core/cli: resume sessions, history, editline Tab, higher tool rounds

Default to file SQLite DB and latest session; /history and /rounds;
bind Tab for libedit; max tool rounds default 32.

tests/test_cli/test_readline_setup.py

@@ -80,6 +80,23 @@ def test_completer_commands(tmp_path: object, monkeypatch: object) -> None:
     assert set(found) <= set(SLASH_COMMANDS)
 
 
+def test_bind_tab_complete_runs() -> None:
+    from plyngent.cli.readline_setup import bind_tab_complete
+
+    class FakeReadline:
+        binds: list[str]
+
+        def __init__(self) -> None:
+            self.binds = []
+
+        def parse_and_bind(self, s: str) -> None:
+            self.binds.append(s)
+
+    fake = FakeReadline()
+    bind_tab_complete(fake)
+    assert any("complete" in b or "rl_complete" in b for b in fake.binds)
+
+
 def test_completer_provider_args(tmp_path: object, monkeypatch: object) -> None:
     import readline
     from pathlib import Path

tests/test_cli/test_repl_commands.py

@@ -121,3 +121,22 @@ async def test_resume(state: ReplState) -> None:
     assert sid is not None
     state.agent.messages.clear()
     assert await handle_slash(state, f"/resume {sid}") is True
+
+
+async def test_history(state: ReplState, capsys: pytest.CaptureFixture[str]) -> None:
+    from plyngent.lmproto.openai_compatible.model import AssistantChatMessage, UserChatMessage
+
+    state.agent.messages = [
+        UserChatMessage(content="hello"),
+        AssistantChatMessage(content="hi there"),
+    ]
+    assert await handle_slash(state, "/history") is True
+    out = capsys.readouterr().out
+    assert "user: hello" in out
+    assert "assistant: hi there" in out
+
+
+async def test_rounds(state: ReplState) -> None:
+    assert await handle_slash(state, "/rounds 40") is True
+    assert state.max_rounds == 40  # noqa: PLR2004
+    assert state.agent.max_rounds == 40  # noqa: PLR2004