
+
unless required by applicable law (such as deliberate and grossly
|
|
150
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
151
|
+
liable to You for damages, including any direct, indirect, special,
|
|
152
|
+
incidental, or exemplary damages of any character arising as a
|
|
153
|
+
result of this License or out of the use or inability to use the
|
|
154
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
155
|
+
work stoppage, computer failure or malfunction, or all other
|
|
156
|
+
commercial damages or losses), even if such Contributor has been
|
|
157
|
+
advised of the possibility of such damages.
|
|
158
|
+
|
|
159
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
160
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
161
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
162
|
+
or other liability obligations and/or rights consistent with this
|
|
163
|
+
License. However, in accepting such obligations, You may offer such
|
|
164
|
+
conditions only on Your own behalf and on Your sole responsibility,
|
|
165
|
+
not on behalf of any other Contributor, and only if You agree to
|
|
166
|
+
indemnify, defend, and hold each Contributor harmless for any
|
|
167
|
+
liability incurred by, or claims asserted against, such Contributor
|
|
168
|
+
by reason of your accepting any such warranty or additional liability.
|
|
169
|
+
|
|
170
|
+
END OF TERMS AND CONDITIONS
|
|
171
|
+
|
|
172
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
173
|
+
|
|
174
|
+
To apply the Apache License to your work, attach the following
|
|
175
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
176
|
+
replaced with your own identifying information. (Don't include
|
|
177
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
178
|
+
comment syntax for the format in use. Please also include a
|
|
179
|
+
"NOTICE" file as part of the distribution with the contents:
|
|
180
|
+
|
|
181
|
+
Copyright [yyyy] [name of copyright owner]
|
|
182
|
+
|
|
183
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
184
|
+
you may not use this file except in compliance with the License.
|
|
185
|
+
You may obtain a copy of the License at
|
|
186
|
+
|
|
187
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
188
|
+
|
|
189
|
+
Unless required by applicable law or agreed to in writing, software
|
|
190
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
191
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
192
|
+
See the License for the specific language governing permissions and
|
|
193
|
+
limitations under the License.
|
|
194
|
+
|
|
195
|
+
Copyright 2024 AI Badgr
|
|
196
|
+
|
|
197
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
198
|
+
you may not use this file except in compliance with the License.
|
|
199
|
+
You may obtain a copy of the License at
|
|
200
|
+
|
|
201
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
202
|
+
|
|
203
|
+
Unless required by applicable law or agreed to in writing, software
|
|
204
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
205
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
206
|
+
See the License for the specific language governing permissions and
|
|
207
|
+
limitations under the License.
|
package/README.md
CHANGED
|
@@ -1,5 +1,10 @@
|
|
|
1
1
|
# badgr-cli
|
|
2
2
|
|
|
3
|
+
[](https://www.npmjs.com/package/badgr-cli)
|
|
4
|
+
[](https://www.npmjs.com/package/badgr-cli)
|
|
5
|
+
[](https://github.com/michaelmanly/badgr-cli/blob/main/LICENSE)
|
|
6
|
+
[](https://www.npmjs.com/package/badgr-cli)
|
|
7
|
+
|
|
3
8
|
Badgr supports many GPU workloads through two commands: `serve` for persistent endpoints, `run` for jobs.
|
|
4
9
|
|
|
5
10
|
> **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
|
|
|
8
13
|
npm install -g badgr-cli
|
|
9
14
|
```
|
|
10
15
|
|
|
16
|
+
**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)
|
|
17
|
+
|
|
11
18
|
---
|
|
12
19
|
|
|
13
20
|
## Quick start
|
|
@@ -36,6 +43,76 @@ badgr receipts
|
|
|
36
43
|
|
|
37
44
|
---
|
|
38
45
|
|
|
46
|
+
## Coding & testing agents: `badgr launch`
|
|
47
|
+
|
|
48
|
+
Run a coding agent or a test suite on a CPU VM with one command — no image, source, or `--max-cost` required for the four built-in workloads. Three separate things are going on here, worth keeping straight: **which agent CLI** runs (`cline`, `claude`, `codex`, `playwright`), **who pays for model usage** (Badgr, or your own Anthropic/OpenAI account), and **who provisions the VM and runs the command** (always Badgr).
