ddpsrun 0.1.0__tar.gz

ddpsrun-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 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, whether in Source or
+      Object form, 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 any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to 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 otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated 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 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 a Contribution incorporated 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, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, 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 copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   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 redistributing 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 consequential 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 any and 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 act 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 file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 DDPS Lab
+
+   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.

ddpsrun-0.1.0/PKG-INFO

@@ -0,0 +1,182 @@
+Metadata-Version: 2.4
+Name: ddpsrun
+Version: 0.1.0
+Summary: Submit a GPU job and get results back. No kubectl, no cloud account.
+Author: DDPS Lab
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/ddps-lab/pacsrun-gw
+Project-URL: Repository, https://github.com/ddps-lab/pacsrun-gw
+Project-URL: Issues, https://github.com/ddps-lab/pacsrun-gw/issues
+Keywords: gpu,kubernetes,batch,jobs,machine-learning,cloud
+Classifier: Development Status :: 3 - Alpha
+Classifier: Environment :: Console
+Classifier: Intended Audience :: Science/Research
+Classifier: Intended Audience :: Developers
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: System :: Distributed Computing
+Classifier: Typing :: Typed
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: requests>=2.31
+Requires-Dist: PyYAML>=6.0
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0; extra == "dev"
+Requires-Dist: responses>=0.25; extra == "dev"
+Dynamic: license-file
+
+# ddpsrun
+
+**Submit a GPU job. Get results back. No `kubectl`, no cloud account, no VM to babysit.**
+
+`ddpsrun` is the front door to PACSrun, a Kubernetes-native batch job system that rents GPUs from
+whichever vendor is cheapest for the shape you asked for — AWS, GCP or RunPod — runs your code
+there, and puts the results in object storage. You describe the job; you never see the machine.
+
+```console
+$ ddpsrun login <token>
+$ ddpsrun estimate -f job.yaml
+$ ddpsrun submit -f job.yaml
+$ ddpsrun logs <job-id> --follow
+```
+
+## Why it exists
+
+A researcher who wants a GPU for two hours has three bad options today: get a cloud account and
+learn its console, get `kubectl` access to somebody's cluster, or ask a person. Each of those
+teaches infrastructure to somebody whose job is not infrastructure.
+
+The alternative here is that **a batch job is the unit**. You hand over a job description and a
+program. The platform decides which machine to rent, rents it, runs your code, brings the output
+home, and hands the machine back. When it goes wrong you get an exit code and a sentence, not a
+half-configured VM.
+
+## Install
+
+```console
+pip install ddpsrun
+```
+
+Two dependencies, `requests` and `PyYAML`, and that is deliberate: this package installs next to
+your research code, so every extra dependency is one that can fight with something you have
+pinned. No `click`, no `rich`, no `pydantic`.
+
+Python 3.9 or newer.
+
+## Configure
+
+`ddpsrun` needs a server URL and a token. Ask whoever runs your deployment for both.
+
+```console
+$ export DDPSRUN_SERVER=https://<your-gateway-url>
+$ ddpsrun login <token>
+```
+
+`login` writes them to `~/.config/ddpsrun/config.json` with mode 0600, or to
+`$XDG_CONFIG_HOME/ddpsrun` when that is set. For CI, where a file is the wrong shape, set
