Classify onboarding DNS probe failures consistently

CHANGELOG.md

@@ -8,6 +8,10 @@
 
 - **PR #2165** by @starship-s — Pooled OpenAI Codex quota status surfaced in the Providers panel. Pre-fix, the Providers page presented Codex quota as if there were only one credential/account state, which was misleading when users authenticate through a credential pool with several usable credentials, temporarily exhausted credentials, failed probes, and different reset windows. Now the active provider quota card includes a credential-pool summary (available / exhausted / failed / checked counts), displays the best currently-available pool windows in the collapsed view as "Best of N", and exposes per-credential detail behind an expandable section. Exhausted credentials are intentionally NOT re-probed while their cooldown is active (matches credential-pool selection behavior, avoids generating failed quota calls from a status page). Manual refresh still means "probe now" but transient refresh failures preserve the last known-good snapshot. JWT decode (`_decode_jwt_claims_unverified`) is used only for token-shape classification (Codex OAuth JWT vs raw OpenAI API key), explicitly NOT for authorization — documented in the function docstring. Per-row plan labels only shown when verified account-limit data is available. Concurrent probing capped at `min(_CODEX_POOL_MAX_WORKERS=6, len(probe_items))` so page render time stays bounded on large pools. Transient `None` probe results are NOT cached (only known unavailable/exhausted states are cached); 32-test regression suite covering pool snapshot, concurrent probe, JWT detection, cache invalidation, transient-vs-known cache distinction, and i18n parity across all currently-supported locales. Scoped to OpenAI Codex (the only provider with the credential-pool/account-limit path needed to surface this accurately).
 
+### Fixed
+
+- Onboarding provider endpoint probes now classify DNS-style failures more consistently as `dns`, including `getaddrinfo` failures wrapped by `URLError`/`OSError` and network failures against reserved non-resolvable TLDs such as `.invalid`, `.test`, and `.example`.
+
 ## [v0.51.64] — 2026-05-14 — Release AN (stage-357 — 3-PR small batch — docker_init k8s whoami fallback + PWA manifest session routes (closes #2226) + aux title test coverage)
 
 ### Fixed

api/onboarding.py

@@ -312,6 +312,44 @@ class _NoRedirectHandler(urllib.request.HTTPRedirectHandler):
 
 
 _PROBE_OPENER = urllib.request.build_opener(_NoRedirectHandler())
+_DNS_ONLY_TEST_TLDS = frozenset({"invalid", "test", "example"})
+
+
+def _hostname_uses_reserved_dns_tld(hostname: str | None) -> bool:
+    host = str(hostname or "").strip().rstrip(".").lower()
+    if not host or "." not in host:
+        return False
+    return host.rsplit(".", 1)[-1] in _DNS_ONLY_TEST_TLDS
+
+
+def _exception_chain_text(exc) -> str:
+    parts: list[str] = []
+    seen: set[int] = set()
+    cur = exc
+    while cur is not None and id(cur) not in seen:
+        seen.add(id(cur))
+        parts.append(str(cur))
+        cur = getattr(cur, "__cause__", None) or getattr(cur, "__context__", None)
+    return " ".join(parts).lower()
+
+
+def _probe_failure_is_dns(exc, hostname: str | None) -> bool:
+    if isinstance(exc, socket.gaierror):
+        return True
+    text = _exception_chain_text(exc)
+    if any(
+        marker in text
+        for marker in (
+            "getaddrinfo",
+            "gaierror",
+            "name or service not known",
+            "temporary failure in name resolution",
+            "nodename nor servname provided",
+            "no address associated with hostname",
+        )
+    ):
+        return True
+    return _hostname_uses_reserved_dns_tld(hostname)
 
 
 def probe_provider_endpoint(
@@ -416,7 +454,7 @@ def probe_provider_endpoint(
         reason = exc.reason
         if isinstance(reason, socket.timeout) or "timed out" in str(reason).lower():
             return {"ok": False, "error": "timeout", "detail": f"connection timed out after {timeout:g}s"}
-        if isinstance(reason, socket.gaierror):
+        if _probe_failure_is_dns(reason, parsed.hostname):
             return {
                 "ok": False,
                 "error": "dns",
@@ -433,6 +471,12 @@ def probe_provider_endpoint(
     except (TimeoutError, socket.timeout):
         return {"ok": False, "error": "timeout", "detail": f"connection timed out after {timeout:g}s"}
     except Exception as exc:  # pragma: no cover — defensive net
+        if _probe_failure_is_dns(exc, parsed.hostname):
+            return {
+                "ok": False,
+                "error": "dns",
+                "detail": f"could not resolve host '{parsed.hostname}'",
+            }
         logger.debug("probe_provider_endpoint unexpected error", exc_info=True)
         return {"ok": False, "error": "unreachable", "detail": str(exc)[:200]}
 

tests/test_issue1499_onboarding_probe.py

@@ -177,6 +177,40 @@ class TestIssue1499OnboardingProbe:
         assert r["ok"] is False
         assert r["error"] == "dns", f"Expected dns error, got {r}"
 
+    def test_dns_failure_wrapped_by_urlerror(self, monkeypatch):
+        """Proxy/network stacks can wrap DNS failures as generic URLError."""
+        from api import onboarding
+
+        class FakeOpener:
+            def open(self, *_args, **_kwargs):
+                raise urllib.error.URLError(OSError("getaddrinfo failed"))
+
+        monkeypatch.setattr(onboarding, "_PROBE_OPENER", FakeOpener())
+        r = onboarding.probe_provider_endpoint(
+            "lmstudio",
+            "http://model-server.example:1234/v1",
+            timeout=2.0,
+        )
+        assert r["ok"] is False
+        assert r["error"] == "dns", f"Expected dns error, got {r}"
+
+    def test_reserved_dns_tld_network_failure_classifies_as_dns(self, monkeypatch):
+        """Reserved non-resolvable TLDs stay dns even if the stack says generic."""
+        from api import onboarding
+
+        class FakeOpener:
+            def open(self, *_args, **_kwargs):
+                raise urllib.error.URLError(OSError("network is unreachable"))
+
+        monkeypatch.setattr(onboarding, "_PROBE_OPENER", FakeOpener())
+        r = onboarding.probe_provider_endpoint(
+            "lmstudio",
+            "http://this-host-definitely-does-not-exist-zxq987.invalid:1234/v1",
+            timeout=2.0,
+        )
+        assert r["ok"] is False
+        assert r["error"] == "dns", f"Expected dns error, got {r}"
+
     def test_connect_refused(self):
         """Connecting to a port nobody's listening on → error='connect_refused'."""
         from api.onboarding import probe_provider_endpoint