|
|
49
|
+
|
|
50
|
+
```bash
|
|
51
|
+
badgr launch cline "Fix the checkout bug" # Badgr provides model access — no account to connect
|
|
52
|
+
badgr launch claude "Fix the checkout bug" # runs Claude Code — connect your Anthropic account
|
|
53
|
+
badgr launch codex "Write tests" # runs the Codex CLI — connect your OpenAI account
|
|
54
|
+
badgr launch playwright "Test the checkout flow" # no model account involved at all
|
|
55
|
+
```
|
|
56
|
+
|
|
57
|
+
**Authentication model:**
|
|
58
|
+
|
|
59
|
+
| Workload | CLI that runs | Who pays for model usage |
|
|
60
|
+
|----------|---------------|---------------------------|
|
|
61
|
+
| `cline` | Cline | Badgr provides and pays for model access |
|
|
62
|
+
| `claude` | Claude Code | Your Anthropic account — Badgr only provides the VM |
|
|
63
|
+
| `codex` | Codex CLI | Your OpenAI/ChatGPT account — Badgr only provides the VM |
|
|
64
|
+
| `playwright` | Playwright | No model account required |
|
|
65
|
+
|
|
66
|
+
Installing/running the `claude` or `codex` CLI doesn't by itself give a disposable Badgr VM model access — the CLI still needs to authenticate, and a VM's sign-in doesn't inherit from your laptop. `badgr launch claude`/`badgr launch codex` prompt inline the first time to connect your account and store it for next time; `cline` and `playwright` need nothing. Each workload picks its own VM size automatically (`small`, or `browser` for playwright's preinstalled Chromium) — override with `--size small|medium|browser`. A $2 default `--max-cost` applies unless you pass your own.
|
|
67
|
+
|
|
68
|
+
Today, "connect your account" means securely storing an API key (`ANTHROPIC_API_KEY` / `OPENAI_API_KEY`) — both Claude Code and the Codex CLI also support signing in via a Claude.ai/ChatGPT account, and a future version of `badgr connect` may add that OAuth flow instead of a pasted key; the one-time-connection UX is the same either way.
|
|
69
|
+
|
|
70
|
+
```bash
|
|
71
|
+
badgr connect anthropic --key sk-ant-... # connect your Anthropic account ahead of time (optional — badgr launch prompts inline if missing)
|
|
72
|
+
badgr connect # list what's already connected
|
|
73
|
+
badgr connect anthropic --remove # disconnect
|
|
74
|
+
```
|
|
75
|
+
|
|
76
|
+
Retrieve results after a run finishes:
|
|
77
|
+
|
|
78
|
+
```bash
|
|
79
|
+
badgr pull <deployment-id> # pull a code-editing agent's patch as a local git diff/branch
|
|
80
|
+
badgr artifacts <deployment-id> # download everything else — test reports, screenshots, traces
|
|
81
|
+
```
|
|
82
|
+
|
|
83
|
+
### Advanced escape hatch — any other command
|
|
84
|
+
|
|
85
|
+
For anything beyond the four built-in workloads, run an arbitrary command on a CPU VM the same way `badgr run` does for GPU jobs:
|
|
86
|
+
|
|
87
|
+
```bash
|
|
88
|
+
badgr launch . --max-cost 1 -- npm test
|
|
89
|
+
badgr launch https://github.com/user/repo --max-cost 1 -- python narrgo.py
|
|
90
|
+
```
|
|
91
|
+
|
|
92
|
+
Everything before `--` is a `badgr launch` flag; everything after `--` is passed to your command verbatim, including anything that looks like a flag (`badgr launch . -- claude --max-cost 1` sends `--max-cost 1` to `claude`, not to Badgr). The default runner image has no Node.js/npm — use `--image <image>` for anything that needs it.