+`DDPSRUN_TOKEN` in the environment and skip `login` entirely.
+
+## The commands
+
+| | |
+|---|---|
+| `login` / `logout` | store and remove the server URL and token |
+| `explain` | what this deployment can do, in prose — run it first |
+| `schema` | the job description's fields and their types |
+| `estimate` | what a job would cost and how long it would take, before you spend anything |
+| `validate` | check a job description without submitting it |
+| `submit` | submit it |
+| `status` / `watch` | where a job is now; `watch` follows until it ends |
+| `logs` | your program's own output, `--follow` to stream |
+| `stats` | GPU utilisation, memory, temperature and power while the job runs |
+| `cancel` | stop a job and hand its machine back |
+
+Exit codes are contractual: **0** it worked, **1** the server refused or a `validate` finding would
+stop the job, **2** the command was wrong or there are no credentials.
+
+## Writing a job
+
+A job description is YAML:
+
+```yaml
+image: nvcr.io/nvidia/pytorch:24.10-py3
+command: ["/bin/bash", "-c"]
+args:
+  - |
+    python train.py --epochs 3
+resources:
+  gpus:
+    name: L4
+    count: 1
+resultPath: s3://<your-bucket>/runs/my-experiment/
+```
+
+Run `ddpsrun schema` for every field and `ddpsrun explain` for what your deployment allows.
+
+**Do not guess the GPU or the runtime.** `ddpsrun estimate` answers both from measured data, and
+guessing is how a job ends up on a card several times more expensive than it needed.
+
+## Using it from an AI coding agent
+
+This repository ships a [Claude Code](https://claude.com/claude-code) plugin. It teaches an agent
+five steps: read what the deployment allows, read your repository against the script contract,
+estimate rather than assume, validate and stop on a finding, and submit only after you approve.
+
+```
+/plugin marketplace add ddps-lab/pacsrun-gw
+/plugin install ddpsrun
+```
+
+The plugin's reference documents are in [`agent/references/`](agent/references/). The one worth
+reading yourself is [`script-contract.md`](agent/references/script-contract.md): a list of the ways
+a long training run dies in its last minute, each one taken from a run that did.
+
+## What this is not
+
+- **Not an interactive machine.** There is no SSH and no shell into a running job. You submit a
+  program and read its output. If you need to poke at a live container, this is the wrong tool
+  today.
+- **Not a scheduler you host.** `ddpsrun` is a client. Somebody has to run the gateway and the
+  PACSrun operator; see [`docs/`](docs/) if that somebody is you.
+- **Not free of limits.** A job's credentials for writing results last twelve hours, which is
+  AWS's hard maximum for a role session and not a setting anyone can raise. A run longer than that
+  must checkpoint and resume, and the driver warns half an hour before the deadline.
+
+## Repository layout
+
+| | |
+|---|---|
+| `cli/` | the `ddpsrun` package published to PyPI |
+| `server/` | the gateway: authenticates users, talks to Kubernetes |
+| `agent/` | the Claude Code plugin — one skill, four reference documents |
+| `ui/` | a small static web front end (`index.html`, `app.js`, `style.css`) |
+| `terraform/` | the deployment: Lambda, Cognito, S3, CloudFront |
+| `docs/` | seventeen design documents, numbered in reading order |
+
+## Development
+
+```console
+$ pip install -e 'cli/[dev]'      # the client
+$ pip install -e 'server/[dev]'   # the gateway
+$ pytest cli/tests server/tests
+```
+
+Both halves live in one repository so the two sides of an API change land in one commit. They share
+nothing else: the client never imports the Kubernetes libraries, and the server never imports the
+browser login flow.
+
+**No account identifiers in this repository.** Documents and code use placeholders —
+`<ACCOUNT_ID>`, `<RESULT_BUCKET>` — and CI checks every push for AWS account numbers, access keys,
+GitHub and RunPod tokens, private keys, and Google OAuth secrets.
+
+## License
+
+Apache-2.0. See [`LICENSE`](LICENSE).

