Skip to main content

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 tool install "harbor==0.25.0" --with "reason-machines-harbor>=0.3.44"

The adapter works with Harbor 0.22 to 0.25 and Python 3.12 or later. For cloud environments, add the matching Harbor extra, for example "harbor[e2b,modal]==0.25.0". To reproduce our published results, use the Harbor version the benchmark scripts pin.

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. Drop --n-tasks 1 to run the whole dataset. On e2b, use --env reasonmachines_harbor.environment:ReasonE2BEnvironment: it keeps the task image's environment variables, PATH included, which e2b otherwise drops.

Each trial's agent/ folder holds the Session as the model saw it (trajectory.json, ATIF), its link, status and cost (session.json) and what it ran on (receipt.json, deployment.json). API errors are reported by code, for example missing_scope or ephemeral_workspace_parent_payment_required.

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-1.3 in ephemeral mode; the server default in standard mode A harness listed by GET /v3/deployment. The default is the frozen Reason Agent 1.3 release: it never changes, and its trials install the CLI and agent tools it pins (CLI 0.2.625, agent-tools-2026-10-27). Name an earlier release to rerun it, for example runtime/reason-agent-1.2; 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.

License

Apache-2.0.

Metadata

Release files for reason-machines-harbor 0.3.46

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for reason-machines-harbor 0.3.46
File Size Uploaded Provenance Actions
reason_machines_harbor-0.3.46.tar.gz 215.1 kB With provenance Details for reason_machines_harbor-0.3.46.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for reason-machines-harbor 0.3.46
File Interpreter ABI Platform Actions
reason_machines_harbor-0.3.46-py3-none-any.whl Python 3 none any Details for reason_machines_harbor-0.3.46-py3-none-any.whl

Total release size: 267.8 kB

Release files / reason_machines_harbor-0.3.46.tar.gz

Download URL reason_machines_harbor-0.3.46.tar.gz
Size 215.1 kB
Tags Source
SHA-256 checksum
How to use checksums
e366cfbb7962234511dd7bb5c53960988fc530d920730f5955e7bb02a8f6c583
BLAKE2b-256 checksum
How to use checksums
9d6e9437b652b73ba42ddc2480cf480a9ec7f7654407629165719422b08cc4da
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 Nov 4, 2026.

Transparency log

Release files / reason_machines_harbor-0.3.46-py3-none-any.whl

Download URL reason_machines_harbor-0.3.46-py3-none-any.whl
Size 52.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
8c202348ba79850b84b32a0fd13194cb135e92f1f2636637caa470f728e73e7c
BLAKE2b-256 checksum
How to use checksums
833692ff1f9bb72fa8259c719c815ff407a676333a325172da965d63bc13adbd
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 Nov 4, 2026.

Transparency log

Security for reason-machines-harbor 0.3.46

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

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for reason_machines_harbor-0.3.46.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 Nov 4, 2026.

Transparency log

A 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.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page