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`.
93 lines
3.1 KiB
Python
93 lines
3.1 KiB
Python
"""The canonical bytes and digests are the Rust crate's, read from tests/vectors/rust.json."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
import json
|
|
import math
|
|
|
|
import pytest
|
|
from hanzo_research import Run, Measure, canonical
|
|
|
|
VECTORS = json.load(open(os.path.join(os.path.dirname(__file__), "vectors", "rust.json"), encoding="utf-8"))
|
|
|
|
|
|
@pytest.mark.parametrize("v", VECTORS["vectors"], ids=lambda v: v["name"])
|
|
def test_bytes_and_digest_equal_the_crates(v):
|
|
assert canonical.canonicalize(v["value"]).decode() == v["canonical"]
|
|
assert canonical.digest(v["value"]) == v["digest"]
|
|
|
|
|
|
def test_a_run_digests_as_the_crate_digests_it():
|
|
rec = VECTORS["records"]["run"]
|
|
run = Run.load(rec["value"])
|
|
assert canonical.digest(run) == rec["digest"]
|
|
assert canonical.digest(run.dump()) == rec["digest"]
|
|
|
|
|
|
def test_rfc8785_appendix_example():
|
|
# RFC 8785 section 3.2.2's sample, built from code points so no escape is read twice
|
|
bs, q = chr(92), chr(34)
|
|
text = chr(0x20AC) + "$" + chr(15) + chr(10) + "A'B" + q + bs + bs + q + "/"
|
|
value = {"numbers": [333333333.33333329, 1e30, 4.50, 2e-3, 1e-27], "string": text, "literals": [None, True, False]}
|
|
want = (
|
|
'{"literals":[null,true,false],"numbers":[333333333.3333333,1e+30,4.5,0.002,1e-27],"string":"'
|
|
+ chr(0x20AC)
|
|
+ "$"
|
|
+ bs
|
|
+ "u000f"
|
|
+ bs
|
|
+ "nA'B"
|
|
+ bs
|
|
+ q
|
|
+ bs * 4
|
|
+ bs
|
|
+ q
|
|
+ '/"}'
|
|
)
|
|
assert canonical.canonicalize(value).decode() == want
|
|
|
|
|
|
def test_numbers_past_the_crates_range_are_ecmascripts():
|
|
# the crate writes these with Rust's Display (recorded in rust.json "apart"); RFC 8785 says:
|
|
want = {
|
|
1e21: "1e+21",
|
|
1e-7: "1e-7",
|
|
1.5e300: "1.5e+300",
|
|
-0.0: "0",
|
|
5e-324: "5e-324",
|
|
9007199254740993: "9007199254740992",
|
|
2**64 - 1: "18446744073709552000",
|
|
}
|
|
for x, s in want.items():
|
|
assert canonical.number(x) == s
|
|
crate = {str(a["value"]): a["canonical"] for a in VECTORS["apart"]}
|
|
assert crate["1e+21"] == "1000000000000000000000"
|
|
assert crate["-0.0"] == "-0"
|
|
|
|
|
|
def test_shortest_round_trip_digits():
|
|
for x in (0.1, 0.8734610296764017, 123456.789, 1e-6, 1e20, 2.5e-5, 1 / 3, 100.0, -3.5):
|
|
assert float(canonical.number(x)) == x
|
|
|
|
|
|
def test_what_has_no_json_form_is_refused():
|
|
for bad in (math.nan, math.inf, -math.inf):
|
|
with pytest.raises(ValueError):
|
|
canonical.canonicalize({"x": bad})
|
|
with pytest.raises(ValueError):
|
|
canonical.canonicalize("\ud800")
|
|
with pytest.raises(TypeError):
|
|
canonical.canonicalize({1: "x"})
|
|
with pytest.raises(TypeError):
|
|
canonical.canonicalize({"x": object()})
|
|
assert canonical.canonicalize([True, False, None]) == b"[true,false,null]"
|
|
|
|
|
|
def test_a_dataclass_reads_as_its_fields():
|
|
m = Measure("all", "f1", 0.5, n=3)
|
|
assert canonical.canonicalize(m) == canonical.canonicalize(m.dump())
|
|
assert (
|
|
canonical.canonicalize(m) == b'{"category":"all","hi":null,"lo":null,"metric":"f1","n":3,"of":null,"value":0.5}'
|
|
)
|