|
|
93
|
+
|
|
94
|
+
| Flag | Default | Description |
|
|
95
|
+
|------|---------|-------------|
|
|
96
|
+
| `--cmd "<command>"` | — | Quoted command form, equivalent to `-- <command>` |
|
|
97
|
+
| `--image <image>` | CPU runtime default | Custom image instead of the default |
|
|
98
|
+
| `--detach` / `--no-detach` | detach | `launch` detaches by default; `--no-detach` streams logs and waits |
|
|
99
|
+
| `--env KEY=VALUE` | — | Environment variable (repeatable) — Badgr warns if a value looks like a secret |
|
|
100
|
+
| `--artifacts <path>` | — | Extra path to capture and upload (repeatable), e.g. `--artifacts playwright-report`. Retrieve with `badgr artifacts <id>` |
|
|
101
|
+
| `--max-cost <$>` | `$2` | Auto-stop when spend reaches this amount |
|
|
102
|
+
| `--max-runtime <min>` | 60 | Auto-stop after N minutes |
|
|
103
|
+
| `--region US\|EU\|AU` | — | Region preference |
|
|
104
|
+
| `--size small\|medium\|browser` | per-workload default | VM class override |
|
|
105
|
+
|
|
106
|
+
### `badgr task` — a labeled launch
|
|
107
|
+
|
|
108
|
+
```bash
|
|
109
|
+
badgr task "Run the Chromium tests and tell me what failed" --max-cost 1 -- npm run test:chromium
|
|
110
|
+
```
|
|
111
|
+
|
|
112
|
+
A thin wrapper over `badgr launch . -- <command>` — the description is printed for the human and otherwise discarded; the receipt and `badgr status` still key off the deployment ID like any other launch.
|
|
113
|
+
|
|
114
|
+
---
|
|
115
|
+
|
|
39
116
|
## Also try: image generation
|
|
40
117
|
|
|
41
118
|
```bash
|
|
@@ -78,7 +155,7 @@ badgr doctor --json
|
|
|
78
155
|
```
|
|
79
156
|
|
|
80
157
|
Run `badgr doctor --help` for the full flag list. Details in
|
|
81
|
-
[`docs/gpu-doctor.md`](
|
|
158
|
+
[`docs/gpu-doctor.md`](https://github.com/michaelmanly/gpu-ai/blob/main/docs/gpu-doctor.md).
|
|
82
159
|
|
|
83
160
|
---
|
|
84
161
|
|
|
@@ -86,11 +163,16 @@ Run `badgr doctor --help` for the full flag list. Details in
|
|
|
86
163
|
|
|
87
164
|
```text
|
|
88
165
|
login
|
|
166
|
+
connect
|
|
89
167
|
doctor
|
|
90
168
|
run
|
|
169
|
+
launch
|
|
170
|
+
task
|
|
91
171
|
serve
|
|
92
172
|
status
|
|
93
173
|
logs
|
|
174
|
+
pull
|
|
175
|
+
artifacts
|
|
94
176
|
down
|
|
95
177
|
receipts
|
|
96
178
|
test
|
|
@@ -99,16 +181,21 @@ test
|
|
|
99
181
|
| Command | What it does |
|
|
100
182
|
|---------|-------------|
|
|
101
183
|
| `badgr login` | Save API key to `~/.badgr/config.json` |
|
|
184
|
+
| `badgr connect <provider>` | Store a provider credential (`anthropic`, `openai`) for `badgr launch` |
|
|
102
185
|
| `badgr doctor` | Diagnose a GPU workload failure — read-only, no login needed |
|
|
103
186
|
| `badgr run <command>` | Run a one-off GPU job (any container command) |
|
|
187
|
+
| `badgr launch cline\|claude\|codex\|playwright "<task>"` | Run a coding/testing agent on a CPU VM — image + command auto-selected |
|
|
188
|
+
| `badgr task "<desc>" -- <command>` | Label + launch — thin wrapper over `badgr launch . -- <command>` |
|
|
104
189
|
| `badgr serve <model>` | Start a persistent OpenAI-compatible endpoint |
|
|
105
190
|
| `badgr status` | Show what's running and what's billing |
|
|
106
191
|
| `badgr logs <id>` | Fetch log output from a deployment |
|
|
192
|
+
| `badgr pull <id>` | Pull a code-editing agent's patch as a local git diff/branch |
|
|
193
|
+
| `badgr artifacts <id>` | Download non-patch outputs (test reports, screenshots, traces) |
|
|
107
194
|
| `badgr down <id>` | Terminate a deployment — stops billing immediately |
|
|
108
195
|
| `badgr receipts [n]` | Cost, route, and retry receipts (default 10) |
|
|
109
196
|
| `badgr test` | Run an end-to-end test (provision → run → teardown) |
|
|
110
197
|
|
|
111
|
-
More commands below, under [Advanced](#advanced): `comfyui`, `train`, `transcribe`, `embed`, `workload`, `workspace`, `capacity`, `billing`.
