bridge: retry transport blips (TLS timeout/reset), never HTTP errors

A single GitHub TLS handshake timeout failed the whole sync, flipped its
windy-job heartbeat to ok:false and would page for nothing. Up to 3
attempts with backoff for URLError/timeout/reset; HTTP errors return
immediately as before. Test covers both.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

api/tests/test_pr_status_bridge.py

@@ -171,3 +171,41 @@ def test_default_non_blocking_is_grants_ruling():
         "ci/test-installer",
         "ci/reality-check",
     }
+
+
+def test_transport_blips_are_retried_but_http_errors_are_not(monkeypatch):
+    import urllib.error
+
+    calls = {"n": 0}
+
+    class _R:
+        status = 200
+
+        def read(self):
+            return b"{}"
+
+        def __enter__(self):
+            return self
+
+        def __exit__(self, *a):
+            return False
+
+    def flaky(req, timeout):
+        calls["n"] += 1
+        if calls["n"] < 3:
+            raise urllib.error.URLError("_ssl.c:983: The handshake operation timed out")
+        return _R()
+
+    monkeypatch.setattr(bridge.urllib.request, "urlopen", flaky)
+    monkeypatch.setattr(bridge.time, "sleep", lambda s: None)
+    assert bridge._call("http://x", "t", "GET", "/p") == (200, {})
+    assert calls["n"] == 3
+
+    def forbidden(req, timeout):
+        calls["n"] += 1
+        raise urllib.error.HTTPError("http://x/p", 403, "no", {}, None)
+
+    calls["n"] = 0
+    monkeypatch.setattr(bridge.urllib.request, "urlopen", forbidden)
+    assert bridge._call("http://x", "t", "GET", "/p") == (403, None)
+    assert calls["n"] == 1

scripts/pr_status_bridge.py

@@ -32,6 +32,7 @@ import json
 import os
 import re
 import sys
+import time
 import urllib.error
 import urllib.request
 
@@ -98,12 +99,21 @@ def _call(base: str, token_header: str, method: str, path: str, body=None):
             "User-Agent": "windy-git-pr-bridge/1",
         },
     )
-    try:
+    # Transport errors (TLS handshake timeout, reset) are retried: one GitHub
-        with urllib.request.urlopen(req, timeout=60) as r:
+    # blip used to fail the whole sync, flip its heartbeat to ok:false and page
-            raw = r.read()
+    # someone for nothing. HTTP errors are answers, not blips — never retried.
-            return r.status, (json.loads(raw) if raw else None)
+    for attempt in range(3):
-    except urllib.error.HTTPError as e:
+        try:
-        return e.code, None
+            with urllib.request.urlopen(req, timeout=60) as r:
+                raw = r.read()
+                return r.status, (json.loads(raw) if raw else None)
+        except urllib.error.HTTPError as e:
+            return e.code, None
+        except (urllib.error.URLError, TimeoutError, ConnectionError):
+            if attempt == 2:
+                raise
+            time.sleep(2 * (attempt + 1))
+    raise AssertionError("unreachable")
 
 
 def gitea(method, path, body=None):