rein-aharness/tests/test_repository_artifact_bwrap.py

"""Opt-in real sandbox/Glas/worker proof; queue and task authoring are fixtures."""

from __future__ import annotations
import json
import os
from pathlib import Path
from unittest.mock import MagicMock
import pytest

from glas_harness.contract import (
    ExecutionSummary,
    ExecutionLimits,
    OperationalReadiness,
    Rein,
    ToolResult,
)
from glas_harness.gateway import run_execution
from glas_harness.profiles import ProfileCatalog
from glas_harness.transport import transport_from_sandbox
from sandboxer.core.manager import SandboxManager
from sandboxer.lifecycle.store import SandboxStore
from rein_aharness.claim_loop import process_one
from rein_aharness.close_outbox import CloseOutbox
from rein_aharness.metrics import external_metrics_dir
from rein_aharness.ops_run_client import (
    ActivityCoreOpsClient,
    OpsRun,
    OpsRunConfig,
    OpsRunError,
)
from test_repository_artifact import commit, git
from rein_aharness.repository_grant import RepositoryGrant
from rein_aharness.spend_admission import SpendLedger, SpendPolicy, digest

pytestmark = pytest.mark.skipif(
    os.environ.get("REIN_REAL_BWRAP") != "1", reason="opt-in kernel namespace proof"
)


class DeterministicRein(Rein):
    calls = 0
    workspace = None
    head = None

    def __init__(self, source, baseline):
        self.source, self.baseline = source, baseline

    def start_session(self, profile, inputs, sandbox):
        transport = transport_from_sandbox(sandbox)
        self.workspace = Path(transport.workspace)
        return transport

    def dispatch_tool(self, transport, tool_call):
        self.calls += 1
        code = """from pathlib import Path
import subprocess
Path('result.txt').write_text('sandbox-result-only\\n')
def git(*args):
 p=subprocess.run(['git',*args],check=True,capture_output=True,text=True)
 return p.stdout.strip()
git('add','result.txt')
git('-c','user.name=Fixture','-c','user.email=fixture@example.invalid','commit','-qm','bounded result')
print(git('rev-parse','HEAD'))
"""
        result = transport.run(["python3", "-c", code], timeout=30)
        assert result.returncode == 0, result.stderr
        self.head = result.stdout.strip()
        assert git(self.source, "rev-parse", "HEAD") == self.baseline
        assert not (self.source / "result.txt").exists()
        return ToolResult(ok=True, output="sandbox-result-only", tokens_spent=0)

    def end_session(self, session):
        return ExecutionSummary(
            committed=True, commit_sha=self.head, outcome="succeeded", tokens_spent=0, cost_usd=0.0
        )

    def cleanup_session(self, session):
        assert self.workspace.exists()
        assert git(self.source, "rev-parse", "HEAD") == self.baseline