|
|
198
|
+
More commands below, under [Advanced](#advanced): `comfyui`, `train`, `transcribe`, `embed`, `workload`, `workspace`, `batch`, `sbatch`, `capacity`, `billing`.
|
|
112
199
|
|
|
113
200
|
`badgr serve` — for anything that needs a persistent endpoint: LLM serving, embeddings, image generation APIs, transcription APIs.
|
|
114
201
|
|
|
@@ -304,7 +391,7 @@ Badgr Auto selects the best eligible GPU for your workload. Add `--gpu <type>` o
|
|
|
304
391
|
| A100 | NVIDIA A100 | 40–80 GB | Training, inference |
|
|
305
392
|
| H100 | NVIDIA H100 | 80 GB | Large model training |
|
|
306
393
|
|
|
307
|
-
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](
|
|
394
|
+
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).
|
|
308
395
|
|
|
309
396
|
---
|
|
310
397
|
|
|
@@ -407,6 +494,51 @@ badgr workspace list
|
|
|
407
494
|
badgr workspace delete my-project
|
|
408
495
|
```
|
|
409
496
|
|
|
497
|
+
### `badgr batch` — generic containerized batch jobs
|
|
498
|
+
|
|
499
|
+
```bash
|
|
500
|
+
badgr batch run workload.yml
|
|
501
|
+
badgr batch status dep-abc123
|
|
502
|
+
badgr batch artifacts dep-abc123
|
|
503
|
+
badgr batch receipt dep-abc123
|
|
504
|
+
badgr batch compare dep-abc123 dep-def456
|
|
505
|
+
```
|
|
506
|
+
|
|
507
|
+
For CV/video/scientific batch, simulation, and physical-AI eval workloads — runs a container from a `workload.yml` spec and captures output artifacts automatically.
|
|
508
|
+
|
|
509
|
+
**Fan-out** — run the same program once per file in a directory, one deployment per input, in parallel:
|
|
510
|
+
|
|
511
|
+
```bash
|
|
512
|
+
badgr batch run workload.yml --fan-out ./scenarios
|
|
513
|
+
badgr batch run workload.yml --fan-out ./scenarios --max-concurrency 10
|
|
514
|
+
badgr batch run workload.yml --fan-out ./scenarios --only failed1.json,failed2.json
|
|
515
|
+
```
|
|
516
|
+
|
|
517
|
+
`workload.yml` must declare exactly one `inputs:` entry (the path that varies per task).
