glas-harness/tests/test_rein_openweights.py

107 lines
4 KiB
Python
Raw Normal View History

import json
import subprocess
from unittest.mock import MagicMock, patch
import pytest
from glas_harness.contract import Rein, SandboxHandle, ToolCall
from glas_harness.reins.rein_openweights import ReinOpenWeights, ReinOpenWeightsNotInstalled
def test_is_rein_subclass() -> None:
assert issubclass(ReinOpenWeights, Rein)
def test_bin_raises_if_not_installed() -> None:
rein = ReinOpenWeights(cli_bin="does-not-exist-binary")
with pytest.raises(ReinOpenWeightsNotInstalled):
rein._bin()
def test_start_session_writes_task_file_and_captures_head(tmp_path) -> None:
repo = tmp_path / "repo"
repo.mkdir()
subprocess.run(["git", "init", "-q"], cwd=repo, check=True)
subprocess.run(["git", "commit", "-q", "--allow-empty", "-m", "init"], cwd=repo, check=True)
rein = ReinOpenWeights()
sandbox = SandboxHandle(sandbox_id="abc", host="localhost", reachability={"workspace_dir": str(repo)})
session = rein.start_session(
profile={"id": "harness.agent-dev-local"},
inputs={"title": "t", "description": "d"},
sandbox=sandbox,
)
assert session["target_repo"] == str(repo)
assert session["head_before"]
task_spec = json.loads(open(session["task_file"]).read())
assert task_spec["title"] == "t"
assert task_spec["target_repo"] == str(repo)
def test_start_session_requires_resolvable_target_repo() -> None:
rein = ReinOpenWeights()
sandbox = SandboxHandle(sandbox_id="abc", host="localhost", reachability={})
with pytest.raises(ValueError, match="target_repo"):
rein.start_session(profile={}, inputs={"title": "t", "description": "d"}, sandbox=sandbox)
def test_dispatch_tool_invokes_rein_openweights_cli() -> None:
rein = ReinOpenWeights()
session = {"task_file": "/tmp/task.json"}
fake_result = MagicMock(returncode=0, stdout="ok", stderr="")
with patch.object(rein, "_bin", return_value="/usr/bin/rein-openweights"):
with patch("glas_harness.reins.rein_openweights.subprocess.run", return_value=fake_result) as run:
result = rein.dispatch_tool(session, ToolCall(name="run_task"))
argv = run.call_args.args[0]
assert argv[:3] == ["/usr/bin/rein-openweights", "run", "--task-file"]
assert "--no-hub" in argv
assert result.ok is True
assert result.output == "ok"
def test_dispatch_tool_passes_model_when_set() -> None:
rein = ReinOpenWeights(model="meta-llama/llama-3.1-70b-instruct")
session = {"task_file": "/tmp/task.json"}
fake_result = MagicMock(returncode=0, stdout="ok", stderr="")
with patch.object(rein, "_bin", return_value="/usr/bin/rein-openweights"):
with patch("glas_harness.reins.rein_openweights.subprocess.run", return_value=fake_result) as run:
rein.dispatch_tool(session, ToolCall(name="run_task"))
argv = run.call_args.args[0]
assert "--model" in argv
assert "meta-llama/llama-3.1-70b-instruct" in argv
def test_dispatch_tool_reports_failure() -> None:
rein = ReinOpenWeights()
session = {"task_file": "/tmp/task.json"}
fake_result = MagicMock(returncode=1, stdout="", stderr="boom")
with patch.object(rein, "_bin", return_value="/usr/bin/rein-openweights"):
with patch("glas_harness.reins.rein_openweights.subprocess.run", return_value=fake_result):
result = rein.dispatch_tool(session, ToolCall(name="run_task"))
assert result.ok is False
assert result.error == "boom"
def test_end_session_detects_new_commit(tmp_path) -> None:
repo = tmp_path / "repo"
repo.mkdir()
subprocess.run(["git", "init", "-q"], cwd=repo, check=True)
subprocess.run(["git", "commit", "-q", "--allow-empty", "-m", "init"], cwd=repo, check=True)
rein = ReinOpenWeights()
from glas_harness.reins._shared import git_head
head_before = git_head(str(repo))
subprocess.run(["git", "commit", "-q", "--allow-empty", "-m", "task"], cwd=repo, check=True)
summary = rein.end_session({"target_repo": str(repo), "head_before": head_before})
assert summary["committed"] == "True"
assert summary["commit_sha"] != head_before