fix: isolate rein results and normalize manager startup failures

Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a0726e-5232-73f2-aaca-2c05ceb62efb

tests/test_gateway.py

@@ -401,3 +401,17 @@ def test_teardown_failure_is_visible_in_evidence() -> None:
     assert result.evidence.failure_stage == "teardown"
     assert result.evidence.error == "teardown failed; inspect direct caller error"
     assert result.tool_error == "cannot teardown"
+
+
+def test_manager_initialization_failure_returns_redacted_evidence():
+    with patch("glas_harness.gateway.SandboxManager", side_effect=RuntimeError(
+        "private manager configuration"
+    )), patch("glas_harness.gateway.hub.post_progress_event") as post:
+        result = run_execution(_request(report_to_hub=True),
+                               catalog=_catalog_with_readiness(), rein=_FakeRein())
+    assert not result.ok
+    assert result.evidence.failure_stage == "sandbox_create"
+    assert result.evidence.sandbox_id is None
+    assert result.tool_error == "private manager configuration"
+    assert "private manager configuration" not in str(post.call_args)
+    post.assert_called_once()

tests/test_rein_session_isolation.py

@@ -0,0 +1,36 @@
+"""A reusable adapter must keep each sandbox's result in its own session."""
+
+import json
+from unittest.mock import MagicMock
+
+import pytest
+
+from glas_harness.contract import ToolCall
+from glas_harness.reins.rein_aharness import ReinAharness
+from glas_harness.reins.rein_openweights import ReinOpenWeights
+from glas_harness.transport import ExecutionTransport
+
+
+@pytest.mark.parametrize("adapter", [ReinAharness, ReinOpenWeights])
+def test_interleaved_sessions_keep_their_own_outcomes_and_usage(adapter):
+    rein = adapter()
+    sessions = []
+    for index, ok in enumerate([True, False]):
+        transport = MagicMock(spec=ExecutionTransport)
+        transport.resolve_executable.return_value = "/runtime/rein"
+        transport.git_head.return_value = f"head-{index}"
+        transport.run.return_value = MagicMock(returncode=0 if ok else 1, stderr="",
+            stdout=json.dumps({"ok": ok, "tokens_spent": 10 + index,
+                               "model": f"model-{index}", "reason": None if ok else "failed"}))
+        sessions.append({"transport": transport, "task_file": f"/workspace-{index}/task",
+                         "timeout_seconds": 30, "head_before": "baseline"})
+    # Finish A only after B has reported its different result.
+    for session in sessions:
+        rein.dispatch_tool(session, ToolCall(name="run_task"))
+    first, second = [rein.end_session(session) for session in sessions]
+    assert first.outcome == "succeeded"
+    assert first.tokens_spent == 10
+    assert first.resolved_model == "model-0"
+    assert second.outcome == "failed"
+    assert second.tokens_spent == 11
+    assert second.resolved_model == "model-1"