harbor-dsh-evolution
Harbor-side integration for DeepSeek Harness Candidate evolution.
It provides:
DshCandidateAgent: verifies and uploads an immutable Candidate, installs its locked npm dependencies, and runs it through Harbor's ACP runner.EvolutionPlugin: binds each Job to Candidate, Dataset Manifest, Evaluation Stack Manifest, Context v2, Architecture Doctor, Trial assessments, Population report, and Summary.harbor-dsh: initializes strict projects; validates/snapshots Candidates, Datasets, and Stacks; previews Context v2; diagnoses architecture; summarizes Jobs; and runs the deterministic Promotion Gate.
Install it into the same Python environment as Harbor so the plugin entry point is discoverable:
uv venv .venv
uv pip install --python .venv/bin/python harbor-dsh-evolution
source .venv/bin/activate
harbor plugins list
harbor-dsh --help
Development from this repository:
uv sync
uv run harbor plugins list
uv run harbor-dsh --help
uv run harbor-dsh dataset validate ../../examples/deep-research/task --project-root ../..
uv run harbor-dsh stack validate ../../examples/deep-research/.harbor/evaluation-stack.yml --project-root ../..
uv run pytest
uv build
Harbor and this package must be installed into the same Python environment for the dsh-evolution entry point to appear in harbor plugins list.
snapshot derives Candidate id and version from package.json unless explicitly supplied. Context v1 is not accepted. Promotion requires Context v2 and emits structured mismatch, artifact, infrastructure, metric, and regression reason codes.
1 maintainer
Release files for harbor-dsh-evolution 0.8.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| harbor_dsh_evolution-0.8.0.tar.gz | 234.4 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| harbor_dsh_evolution-0.8.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 324.7 kB
Release files / harbor_dsh_evolution-0.8.0.tar.gz
| Download URL | harbor_dsh_evolution-0.8.0.tar.gz |
|---|---|
| Size | 234.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
8fe5e502582cb64bace74f8e5d9673e82b1730d067943fd23420ccb6579f3796
|
|
BLAKE2b-256 checksum How to use checksums |
df2880fae882cb5d4c96206ae29e48300c12ecfb96d27b996fd512ca8f109c43
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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 Aug 30, 2026.
Transparency logRelease files / harbor_dsh_evolution-0.8.0-py3-none-any.whl
| Download URL | harbor_dsh_evolution-0.8.0-py3-none-any.whl |
|---|---|
| Size | 90.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
aa7f9ef40125d40e58560e0d3772abdc2f2df359e575b81f5116e705649e9f83
|
|
BLAKE2b-256 checksum How to use checksums |
d5896ebb69d3a05b02d0916bb3436d355b0235473f8606073581960121d633ea
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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 Aug 30, 2026.
Transparency log
