fix(hindsight): flush buffered turns and drop stale prefetch on session switch

Two data-loss / leak gaps in HindsightMemoryProvider.on_session_switch
introduced by #17409.

1. Buffered turns silently lost when retain_every_n_turns > 1.
   on_session_switch unconditionally cleared _session_turns without
   flushing. Users who batched every N>1 turns and switched mid-batch
   (/reset, /new, /resume, /branch, or context compression) had those
   buffered turns disappear. Same data-loss class as the shutdown race,
   different lifecycle event.

   Note commit_memory_session() -> on_session_end() runs *before*
   on_session_switch on /reset, but Hindsight doesn't implement
   on_session_end so the buffer survives that step and dies at clear
   time. /resume, /branch, and compression skip commit_memory_session
   entirely so an on_session_end impl wouldn't help them anyway.

   Fix: snapshot the old _session_id, _document_id, _parent_session_id,
   _turn_index, and _session_turns; spawn one final retain that lands
   under the OLD document_id; then rotate state. Metadata is built
   synchronously against the old self._* so session_id / lineage tags
   on the flushed item all reference the prior session consistently.

2. Stale _prefetch_result leaks across switch.
   If queue_prefetch ran in the old session and the result hadn't been
   consumed by prefetch() yet, on_session_switch left the cached recall
   text in place. The next session's first prefetch() call would return
   text mined from the prior session's bank/query.

   Fix: join any in-flight _prefetch_thread (3s bounded — matches
   shutdown()), then clear _prefetch_result under _prefetch_lock before
   rotating session_id.

Tests
-----
- tests/plugins/memory/test_hindsight_provider.py (TestSessionSwitchBufferFlush):
    - buffered turns flushed under OLD document_id with OLD lineage tags
    - empty buffer => no spurious retain
    - _prefetch_result cleared on switch
    - in-flight prefetch thread is awaited before clear (no race)
- tests/agent/test_memory_session_switch.py: factory extended to seed the
  attrs the new flush path reads (_retain_source, _platform, _bank_id,
  prefetch state, etc.) and stub _run_hindsight_operation so existing
  switch-state assertions keep passing without network setup.

tests/agent/test_memory_session_switch.py

@@ -205,6 +205,7 @@ def _make_hindsight_provider():
     bypassing __init__ and seeding the attributes on_session_switch
     reads/writes. This keeps the test hermetic.
     """
+    import threading
     hindsight_mod = pytest.importorskip("plugins.memory.hindsight")
     provider = object.__new__(hindsight_mod.HindsightMemoryProvider)
     provider._session_id = "old-sid"
@@ -213,6 +214,33 @@ def _make_hindsight_provider():
     provider._session_turns = ["turn-1", "turn-2"]
     provider._turn_counter = 2
     provider._turn_index = 2
+    # Attrs read by _build_metadata / _build_retain_kwargs when the
+    # buffer-flush path on session switch fires. Empty strings keep the
+    # metadata minimal but well-formed.
+    provider._retain_source = ""
+    provider._platform = ""
+    provider._user_id = ""
+    provider._user_name = ""
+    provider._chat_id = ""
+    provider._chat_name = ""
+    provider._chat_type = ""
+    provider._thread_id = ""
+    provider._agent_identity = ""
+    provider._agent_workspace = ""
+    provider._retain_tags = []
+    provider._retain_context = "test-context"
+    provider._retain_async = False
+    provider._bank_id = "test-bank"
+    # Prefetch state the switch path drains/clears.
+    provider._prefetch_thread = None
+    provider._prefetch_lock = threading.Lock()
+    provider._prefetch_result = ""
+    # Sync thread tracking — flush spawn target.
+    provider._sync_thread = None
+    # Stub the network-touching helper so the spawned flush thread is a
+    # no-op in unit tests. Real plugin behavior is covered by the
+    # mock-client tests in tests/plugins/memory/test_hindsight_provider.py.
+    provider._run_hindsight_operation = lambda _op: None
     return provider