v0.144.1 code: the wrapper survives a dead reader (BrokenPipe) so a killed pass still keeps its report; the agent looks for kept copies every 5 min (R-868, measured live)

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0159rPz1ZhFKsS53msqPYxtS

configs/test_felhom_os_apply.py

@@ -1077,3 +1077,49 @@ class SaveReportOnDisk(unittest.TestCase):
         with self.assertRaises(OSError):
             self.r.save_report(os.path.join(link, "plan-r3-guest-apply.json"), {"mode": "apply"})
         self.assertEqual(os.listdir(real), [])
+
+
+class AgentDiesMidPass(unittest.TestCase):
+    """R-868, MEASURED LIVE 2026-10-05 05:45 UTC on demo-hp (agent v0.144.0): the agent was kill -9-ed while apt-get
+    ran; apt finished all 13 packages, but the wrapper's next log line went to a stderr pipe nobody reads any more ->
+    BrokenPipeError -> the wrapper died before save_report: no DONE in the journal, no kept copy, no report.
+    COMPANION RED-PROOF: let Runner.log write to stderr unguarded -> this test fails (BrokenPipeError)."""
+
+    def test_a_dead_reader_does_not_stop_the_report_copy(self):
+        import io, sys, contextlib
+
+        class DeadPipe(io.TextIOBase):
+            dead = False
+            def write(self, s):
+                if DeadPipe.dead:
+                    raise BrokenPipeError(32, "Broken pipe")
+                return len(s)
+            def flush(self):
+                if DeadPipe.dead:
+                    raise BrokenPipeError(32, "Broken pipe")
+
+        class DyingFake(Fake):
+            def emulate(self, argv):
+                a = [x for x in argv if not re.match(r"^[A-Z_]+=", x) and x != "env"]
+                if a and a[0] == "apt-get" and "install" in a and "-s" not in a and "--print-uris" not in a:
+                    DeadPipe.dead = True  # the agent is killed while apt-get runs
+                return super().emulate(argv)
+
+        f = DyingFake()
+        journal = []
+        f.log = lambda line: osapply.Runner.log(f, line)  # the REAL log(): stderr, then the journal
+        prev_run = osapply.subprocess.run
+        osapply.subprocess.run = lambda argv, *a, **kw: (journal.append(argv[-1]) if argv[0] == "logger"
+                                                         else prev_run(argv, *a, **kw))  # never the real `logger`
+        prev_err, prev_out = sys.stderr, sys.stdout
+        sys.stderr, sys.stdout = DeadPipe(), DeadPipe()
+        try:
+            rc = osapply.main(["felhom-os-apply", "--plan", PLAN], runner=f)
+        finally:
+            sys.stderr, sys.stdout = prev_err, prev_out
+            osapply.subprocess.run = prev_run
+            DeadPipe.dead = False
+        self.assertEqual(rc, 0)
+        self.assertEqual(len(f.saved_reports), 1, "the kept copy is the only way this report reaches the hub")
+        self.assertEqual(len(f.saved_reports[0][1]["upgraded"]), 2)
+        self.assertTrue(any(l.startswith("os-apply: DONE") for l in journal), "the journal must still get the DONE line")