From 2657ffd62ece8b8461d55b398139503ec504c3c6 Mon Sep 17 00:00:00 2001 From: Christophe Besson Date: Fri, 25 Sep 2026 18:59:20 +0200 Subject: fix(node,client): survive a transient hub state on login, and surface a failed node-key link MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Two defensive gaps turned a routine reset-and-reonboard into "impossible de démarrer le node": 1. daemon._login_with_retry retried a 401 (node key not linked yet) but `raise`d on every other status, so a 429 — the daemon's own 5s retries hitting the sign-in rate limit — or a 502/503 while the hub restarts during a deploy killed the process, and systemd crash-looped it. Those statuses (429, 5xx) are now retried with a back-off that respects Retry-After, so a freshly reset node stays alive (the operator needs it up to read its key) instead of dying. A genuine 4xx (400/422) still raises. 2. create-group's linkNodeKey swallowed every error as "already linked or same key" — but PUT /me/node_key is idempotent and returns 200 on a re-link, so there was no benign error to hide: the catch only ever hid a real failure (a rejected session, a bad key), letting the wizard proceed against a node that looked linked but was not, which then could not authenticate. The link failure now surfaces (detectNode shows it). test_login_retry_is_resilient.py holds the retry behaviour (429/5xx retried, Retry-After honoured, 401 stays alive, 400 still raises); red before, green after. common/node/hub suites green. Co-Authored-By: Claude Opus 4.8 --- packages/meshbay-node/src/meshbay_node/daemon.py | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'packages/meshbay-node/src/meshbay_node') diff --git a/packages/meshbay-node/src/meshbay_node/daemon.py b/packages/meshbay-node/src/meshbay_node/daemon.py index 4800dac..dc5df81 100644 --- a/packages/meshbay-node/src/meshbay_node/daemon.py +++ b/packages/meshbay-node/src/meshbay_node/daemon.py @@ -983,6 +983,23 @@ class NodeDaemon(EnrichmentMixin): self._config.hub.username, self._config.hub.url, ) await asyncio.sleep(5) + elif e.response.status_code in (429, 500, 502, 503, 504): + # Transient: the hub is busy (429 — often this daemon's own + # retry storm against the sign-in rate limit), restarting + # (502/503) or erroring (500/504). None of these is a reason + # to exit: the daemon exiting here crash-loops under systemd + # and strands the operator, who needs it alive to read the + # node key (`meshbay-node status`, the desktop client) so + # they can link it. Back off — respecting Retry-After when + # the hub sends one — and try again, rather than dying. + self._state["status"] = "waiting_for_hub" + delay = 10 + ra = (e.response.headers or {}).get("Retry-After") + if ra and str(ra).isdigit(): + delay = min(max(delay, int(ra)), 300) + log.warning("Hub returned %s on login — retrying in %ds", + e.response.status_code, delay) + await asyncio.sleep(delay) else: raise except Exception as e: -- cgit v1.2.3