Reason Harbor adapter
Run Reason as an agent in Harbor. Harbor starts the task container and grades the result. The adapter installs the published Reason CLI in that container, checks its checksum, and starts it as a worker; the agent runs as a normal Reason Session. Your API key stays on your machine; the container only receives a one-use enrollment ticket.
Install
uv pip install reason-machines-harbor
This installs Harbor 0.22.0. For cloud environments, add the matching Harbor
extra, for example uv pip install "harbor[modal]==0.22.0".
Run
Get a Reason API key with
run, sessions:read, deployment:read, devices:read, devices:write,
devices:use and org:write, and enable the model under
Models.
export REASON_API_KEY="YOUR_REASON_API_KEY"
DOCKER_DEFAULT_PLATFORM=linux/amd64 harbor run \
--dataset datacurve/deep-swe-1-1 --n-tasks 1 \
--agent reasonmachines_harbor:ReasonAgent \
--model openai/gpt-6-luna \
--ak reasoning_effort=xhigh \
--allow-agent-host api.reasonmachines.com \
--allow-agent-host relay.reasonmachines.com \
--env reasonmachines_harbor.environment:ReasonDockerEnvironment
The worker connects out to the Reason API and relay, so both
--allow-agent-host flags are required, even for offline tasks.
Agent kwarg (--ak) |
Default | Meaning |
|---|---|---|
reasoning_effort |
medium |
minimal, low, medium, high, xhigh or max |
mode |
ephemeral |
ephemeral: a new single-use workspace per trial, with memory and skills on. standard: your own workspace |
runtime_profile |
runtime/reason-agent-1.2 in ephemeral mode; the server default in standard mode |
A harness listed by GET /v3/deployment. The default is the frozen Reason Agent 1.2 release: it never changes, and its trials install the CLI and agent tools it pins (CLI 0.2.151). Name an earlier release to rerun it, for example runtime/reason-v7-2026-10; runtime/reason-c2-tools-v7 runs the deployment's current default instead |
Ephemeral mode needs an owner or admin key of a workspace with paid model
access. To bill the model to your own provider account, connect its API key
under Models and pass the
model as byok:<provider>:<model>, for example byok:openai:gpt-6-luna.
To run the full benchmarks and reproduce our results, see reason-machines/benchmark.
Source
reason-machines/reason-machines-harbor
is a read-only copy of the adapter in the Reason monorepo, where it is
developed and tested. Releases are tagged vX.Y.Z.
1 maintainer
Metadata
1 maintainer
Release files for reason-machines-harbor 0.3.38
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| reason_machines_harbor-0.3.38.tar.gz | 209.3 kB | With provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| reason_machines_harbor-0.3.38-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 256.8 kB
Release files / reason_machines_harbor-0.3.38.tar.gz
| Download URL | reason_machines_harbor-0.3.38.tar.gz |
|---|---|
| Size | 209.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
62159fa256c215755d2f60c75b96fa0ab7fb4c82326560eb7600df0bb9e9c57a
|
|
BLAKE2b-256 checksum How to use checksums |
634a46ca5d0cbcc762da1099a8519ceb72073a1e334afaf161c902d7b73352fa
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 25, 2026.
Transparency logRelease files / reason_machines_harbor-0.3.38-py3-none-any.whl
| Download URL | reason_machines_harbor-0.3.38-py3-none-any.whl |
|---|---|
| Size | 47.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f818bfff02845439380930bb0465835dc5c5c4b46833ef7c43d8bf73fbbc929e
|
|
BLAKE2b-256 checksum How to use checksums |
0eb8a13b7f72da8988784ade3cfddb68df25d5adec7205b2b95cb602e426bec4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 25, 2026.
Transparency logSecurity for reason-machines-harbor 0.3.38
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for reason_machines_harbor-0.3.38.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 25, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
