Merge PR #7774 into stage/7774-vanished-owner

api/background_process.py

@@ -1883,7 +1883,22 @@ def recover_processes_for_webui(process_registry=None, get_session_fn=None) -> i
             try:
                 proc_session = process_registry.get(process_id)
                 session_key = str(getattr(proc_session, "session_key", "") or "")
-                if not session_key or get_session_fn(session_key, metadata_only=True) is None:
+                if not session_key:
+                    continue
+                # The session resolver (``api.models._resolve_session_once``)
+                # raises ``KeyError(sid)`` for a missing session — that is its
+                # documented contract for the "owner gone" outcome, not a
+                # fault. Treat it identically to a ``None`` return: skip the
+                # process without logging, and let a neighbouring live
+                # process still rebind. The narrow ``except KeyError`` lives
+                # INSIDE the outer try so an unrelated ``KeyError`` from
+                # ``process_registry.get()`` (or any routing-index work) still
+                # surfaces in the existing warning path.
+                try:
+                    resolved = get_session_fn(session_key, metadata_only=True)
+                except KeyError:
+                    continue
+                if resolved is None:
                     continue
             except Exception:
                 logger.warning(

tests/test_background_process_restart_recovery.py

@@ -1,5 +1,6 @@
 """Regression coverage for notify_on_complete across a WebUI restart."""
 
+import logging
 import threading
 import time
 from types import SimpleNamespace
@@ -159,3 +160,102 @@ def test_recovery_is_fail_soft_without_agent(monkeypatch):
 
     assert bp.recover_processes_for_webui() == 0
     assert bp._PROCESS_RECOVERY_DONE is False
+
+
+def test_recovery_skips_process_whose_session_is_gone(monkeypatch, caplog):
+    """A checkpointed process whose owner has been pruned (the resolver's
+    ``KeyError(sid)`` contract) must be silently skipped, while a neighbouring
+    live process in the same recovery sweep still rebinds. Regression for
+    issue #7753: previously every vanished owner logged a full WARNING
+    traceback, indistinguishable from a real fault.
+    """
+    calls = {"registered": []}
+
+    class FakeRegistry:
+        def recover_from_checkpoint(self):
+            return 2  # two checkpointed processes survive restart
+
+        def list_sessions(self):
+            return [
+                {"session_id": "proc_vanished", "detached": True},
+                {"session_id": "proc_live", "detached": True},
+            ]
+
+        def get(self, process_id):
+            if process_id == "proc_vanished":
+                return _FakeProcessSession("vanished-session")
+            if process_id == "proc_live":
+                return _FakeProcessSession("live-session")
+            raise AssertionError(process_id)
+
+    fake_registry = FakeRegistry()
+    monkeypatch.setattr(bp, "_PROCESS_CHECKPOINT_RECOVERED", False)
+    monkeypatch.setattr(bp, "_PROCESS_RECOVERY_DONE", False)
+    monkeypatch.setattr(
+        bp,
+        "register_process_session",
+        lambda key, sid: calls["registered"].append((key, sid)),
+    )
+
+    def get_session(sid, metadata_only=False):
+        # Mirrors api.models._resolve_session_once's contract: missing
+        # sessions raise KeyError, NOT None.
+        if sid == "vanished-session":
+            raise KeyError(sid)
+        return SimpleNamespace(id=sid)
+
+    with caplog.at_level(logging.WARNING, logger="api.background_process"):
+        result = bp.recover_processes_for_webui(fake_registry, get_session)
+
+    assert result == 2
+    # The live process is rebound; the vanished one is silently skipped.
+    assert calls["registered"] == [("live-session", "live-session")]
+    # No WARNING emitted for the vanished-owner case.
+    warning_records = [
+        r for r in caplog.records if r.levelno >= logging.WARNING
+    ]
+    assert warning_records == [], (
+        "vanished-session KeyError must not produce a WARNING, got: "
+        f"{[r.getMessage() for r in warning_records]}"
+    )
+    assert "Could not resolve recovered WebUI process" not in caplog.text
+
+
+def test_recovery_still_warns_on_unexpected_resolve_failure(monkeypatch, caplog):
+    """Non-KeyError failures from the resolver (e.g. ``OSError`` on an
+    unreadable sidecar) must keep entering the existing WARNING path. This
+    pins that the fix for #7753 is narrow and does not over-broaden the
+    silent-skip contract.
+    """
+    class FakeRegistry:
+        def recover_from_checkpoint(self):
+            return 1
+
+        def list_sessions(self):
+            return [{"session_id": "proc_unexpected", "detached": True}]
+
+        def get(self, process_id):
+            assert process_id == "proc_unexpected"
+            return _FakeProcessSession("webui-session")
+
+    fake_registry = FakeRegistry()
+    monkeypatch.setattr(bp, "_PROCESS_CHECKPOINT_RECOVERED", False)
+    monkeypatch.setattr(bp, "_PROCESS_RECOVERY_DONE", False)
+
+    def get_session(sid, metadata_only=False):
+        raise OSError("sidecar unreadable")
+
+    with caplog.at_level(logging.WARNING, logger="api.background_process"):
+        result = bp.recover_processes_for_webui(fake_registry, get_session)
+
+    assert result == 1
+    warning_records = [
+        r for r in caplog.records if r.levelno >= logging.WARNING
+    ]
+    assert any(
+        "Could not resolve recovered WebUI process 'proc_unexpected'" in r.getMessage()
+        for r in warning_records
+    ), (
+        "OSError from the resolver must still emit a WARNING, got: "
+        f"{[r.getMessage() for r in warning_records]}"
+    )