mirror of
https://github.com/hanzoai/python-sdk.git
synced 2026-10-27 04:20:09 +00:00
zeekay
42124b1f45
The Python client now reaches what the Rust crate does and the server serves. Research covers every /v1/research route: record() files benchmarks, studies, runs and papers in one batch a kind; runs(), get_run() and compare() read them; grant(), revise() and retract() move consent and versions; the experiment plane and artifacts as before. Arena covers /v1/benchmark: catalog, leaderboard, claims (written with protocol and source), history, compare, presets, and runs, which queue a paid execution and are refused without confirm=True. wire holds the crate's Run, Benchmark, Measure, Study, Paper and Comparison field for field; canonical writes RFC 8785 bytes equal to the crate's (tests/vectors/rust.json, written by the crate); lineage and wal are the crate's records, and a WAL the crate wrote verifies here. capture() reads the harness commit (the diff's SHA-256 when dirty), the weights' SHA-256, host, CPU, GPU, device, dtype and packages, and apply() folds them into a run. runs(org=) sends no credential: the server answers ?org= only to a caller with no org. An org the token does not belong to is refused before the request, since the server would act in the home org. The command is hanzo-research; the native CLI owns `hanzo`.
73 lines
3.0 KiB
Python
73 lines
3.0 KiB
Python
"""Lineage narrows and never widens; records digest as the crate's do."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
import json
|
|
|
|
import pytest
|
|
from hanzo_research.lineage import (
|
|
ArtifactRef,
|
|
DataPurpose,
|
|
EnvironmentV1,
|
|
LineagePolicy,
|
|
ResearchEvent,
|
|
ContaminationError,
|
|
derive_lineage_policy,
|
|
verify_promotion_eligibility,
|
|
)
|
|
|
|
VECTORS = json.load(open(os.path.join(os.path.dirname(__file__), "vectors", "rust.json"), encoding="utf-8"))
|
|
|
|
|
|
def test_policy_propagation():
|
|
train = LineagePolicy.root(DataPurpose.TRAIN, True)
|
|
train.assert_trainable("source")
|
|
ev = LineagePolicy.root(DataPurpose.EVAL_ONLY, True)
|
|
assert not ev.derivation_allowed
|
|
with pytest.raises(ContaminationError):
|
|
ev.assert_trainable("eval_src")
|
|
derived = LineagePolicy.derive(DataPurpose.TEACHER_MINING, True, [train, ev])
|
|
assert derived.purpose is DataPurpose.EVAL_ONLY and not derived.derivation_allowed
|
|
clean = derive_lineage_policy(DataPurpose.TEACHER_MINING, True, [train])
|
|
assert clean.purpose is DataPurpose.TEACHER_MINING and clean.derivation_allowed
|
|
clean.assert_trainable("clean_child")
|
|
|
|
|
|
def test_promotion_eligibility():
|
|
root = LineagePolicy.root(DataPurpose.TRAIN, True)
|
|
mining = LineagePolicy.derive(DataPurpose.TEACHER_MINING, True, [root])
|
|
ckpt = LineagePolicy.derive(DataPurpose.TRAIN, True, [root, mining])
|
|
verify_promotion_eligibility("ckpt-a10", ckpt, [root, mining])
|
|
with pytest.raises(ContaminationError, match=r"ckpt-a10->transitive_ancestor\[0\] has derivation_allowed = false"):
|
|
verify_promotion_eligibility("ckpt-a10", ckpt, [LineagePolicy(DataPurpose.TRAIN, False)])
|
|
with pytest.raises(ContaminationError, match="purpose EvalOnly"):
|
|
verify_promotion_eligibility("ckpt-a10", LineagePolicy(DataPurpose.EVAL_ONLY, True), [])
|
|
|
|
|
|
def test_purposes_order_and_wire_names():
|
|
assert [p.value for p in DataPurpose] == ["train", "teacher_mining", "dev", "eval_only", "sealed_eval"]
|
|
assert DataPurpose.most_restrictive(DataPurpose.DEV, DataPurpose.TRAIN) is DataPurpose.DEV
|
|
assert DataPurpose.DEV.is_eval() and not DataPurpose.DEV.is_training_allowed()
|
|
|
|
|
|
def test_records_digest_as_the_crates():
|
|
r = VECTORS["records"]
|
|
assert LineagePolicy.load(r["policy"]["value"]).digest() == r["policy"]["digest"]
|
|
assert EnvironmentV1.load(r["environment"]["value"]).digest() == r["environment"]["digest"]
|
|
ev = ResearchEvent.load(r["event"]["value"])
|
|
assert ev.digest() == r["event"]["digest"]
|
|
assert (
|
|
ResearchEvent.new(
|
|
ev.run_id, ev.worker_id, ev.event_id, 1, ev.previous_event_hash, {"loss": 1.25, "step": 1}, ev.created_at
|
|
).payload_hash
|
|
== ev.payload_hash
|
|
)
|
|
|
|
|
|
def test_artifact_ref():
|
|
a = ArtifactRef.new("ab" * 32, LineagePolicy.root(DataPurpose.TRAIN, True))
|
|
assert a.ref_uri == "sha256:" + "ab" * 32 and a.artifact_id == "artifact:" + "ab" * 32
|
|
assert a.dump()["lineage"] == {"purpose": "train", "derivation_allowed": True}
|
|
assert ArtifactRef.load(a.dump()) == a
|