ddpsrun-0.1.0/README.md

@@ -0,0 +1,147 @@
+# ddpsrun
+
+**Submit a GPU job. Get results back. No `kubectl`, no cloud account, no VM to babysit.**
+
+`ddpsrun` is the front door to PACSrun, a Kubernetes-native batch job system that rents GPUs from
+whichever vendor is cheapest for the shape you asked for — AWS, GCP or RunPod — runs your code
+there, and puts the results in object storage. You describe the job; you never see the machine.
+
+```console
+$ ddpsrun login <token>
+$ ddpsrun estimate -f job.yaml
+$ ddpsrun submit -f job.yaml
+$ ddpsrun logs <job-id> --follow
+```
+
+## Why it exists
+
+A researcher who wants a GPU for two hours has three bad options today: get a cloud account and
+learn its console, get `kubectl` access to somebody's cluster, or ask a person. Each of those
+teaches infrastructure to somebody whose job is not infrastructure.
+
+The alternative here is that **a batch job is the unit**. You hand over a job description and a
+program. The platform decides which machine to rent, rents it, runs your code, brings the output
+home, and hands the machine back. When it goes wrong you get an exit code and a sentence, not a
+half-configured VM.
+
+## Install
+
+```console
+pip install ddpsrun
+```
+
+Two dependencies, `requests` and `PyYAML`, and that is deliberate: this package installs next to
+your research code, so every extra dependency is one that can fight with something you have
+pinned. No `click`, no `rich`, no `pydantic`.
+
+Python 3.9 or newer.
+
+## Configure
+
+`ddpsrun` needs a server URL and a token. Ask whoever runs your deployment for both.
+
+```console
+$ export DDPSRUN_SERVER=https://<your-gateway-url>
+$ ddpsrun login <token>
+```
+
+`login` writes them to `~/.config/ddpsrun/config.json` with mode 0600, or to
+`$XDG_CONFIG_HOME/ddpsrun` when that is set. For CI, where a file is the wrong shape, set
+`DDPSRUN_TOKEN` in the environment and skip `login` entirely.
+
+## The commands
+
+| | |
+|---|---|
+| `login` / `logout` | store and remove the server URL and token |
+| `explain` | what this deployment can do, in prose — run it first |
+| `schema` | the job description's fields and their types |
+| `estimate` | what a job would cost and how long it would take, before you spend anything |
+| `validate` | check a job description without submitting it |
+| `submit` | submit it |
+| `status` / `watch` | where a job is now; `watch` follows until it ends |
+| `logs` | your program's own output, `--follow` to stream |
+| `stats` | GPU utilisation, memory, temperature and power while the job runs |
+| `cancel` | stop a job and hand its machine back |
+
+Exit codes are contractual: **0** it worked, **1** the server refused or a `validate` finding would
+stop the job, **2** the command was wrong or there are no credentials.
+
+## Writing a job
+
+A job description is YAML:
+
+```yaml
+image: nvcr.io/nvidia/pytorch:24.10-py3
+command: ["/bin/bash", "-c"]
+args:
+  - |
+    python train.py --epochs 3
+resources:
+  gpus:
+    name: L4
+    count: 1
+resultPath: s3://<your-bucket>/runs/my-experiment/
+```
+
+Run `ddpsrun schema` for every field and `ddpsrun explain` for what your deployment allows.
+
+**Do not guess the GPU or the runtime.** `ddpsrun estimate` answers both from measured data, and
+guessing is how a job ends up on a card several times more expensive than it needed.
+
+## Using it from an AI coding agent
+
+This repository ships a [Claude Code](https://claude.com/claude-code) plugin. It teaches an agent
+five steps: read what the deployment allows, read your repository against the script contract,
+estimate rather than assume, validate and stop on a finding, and submit only after you approve.
+
+```
+/plugin marketplace add ddps-lab/pacsrun-gw
+/plugin install ddpsrun
+```
+
+The plugin's reference documents are in [`agent/references/`](agent/references/). The one worth
+reading yourself is [`script-contract.md`](agent/references/script-contract.md): a list of the ways
+a long training run dies in its last minute, each one taken from a run that did.
+
+## What this is not
+
+- **Not an interactive machine.** There is no SSH and no shell into a running job. You submit a
+  program and read its output. If you need to poke at a live container, this is the wrong tool
+  today.
+- **Not a scheduler you host.** `ddpsrun` is a client. Somebody has to run the gateway and the
+  PACSrun operator; see [`docs/`](docs/) if that somebody is you.
+- **Not free of limits.** A job's credentials for writing results last twelve hours, which is
+  AWS's hard maximum for a role session and not a setting anyone can raise. A run longer than that
+  must checkpoint and resume, and the driver warns half an hour before the deadline.
+
+## Repository layout
+
+| | |
+|---|---|
+| `cli/` | the `ddpsrun` package published to PyPI |
+| `server/` | the gateway: authenticates users, talks to Kubernetes |
+| `agent/` | the Claude Code plugin — one skill, four reference documents |
+| `ui/` | a small static web front end (`index.html`, `app.js`, `style.css`) |
+| `terraform/` | the deployment: Lambda, Cognito, S3, CloudFront |
+| `docs/` | seventeen design documents, numbered in reading order |
+
+## Development
+
+```console
+$ pip install -e 'cli/[dev]'      # the client
+$ pip install -e 'server/[dev]'   # the gateway
+$ pytest cli/tests server/tests
+```
+
+Both halves live in one repository so the two sides of an API change land in one commit. They share
+nothing else: the client never imports the Kubernetes libraries, and the server never imports the
+browser login flow.
+
+**No account identifiers in this repository.** Documents and code use placeholders —
+`<ACCOUNT_ID>`, `<RESULT_BUCKET>` — and CI checks every push for AWS account numbers, access keys,
+GitHub and RunPod tokens, private keys, and Google OAuth secrets.
+
+## License
+
+Apache-2.0. See [`LICENSE`](LICENSE).

ddpsrun-0.1.0/ddpsrun/__init__.py

@@ -0,0 +1,7 @@
+"""ddpsrun — submit a GPU job and get results back.
+
+The command is `ddpsrun`. It talks to a gateway server over HTTPS and needs no
+kubectl, no kubeconfig, and no cloud account. See `docs/00-overview.md`.
+"""
+
+__version__ = "0.1.0"