|
|
518
|
+
|
|
519
|
+
| Flag | Default | Description |
|
|
520
|
+
|------|---------|-------------|
|
|
521
|
+
| `--fan-out <dir>` | — | Run once per file in this directory instead of a single job |
|
|
522
|
+
| `--max-concurrency <n>` | 5 | Cap in-flight fan-out deployments |
|
|
523
|
+
| `--only <f1,f2>` | — | Rerun just the named input files |
|
|
524
|
+
| `--dry-run` | — | Preview the batch/fan-out plan without provisioning |
|
|
525
|
+
|
|
526
|
+
### `badgr sbatch` — existing Slurm scripts
|
|
527
|
+
|
|
528
|
+
```bash
|
|
529
|
+
badgr sbatch job.slurm
|
|
530
|
+
badgr sbatch job.slurm --dry-run
|
|
531
|
+
badgr sbatch array_job.slurm # #SBATCH --array=1-100 fans out into one deployment per task
|
|
532
|
+
badgr sbatch array_job.slurm --max-concurrency 10
|
|
533
|
+
```
|
|
534
|
+
|
|
535
|
+
Translates `--cpus-per-task`/`--mem`/`--gres`/`--time`/`--export` from a real `.slurm` file. `#SBATCH --array=...` directives fan out into bounded-concurrency deployments the same way `batch run --fan-out` does; unsupported directives (`--partition`, `--qos`, `--account`) print a visible warning but don't block translation of the rest.
|
|
536
|
+
|
|
537
|
+
| Flag | Default | Description |
|
|
538
|
+
|------|---------|-------------|
|
|
539
|
+
| `--max-concurrency <n>` | 5 | Cap in-flight array tasks |
|
|
540
|
+
| `--dry-run` | — | Preview the translated job without provisioning |
|
|
541
|
+
|
|
410
542
|
### Other commands
|
|
411
543
|
|
|
412
544
|
- `badgr capacity [--gpu <type>]` — check available GPU capacity right now
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "badgr-cli",
|
|
3
|
-
"version": "1.1.
|
|
3
|
+
"version": "1.1.2",
|
|
4
4
|
"description": "Badgr — run or serve GPU workloads from one command",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"bin": {
|
|
@@ -24,6 +24,14 @@
|
|
|
24
24
|
"engines": {
|
|
25
25
|
"node": ">=20.10.0"
|
|
26
26
|
},
|
|
27
|
+
"homepage": "https://aibadgr.com",
|
|
28
|
+
"repository": {
|
|
29
|
+
"type": "git",
|
|
30
|
+
"url": "https://github.com/michaelmanly/badgr-cli.git"
|
|
31
|
+
},
|
|
32
|
+
"bugs": {
|
|
33
|
+
"url": "https://github.com/michaelmanly/badgr-cli/issues"
|
|
34
|
+
},
|
|
27
35
|
"keywords": [
|
|
28
36
|
"gpu",
|
|
29
37
|
"cli",
|
|
@@ -31,11 +39,45 @@
|
|
|
31
39
|
"compute",
|
|
32
40
|
"gateway",
|
|
33
41
|
"openai",
|
|
42
|
+
"openai-compatible",
|
|
34
43
|
"workload",
|
|
35
44
|
"workspace",
|
|
36
45
|
"llm",
|
|
37
46
|
"inference",
|
|
38
|
-
"fine-tuning"
|
|
47
|
+
"fine-tuning",
|
|
48
|
+
"lora",
|
|
49
|
+
"vllm",
|
|
50
|
+
"gpu-cloud",
|
|
51
|
+
"cloud-gpu",
|
|
52
|
+
"gpu-rental",
|
|
53
|
+
"on-demand-gpu",
|
|
54
|
+
"serverless-gpu",
|
|
55
|
+
"gpu-provisioning",
|
|
56
|
+
"machine-learning",
|
|
57
|
+
"deep-learning",
|
|
58
|
+
"model-serving",
|
|
59
|
+
"model-training",
|
|
60
|
+
"training",
|
|
61
|
+
"huggingface",
|
|
62
|
+
"cuda",
|
|
63
|
+
"h100",
|
|
64
|
+
"a100",
|
|
65
|
+
"rtx-4090",
|
|
66
|
+
"coding-agent",
|
|
67
|
+
"ai-agent",
|
|
68
|
+
"claude-code",
|
|
69
|
+
"codex",
|
|
70
|
+
"playwright",
|
|
71
|
+
"comfyui",
|
|
72
|
+
"stable-diffusion",
|
|
73
|
+
"image-generation",
|
|
74
|
+
"transcription",
|
|
75
|
+
"whisper",
|
|
76
|
+
"embeddings",
|
|
77
|
+
"slurm",
|
|
78
|
+
"batch-jobs",
|
|
79
|
+
"devops",
|
|
80
|
+
"mlops"
|
|
39
81
|
],
|
|
40
82
|
"license": "Apache-2.0"
|
|
41
83
|
}
|
package/src/api.js
CHANGED
|
@@ -153,6 +153,22 @@ export function quoteRun(config, body) {
|
|
|
153
153
|
});
|
|
154
154
|
}
|
|
155
155
|
|
|
156
|
+
// Live, no-provisioning price/capacity check for a GPU dry-run preview (see
|
|
157
|
+
// backend run_serve_routes.py's GET /v1/capacity/suggestions). Used by every
|
|
158
|
+
// GPU-provisioning command's --dry-run to show a real observed rate instead
|
|
159
|
+
// of just the requested config — callers must treat a failure here as
|
|
160
|
+
// non-fatal (best-effort) and never let it block or delay the dry-run.
