glas-harness/tests/test_rein_openweights.py

import json
import os
import subprocess
from unittest.mock import MagicMock, patch

import pytest

from glas_harness.contract import Rein, SandboxHandle, ToolCall
from glas_harness.profiles import ProfileCatalog
from glas_harness.reins.rein_openweights import ReinOpenWeights, ReinOpenWeightsNotInstalled
from glas_harness.transport import ExecutionTransport, TransportError


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")
    transport = MagicMock(spec=ExecutionTransport)
    transport.resolve_executable.side_effect = TransportError("missing")
    with pytest.raises(ReinOpenWeightsNotInstalled):
        rein._bin(transport)


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={"pid": str(os.getpid()), "workspace_dir": str(repo)},
    )
    with patch.object(ExecutionTransport, "git_head", return_value="abc123"):
        session = rein.start_session(
            profile=ProfileCatalog().resolve("harness.agent-dev-openweights-local@1.0.0")[0],
            inputs={"title": "t", "description": "d"},
            sandbox=sandbox,
        )

    assert session["target_repo"] == str(repo)
    assert session["head_before"] == "abc123"
    assert session["transport"].workspace == str(repo)
    task_spec = json.loads(open(session["task_file"]).read())
    assert task_spec["title"] == "t"
    assert task_spec["target_repo"] == str(repo)
    rein.cleanup_session(session)
    assert not os.path.exists(session["task_file"])


def test_start_session_requires_resolvable_target_repo() -> None:
    rein = ReinOpenWeights()
    sandbox = SandboxHandle(sandbox_id="abc", host="localhost", reachability={})
    with pytest.raises(RuntimeError, match="reachability"):
        rein.start_session(profile={}, inputs={"title": "t", "description": "d"}, sandbox=sandbox)


def test_dispatch_tool_invokes_rein_openweights_cli() -> None:
    rein = ReinOpenWeights()
    transport = MagicMock(spec=ExecutionTransport)
    transport.run.return_value = MagicMock(returncode=0, stdout="ok", stderr="")
    session = {"task_file": "/tmp/task.json", "transport": transport, "timeout_seconds": 30}

    with patch.object(rein, "_bin", return_value="/usr/bin/rein-openweights"):
        result = rein.dispatch_tool(session, ToolCall(name="run_task"))

    argv = transport.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",
        max_turns=8,
        budget_tokens=1234,
        tool_profile="green-commit-only",
    )
    transport = MagicMock(spec=ExecutionTransport)
    transport.run.return_value = MagicMock(returncode=0, stdout="ok", stderr="")
    session = {"task_file": "/tmp/task.json", "transport": transport, "timeout_seconds": 30}

    with patch.object(rein, "_bin", return_value="/usr/bin/rein-openweights"):
        rein.dispatch_tool(session, ToolCall(name="run_task"))

    argv = transport.run.call_args.args[0]
    assert "--model" in argv
    assert "meta-llama/llama-3.1-70b-instruct" in argv
    assert argv[argv.index("--max-turns") + 1] == "8"
    assert argv[argv.index("--budget-tokens") + 1] == "1234"
    assert argv[argv.index("--tool-profile") + 1] == "green-commit-only"


def test_dispatch_tool_reports_failure() -> None:
    rein = ReinOpenWeights()
    transport = MagicMock(spec=ExecutionTransport)
    transport.run.return_value = MagicMock(returncode=1, stdout="", stderr="boom")
    session = {"task_file": "/tmp/task.json", "transport": transport, "timeout_seconds": 30}

    with patch.object(rein, "_bin", return_value="/usr/bin/rein-openweights"):
        result = rein.dispatch_tool(session, ToolCall(name="run_task"))

    assert result.ok is False
    assert result.error == "boom"


def test_dispatch_tool_enforces_outer_timeout() -> None:
    rein = ReinOpenWeights()
    transport = MagicMock(spec=ExecutionTransport)
    transport.run.side_effect = subprocess.TimeoutExpired("rein-openweights", 30)
    session = {
        "task_file": "/tmp/task.json",
        "transport": transport,
        "timeout_seconds": 30,
    }

    with patch.object(rein, "_bin", return_value="/usr/bin/rein-openweights"):
        with pytest.raises(subprocess.TimeoutExpired):
            rein.dispatch_tool(session, ToolCall(name="run_task"))

    assert transport.run.call_args.kwargs["timeout"] == 30


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()
    head_before = subprocess.run(
        ["git", "-C", str(repo), "rev-parse", "HEAD"],
        capture_output=True,
        text=True,
        check=True,
    ).stdout.strip()
    subprocess.run(["git", "commit", "-q", "--allow-empty", "-m", "task"], cwd=repo, check=True)

    transport = MagicMock(spec=ExecutionTransport)
    transport.git_head.return_value = subprocess.run(
        ["git", "-C", str(repo), "rev-parse", "HEAD"],
        capture_output=True,
        text=True,
        check=True,
    ).stdout.strip()
    summary = rein.end_session({"transport": transport, "head_before": head_before})
    assert summary.committed is True
    assert summary.outcome == "succeeded"
    assert summary.commit_sha != head_before


def test_cleanup_session_removes_generated_task_file() -> None:
    rein = ReinOpenWeights()
    transport = MagicMock(spec=ExecutionTransport)
    rein.cleanup_session(
        {"transport": transport, "task_file": "/sandbox/task.json", "generated_task_file": True}
    )
    transport.remove_file.assert_called_once_with("/sandbox/task.json")