1 files changed, 109 insertions, 0 deletions
diff --git a/packages/meshbay-node/tests/test_login_retry_is_resilient.py b/packages/meshbay-node/tests/test_login_retry_is_resilient.py
new file mode 100644
index 0000000..e37a413
--- /dev/null
+++ b/packages/meshbay-node/tests/test_login_retry_is_resilient.py
@@ -0,0 +1,109 @@
+"""A transient hub state on node sign-in must not crash the daemon.
+
+`_login_with_retry` retries a 401 (the node key is not linked yet — a human has
+to link it, and the daemon must stay alive so its key can be read). It used to
+`raise` on every other status, so a **429** (the daemon's own retries hitting
+the sign-in rate limit) or a **502/503** (the hub restarting during a deploy)
+killed the process — systemd then crash-looped it, which is what "impossible de
+démarrer le node" looked like after a reset left the node with a fresh, unlinked
+key. Those transient statuses are now retried with a back-off that respects
+`Retry-After`.
+"""
+
+import asyncio
+
+import httpx
+import pytest
+from cryptography.hazmat.primitives.asymmetric.ed25519 import Ed25519PrivateKey
+from meshbay_node.config import Config, GroupConfig, HubConfig, KeystoreConfig, NodeConfig
+from meshbay_node.daemon import NodeDaemon
+
+
+def _daemon(tmp_path):
+    cfg = Config(
+        hub=HubConfig(url="http://localhost:9999", username="testuser"),
+        node=NodeConfig(quic_port=29011, ui_port=29012),
+        groups=[],
+        keystore=KeystoreConfig(path=tmp_path / "keystore.enc"),
+        data_dir=tmp_path / "data",
+    )
+    return NodeDaemon(cfg)
+
+
+def _http_error(status: int, headers: dict | None = None) -> httpx.HTTPStatusError:
+    req = httpx.Request("POST", "http://localhost:9999/v1/nodes/auth")
+    resp = httpx.Response(status, headers=headers or {}, request=req)
+    return httpx.HTTPStatusError(f"{status}", request=req, response=resp)
+
+
+class _Hub:
+    """A hub whose `startup` raises the given sequence, then returns a session."""
+    def __init__(self, seq):
+        self._seq = list(seq)
+        self.calls = 0
+
+    async def startup(self, endpoint_hint=None):
+        self.calls += 1
+        item = self._seq.pop(0)
+        if isinstance(item, Exception):
+            raise item
+        return item
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize("status", [429, 500, 502, 503, 504])
+async def test_a_transient_status_is_retried_not_fatal(tmp_path, status, monkeypatch):
+    slept = []
+
+    async def _sleep(d):
+        slept.append(d)
+    monkeypatch.setattr(asyncio, "sleep", _sleep)
+
+    daemon = _daemon(tmp_path)
+    session = object()
+    hub = _Hub([_http_error(status), session])   # transient, then success
+    got = await daemon._login_with_retry(hub)
+    assert got is session          # it recovered instead of crashing
+    assert hub.calls == 2          # retried once
+    assert slept                   # it backed off
+
+
+@pytest.mark.asyncio
+async def test_retry_after_is_respected(tmp_path, monkeypatch):
+    slept = []
+
+    async def _sleep(d):
+        slept.append(d)
+    monkeypatch.setattr(asyncio, "sleep", _sleep)
+
+    daemon = _daemon(tmp_path)
+    hub = _Hub([_http_error(429, {"Retry-After": "42"}), object()])
+    await daemon._login_with_retry(hub)
+    assert 42 in slept
+
+
+@pytest.mark.asyncio
+async def test_a_401_still_retries_and_stays_alive(tmp_path, monkeypatch):
+    async def _sleep(d):
+        pass
+    monkeypatch.setattr(asyncio, "sleep", _sleep)
+
+    daemon = _daemon(tmp_path)
+    session = object()
+    hub = _Hub([_http_error(401), session])
+    got = await daemon._login_with_retry(hub)
+    assert got is session
+    assert daemon._state.get("status") in ("waiting_for_node_key", "waiting_for_account")
+
+
+@pytest.mark.asyncio
+async def test_a_genuine_client_error_still_raises(tmp_path, monkeypatch):
+    """A 400/422 is a bug, not a transient state — it must not be swallowed."""
+    async def _sleep(d):
+        pass
+    monkeypatch.setattr(asyncio, "sleep", _sleep)
+
+    daemon = _daemon(tmp_path)
+    hub = _Hub([_http_error(400), object()])
+    with pytest.raises(httpx.HTTPStatusError):
+        await daemon._login_with_retry(hub)