|
|
161
|
+
export function getCapacityPreview(config, { gpu, region, maxPrice } = {}) {
|
|
162
|
+
const params = new URLSearchParams({ gpu: gpu || 'RTX_4090' });
|
|
163
|
+
if (region) params.set('region', region);
|
|
164
|
+
if (maxPrice != null) params.set('max_price', String(maxPrice));
|
|
165
|
+
return callApi(`/capacity/suggestions?${params}`, {
|
|
166
|
+
apiKey: config.apiKey,
|
|
167
|
+
baseUrl: config.baseUrl,
|
|
168
|
+
timeoutMs: 8_000,
|
|
169
|
+
});
|
|
170
|
+
}
|
|
171
|
+
|
|
156
172
|
export function serveModel(config, body) {
|
|
157
173
|
return callApi('/serve', {
|
|
158
174
|
method: 'POST',
|
package/src/badgr.js
CHANGED
|
@@ -37,7 +37,7 @@ const HELP = `
|
|
|
37
37
|
${chalk.bold('badgr')} — run or serve GPU workloads from one command
|
|
38
38
|
|
|
39
39
|
${chalk.bold('COMMANDS')}
|
|
40
|
-
${chalk.cyan('badgr login')}
|
|
40
|
+
${chalk.cyan('badgr login')} Open a browser to log in (or: badgr login --key <value>)
|
|
41
41
|
${chalk.cyan('badgr connect <provider>')} Credential setup (badgr connect anthropic/openai) — also prompted inline by badgr launch if missing
|
|
42
42
|
${chalk.cyan('badgr detect <path>')} Inspect a project and report the GPU job Badgr would run
|
|
43
43
|
${chalk.cyan('badgr run <command>')} Run a one-off GPU job
|
|
@@ -265,7 +265,7 @@ async function main() {
|
|
|
265
265
|
}
|
|
266
266
|
|
|
267
267
|
switch (cmd) {
|
|
268
|
-
case 'login': return loginCommand(chalk, saveConfig);
|
|
268
|
+
case 'login': return loginCommand(chalk, saveConfig, rest);
|
|
269
269
|
case 'connect': return connectCommand(rest, chalk);
|
|
270
270
|
case 'detect': return detectCommand(config, rest, chalk);
|
|
271
271
|
case 'run': return runCommand(config, rest, chalk);
|
package/src/commands/batch.js
CHANGED
|
@@ -25,6 +25,7 @@ import { monitorBatchJob, fmtRuntime } from '../batch.js';
|
|
|
25
25
|
import { runFanOut, DEFAULT_CONCURRENCY } from '../fanout.js';
|
|
26
26
|
import { uploadBlob } from '../api.js';
|
|
27
27
|
import { downloadAndExtractArtifact } from '../artifactDownload.js';
|
|
28
|
+
import { printCapacityPreview, formatTierLabel } from '../progress.js';
|
|
28
29
|
import { logsCommand } from './logs.js';
|
|
29
30
|
|
|
30
31
|
// Server-side watchdog / batch.js reason strings, mapped to the vocabulary
|
|
@@ -240,17 +241,21 @@ async function runFanOutSubcommand(config, spec, flags, chalk, yamlPath) {
|
|
|
240
241
|
const [{ containerPath }] = spec.inputs;
|
|
241
242
|
const effectiveTier = normalizeTier(flags.tier);
|
|
242
243
|
const concurrency = flags.maxConcurrency ?? DEFAULT_CONCURRENCY;
