core/agent+cli: persist user immediately; /retry reuses DB turn

Keep incomplete user messages in memory/DB; roll back only
assistant/tool on failure. /retry and resume of orphan-user sessions
re-run without duplicating the user message.

tests/test_agent/test_loop.py

@@ -505,7 +505,7 @@ async def test_chat_agent_memory_roundtrip() -> None:
     await store.close()
 
 
-async def test_chat_agent_failed_turn_not_persisted() -> None:
+async def test_chat_agent_failed_turn_keeps_user_in_db() -> None:
     store = await MemoryStore.open(DatabaseConfig())
     session = await store.create_session(name="t")
 
@@ -531,10 +531,13 @@ async def test_chat_agent_failed_turn_not_persisted() -> None:
     with pytest.raises(RuntimeError, match="network down"):
         _ = [e async for e in agent.run("hello")]
 
-    assert agent.messages == []
+    assert len(agent.messages) == 1
+    assert isinstance(agent.messages[0], UserChatMessage)
     assert agent.pending_retry_text == "hello"
     loaded = await store.list_messages(session.sid)
-    assert loaded == []
+    assert len(loaded) == 1
+    assert isinstance(loaded[0], UserChatMessage)
+    assert loaded[0].content == "hello"
     await store.close()
 
 
@@ -581,7 +584,8 @@ async def test_chat_agent_retry_after_failure() -> None:
     with pytest.raises(RuntimeError, match="temporary"):
         _ = [e async for e in agent.run("ping")]
     assert agent.pending_retry_text == "ping"
-    assert await store.list_messages(session.sid) == []
+    # User already in DB after first attempt
+    assert len(await store.list_messages(session.sid)) == 1
 
     events = [e async for e in agent.retry()]
     assert any(isinstance(e, TextDeltaEvent) and e.content == "recovered" for e in events)
@@ -590,9 +594,30 @@ async def test_chat_agent_retry_after_failure() -> None:
     assert len(loaded) == 2
     assert isinstance(loaded[0], UserChatMessage)
     assert loaded[0].content == "ping"
+    # Single user message (no duplicate on retry)
+    assert sum(1 for m in loaded if isinstance(m, UserChatMessage)) == 1
     await store.close()
 
 
+async def test_retry_after_resume_orphan_user() -> None:
+    store = await MemoryStore.open(DatabaseConfig())
+    session = await store.create_session(name="t")
+    _ = await store.append_message(session.sid, UserChatMessage(content="left hanging"))
+
+    client = ScriptedClient([_response(AssistantChatMessage(content="ok now"))])
+    agent = ChatAgent(client, model="m", memory=store, session_id=session.sid)
+    await agent.load_history()
+    assert agent.pending_retry_text == "left hanging"
+
+    events = [e async for e in agent.retry()]
+    assert any(isinstance(e, TextDeltaEvent) and e.content == "ok now" for e in events)
+    loaded = await store.list_messages(session.sid)
+    assert len(loaded) == 2
+    assert sum(1 for m in loaded if isinstance(m, UserChatMessage)) == 1
+    await store.close()
+
+
+
 async def test_chat_agent_system_prompt_prepended() -> None:
     from plyngent.lmproto.openai_compatible.model import SystemChatMessage
 

tests/test_cli/test_retry.py

@@ -173,8 +173,11 @@ async def test_cancel_turn_rolls_back_and_sets_pending() -> None:
         await turn
 
     assert agent.pending_retry_text == "cancel-me"
-    assert agent.messages == []
-    assert await store.list_messages(session.sid) == []
+    assert len(agent.messages) == 1
+    assert isinstance(agent.messages[0], UserChatMessage)
+    loaded = await store.list_messages(session.sid)
+    assert len(loaded) == 1
+    assert isinstance(loaded[0], UserChatMessage)
     await store.close()
 
 
@@ -195,17 +198,16 @@ async def test_manual_retry_after_exhausted(monkeypatch: pytest.MonkeyPatch) ->
     )
     assert ok is False
     assert agent.pending_retry_text == "hold-me"
-    assert await store.list_messages(session.sid) == []
+    assert len(await store.list_messages(session.sid)) == 1
 
-    # Now succeed on manual /retry path
+    # Now succeed on manual /retry path (no second user message)
     client.fail_times = client.calls  # next call succeeds
     ok2 = await retry_pending_with_retries(agent)
-    # retry_pending uses default delays; force zero-wait already patched
-    # But fail_times set so first attempt of manual retry succeeds immediately
     assert ok2 is True
     assert agent.pending_retry_text is None
     loaded = await store.list_messages(session.sid)
     assert len(loaded) == 2
     assert isinstance(loaded[0], UserChatMessage)
     assert loaded[0].content == "hold-me"
+    assert sum(1 for m in loaded if isinstance(m, UserChatMessage)) == 1
     await store.close()