From dcdcfb99776f5e419563ae94a52e45101c296218 Mon Sep 17 00:00:00 2001
From: nesquena-hermes <agent@nesquena-hermes>
Date: Thu, 16 Jul 2026 19:14:53 +0000
Subject: [PATCH] fix(streaming): degrade self-heal SessionDB to None on failed
 rebuild

Codex gate on #6143 found a SILENT regression the reuse-path fix introduced:
_replace_session_db_in_kwargs early-returned the OLD handle when the rebuild
failed, but master assigned None. If the old handle was already CLOSED, both
credential self-heal callers (streaming.py:9032/10253) then built a fresh agent
around a closed SessionDB -> every persist/search fails with 'NoneType has no
attribute execute' while the chat keeps going. Guard on _session_db_is_open:
keep a live handle (subagents hold it by ref), else degrade to None (clean lazy
reinit, master behaviour). +2 regression tests.

Co-authored-by: carlotestor <carlotestor@users.noreply.github.com>
---
 api/streaming.py                        | 11 +++++-
 tests/test_v050259_sessiondb_fd_leak.py | 52 +++++++++++++++++++++++++
 2 files changed, 62 insertions(+), 1 deletion(-)

diff --git a/api/streaming.py b/api/streaming.py
index 55c51d0e6..5e222a5f1 100644
--- a/api/streaming.py
+++ b/api/streaming.py
@@ -6350,7 +6350,16 @@ def _replace_session_db_in_kwargs(agent_kwargs, state_db_path):
     _old_session_db = agent_kwargs.get("session_db")
     _next_session_db = _build_session_db_for_stream(state_db_path)
     if _next_session_db is None:
-        return _old_session_db
+        # Replacement construction failed. Keep the prior handle only if it is
+        # still open (live subagents may hold it by reference); otherwise
+        # degrade cleanly to None — as master did — so the rebuilt agent lazily
+        # reinitialises its SessionDB instead of reusing a closed handle and
+        # failing every persist/search with
+        # "'NoneType' object has no attribute 'execute'".
+        if _session_db_is_open(_old_session_db):
+            return _old_session_db
+        agent_kwargs["session_db"] = None
+        return None
     if _session_db_is_open(_old_session_db):
         # Keep the live handle; discard the unused new one.
         try:
diff --git a/tests/test_v050259_sessiondb_fd_leak.py b/tests/test_v050259_sessiondb_fd_leak.py
index 6ad48124c..12bfd90e4 100644
--- a/tests/test_v050259_sessiondb_fd_leak.py
+++ b/tests/test_v050259_sessiondb_fd_leak.py
@@ -280,3 +280,55 @@ def test_lru_eviction_closes_evicted_session_db():
     assert db1.close_calls == 1, "evicted agent's SessionDB must be closed exactly once"
     assert db2.close_calls == 0, "remaining agents' SessionDBs must not be touched"
     assert db3.close_calls == 0
+
+
+# ── 6: self-heal path must not reuse a CLOSED handle when the rebuild fails ──
+
+
+def _import_replace_helper():
+    """Import the real credential-self-heal SessionDB replacer."""
+    try:
+        from api.streaming import _replace_session_db_in_kwargs  # type: ignore
+    except Exception as exc:
+        pytest.skip(f"api.streaming not importable: {exc}")
+    return _replace_session_db_in_kwargs
+
+
+def test_replace_degrades_to_none_when_rebuild_fails_and_old_is_closed(monkeypatch):
+    """Credential self-heal regression (Codex gate finding on PR #6143).
+
+    When ``_build_session_db_for_stream`` returns None (rebuild failed) AND the
+    prior handle is already CLOSED, ``_replace_session_db_in_kwargs`` must leave
+    ``agent_kwargs['session_db'] = None`` — as master did — so the rebuilt agent
+    lazily reinitialises. Retaining the closed handle (the pre-fix behaviour)
+    makes every persist/search fail with
+    ``'NoneType' object has no attribute 'execute'`` while the chat continues.
+    """
+    import api.streaming as streaming
+
+    _replace = _import_replace_helper()
+    monkeypatch.setattr(streaming, "_build_session_db_for_stream", lambda _p: None)
+
+    old_db = _MockSessionDB("old", open_=False)  # already closed
+    kwargs = {"session_db": old_db}
+    result = _replace(kwargs, "/tmp/does-not-matter.db")
+
+    assert result is None, "must not hand back a closed handle when rebuild fails"
+    assert kwargs["session_db"] is None, "kwargs must degrade to None (clean lazy reinit)"
+
+
+def test_replace_keeps_open_handle_when_rebuild_fails(monkeypatch):
+    """Inverse: a still-OPEN prior handle (held by live subagents) is retained
+    when the rebuild fails — do not orphan a live shared connection."""
+    import api.streaming as streaming
+
+    _replace = _import_replace_helper()
+    monkeypatch.setattr(streaming, "_build_session_db_for_stream", lambda _p: None)
+
+    old_db = _MockSessionDB("old", open_=True)  # still live (subagents hold it)
+    kwargs = {"session_db": old_db}
+    result = _replace(kwargs, "/tmp/does-not-matter.db")
+
+    assert result is old_db, "a live handle must be kept when the rebuild fails"
+    assert kwargs["session_db"] is old_db
+    assert old_db.close_calls == 0, "must not close a live shared handle"