@pytest.mark.parametrize("with_spend", [False, True])
def test_real_bwrap_worker_import_and_close_replay(tmp_path, monkeypatch, with_spend):
    monkeypatch.setenv("XDG_DATA_HOME", str(tmp_path / "data"))
    monkeypatch.setenv("REIN_AHARNESS_STATE_DIR", str(tmp_path / "state"))
    monkeypatch.setenv("SANDBOXER_NO_STATE_HUB", "1")
    source = tmp_path / "source"
    source.mkdir()
    git(source, "init", "-q")
    baseline = commit(source, "README.md", "baseline\n")
    grant = RepositoryGrant.from_mapping(
        {
            "version": "1",
            "allowed_paths": ["result.txt"],
            "commit_count": {"min": 1, "max": 1},
            "publish": False,
        }
    )
    run = OpsRun(
        id="fixture-run",
        activity_definition_id="fixture-definition",
        idempotency_key="fixture-key",
        target_repo=str(source),
        title="deterministic fixture",
        description="no inference",
        state="claimed",
        harness_profile_ref="harness.agent-dev-local@1.0.0",
        repository_grant=grant,
        claim_owner="fixture-worker",
        attempt=1,
    )
    client = MagicMock(spec=ActivityCoreOpsClient)
    client.config = OpsRunConfig(
        worker_id="fixture-worker", lease_seconds=90, repo_roots=(str(tmp_path),)
    )
    client.claim.return_value = [run]
    client.heartbeat.return_value = run
    client.complete.side_effect = [
        OpsRunError("response lost", action="complete"),
        OpsRun(
            id=run.id,
            activity_definition_id="fixture-definition",
            idempotency_key="fixture-key",
            target_repo=str(source),
            title=run.title,
            description=run.description,
            state="succeeded",
            close_disposition="reconciled",
        ),
    ]
    catalog = ProfileCatalog()
    profile, _ = catalog.resolve(run.harness_profile_ref)
    catalog.profiles()[(profile.id, profile.version)] = profile.model_copy(
        update={
            "limits": ExecutionLimits(max_budget_usd=4.0, max_turns=8),
            "operational_readiness": OperationalReadiness(
                status="ready",
                reason="isolated test fixture",
                owner="tests",
                evidence_ref="test:artifact-bwrap",
            )
        }
    )
    spend = None
    if with_spend:
        private = tmp_path / "spend-state"
        private.mkdir(mode=0o700)
        admitted_profile, descriptor = catalog.resolve(run.harness_profile_ref)
        policy = SpendPolicy(
            version="1", envelope_id="bwrap-fixture", authority_ref="test:no-live-authority",
            valid_from="2026-09-01T00:00:00Z", expires_at="2099-01-01T00:00:00Z",
            timezone="Europe/Berlin", worker_id="fixture-worker",
            activity_definition_id="fixture-definition", target_repo=str(source),
            project="fixture-factory", profile_ref=run.harness_profile_ref,
            profile_sha256=digest(admitted_profile.model_dump(mode="json")),
            descriptor_sha256=digest(descriptor.model_dump(mode="json")),
            repository_grant_id=grant.grant_id, max_budget_usd="4", max_liability_usd="5",
            max_turns=8, eur_per_usd="1", per_run_eur="5", daily_eur="10", total_eur="15",
        )
        policy_path = private / "policy.json"
        policy_path.write_text(json.dumps(policy.__dict__))
        policy_path.chmod(0o600)
        spend = SpendLedger(private / "spend.sqlite3", policy)
        spend.initialize()
        client.config.execution_project = "fixture-factory"
        client.config.spend_policy_path = str(policy_path)
        client.config.spend_ledger_path = str(spend.path)
        monkeypatch.setattr("glas_harness.profiles.ProfileCatalog", lambda: catalog)
    manager = SandboxManager(store=SandboxStore(tmp_path / "sandboxes.json"))
    rein = DeterministicRein(source, baseline)
    monkeypatch.setattr(
        "glas_harness.gateway.run_execution",
        lambda request, **kwargs: run_execution(
            request, catalog=kwargs.pop("catalog", catalog), rein=rein, manager=manager, **kwargs
        ),
    )
    outbox = CloseOutbox(state_dir=tmp_path / "state")
    first = process_one(client, outbox=outbox, report_to_hub=False)
    assert first.reason == "close evidence remains pending", first
    assert not rein.workspace.exists()
    assert git(source, "rev-parse", "HEAD") == rein.head
    assert (source / "result.txt").read_text() == "sandbox-result-only\n"
    assert not git(source, "status", "--porcelain")
    assert outbox.status()["pending"] == 1
    record = json.loads(
        (external_metrics_dir(source, "rein-aharness") / "executions.jsonl")
        .read_text()
        .strip()
    )
    assert record["success"]
    durable = json.dumps(client.complete.call_args.kwargs["result"])
    assert rein.head in durable
    assert "sandbox-result-only" not in durable and '"bundle"' not in durable
    client.claim.return_value = []
    second = process_one(client, outbox=outbox, report_to_hub=False)
    assert second.empty and rein.calls == 1
    assert outbox.status() == {"pending": 0, "delivered": 1, "quarantined": 0}
    if spend is not None:
        rows = spend.status()["reservations"]
        assert len(rows) == 1 and rows[0]["state"] == "charged"
        assert rows[0]["liability"] == 5_000_000
        client.claim.return_value = [run]
        replay = process_one(client, outbox=outbox, report_to_hub=False)
        assert not replay.ok and rein.calls == 1
    assert client.complete.call_count == 2
    assert client.heartbeat.call_count >= 1
    assert git(source, "rev-list", "--count", "HEAD") == "2"