|
|
244
|
+
const resolvedGpu = flags.gpu ? flags.gpu.toUpperCase().replace(/-/g, '_') : 'AUTO';
|
|
243
245
|
|
|
244
246
|
console.log(chalk.bold(`\n📦 Batch fan-out: ${spec.name}\n`));
|
|
245
247
|
console.log(` ${chalk.bold('Image:')} ${spec.image}`);
|
|
246
248
|
console.log(` ${chalk.bold('Command:')} ${spec.command.join(' ')}`);
|
|
247
249
|
console.log(` ${chalk.bold('Inputs dir:')} ${fanOutDir} (${files.length} task(s), max ${Math.min(concurrency, files.length)} concurrent)`);
|
|
250
|
+
console.log(` ${chalk.bold('GPU:')} ${resolvedGpu}`);
|
|
251
|
+
console.log(` ${chalk.bold('Tier:')} ${formatTierLabel(effectiveTier)}`);
|
|
248
252
|
console.log(` ${chalk.bold('Max cost:')} $${spec.maxCost.toFixed(2)} per task`);
|
|
249
253
|
console.log(` ${chalk.bold('Max runtime:')} ${spec.maxRuntimeMinutes}min per task`);
|
|
250
254
|
console.log();
|
|
251
255
|
|
|
252
256
|
if (flags.dryRun) {
|
|
253
257
|
console.log(chalk.bold(`⚡ Dry run — no GPU will be provisioned (${files.length} task(s) would be submitted)\n`));
|
|
258
|
+
await printCapacityPreview(chalk, config, { gpu: resolvedGpu, region: flags.region?.toUpperCase() });
|
|
254
259
|
return;
|
|
255
260
|
}
|
|
256
261
|
|
|
@@ -402,9 +407,14 @@ async function runSubcommand(config, args, chalk) {
|
|
|
402
407
|
return runFanOutSubcommand(config, spec, flags, chalk, yamlPath);
|
|
403
408
|
}
|
|
404
409
|
|
|
410
|
+
const resolvedGpu = flags.gpu ? flags.gpu.toUpperCase().replace(/-/g, '_') : 'AUTO';
|
|
411
|
+
const previewTier = normalizeTier(flags.tier);
|
|
412
|
+
|
|
405
413
|
console.log(chalk.bold(`\n📦 Batch: ${spec.name}\n`));
|
|
406
414
|
console.log(` ${chalk.bold('Image:')} ${spec.image}`);
|
|
407
415
|
console.log(` ${chalk.bold('Command:')} ${spec.command.join(' ')}`);
|
|
416
|
+
console.log(` ${chalk.bold('GPU:')} ${resolvedGpu}`);
|
|
417
|
+
console.log(` ${chalk.bold('Tier:')} ${formatTierLabel(previewTier)}`);
|
|
408
418
|
console.log(` ${chalk.bold('Max cost:')} $${spec.maxCost.toFixed(2)}`);
|
|
409
419
|
console.log(` ${chalk.bold('Max runtime:')} ${spec.maxRuntimeMinutes}min`);
|
|
410
420
|
if (spec.inputs.length) console.log(` ${chalk.bold('Inputs:')} ${spec.inputs.length} path(s)`);
|
|
@@ -413,6 +423,7 @@ async function runSubcommand(config, args, chalk) {
|
|
|
413
423
|
|
|
414
424
|
if (flags.dryRun) {
|
|
415
425
|
console.log(chalk.bold('⚡ Dry run — no GPU will be provisioned\n'));
|
|
426
|
+
await printCapacityPreview(chalk, config, { gpu: resolvedGpu, region: flags.region?.toUpperCase() });
|
|
416
427
|
return;
|
|
417
428
|
}
|
|
418
429
|
|