refactor(tests): optimize unit test structure

tests/agent/test_consolidate_offset.py

@@ -0,0 +1,619 @@
+"""Test session management with cache-friendly message handling."""
+
+import asyncio
+from unittest.mock import AsyncMock, MagicMock
+
+import pytest
+from pathlib import Path
+from nanobot.session.manager import Session, SessionManager
+
+# Test constants
+MEMORY_WINDOW = 50
+KEEP_COUNT = MEMORY_WINDOW // 2  # 25
+
+
+def create_session_with_messages(key: str, count: int, role: str = "user") -> Session:
+    """Create a session and add the specified number of messages.
+
+    Args:
+        key: Session identifier
+        count: Number of messages to add
+        role: Message role (default: "user")
+
+    Returns:
+        Session with the specified messages
+    """
+    session = Session(key=key)
+    for i in range(count):
+        session.add_message(role, f"msg{i}")
+    return session
+
+
+def assert_messages_content(messages: list, start_index: int, end_index: int) -> None:
+    """Assert that messages contain expected content from start to end index.
+
+    Args:
+        messages: List of message dictionaries
+        start_index: Expected first message index
+        end_index: Expected last message index
+    """
+    assert len(messages) > 0
+    assert messages[0]["content"] == f"msg{start_index}"
+    assert messages[-1]["content"] == f"msg{end_index}"
+
+
+def get_old_messages(session: Session, last_consolidated: int, keep_count: int) -> list:
+    """Extract messages that would be consolidated using the standard slice logic.
+
+    Args:
+        session: The session containing messages
+        last_consolidated: Index of last consolidated message
+        keep_count: Number of recent messages to keep
+
+    Returns:
+        List of messages that would be consolidated
+    """
+    return session.messages[last_consolidated:-keep_count]
+
+
+class TestSessionLastConsolidated:
+    """Test last_consolidated tracking to avoid duplicate processing."""
+
+    def test_initial_last_consolidated_zero(self) -> None:
+        """Test that new session starts with last_consolidated=0."""
+        session = Session(key="test:initial")
+        assert session.last_consolidated == 0
+
+    def test_last_consolidated_persistence(self, tmp_path) -> None:
+        """Test that last_consolidated persists across save/load."""
+        manager = SessionManager(Path(tmp_path))
+        session1 = create_session_with_messages("test:persist", 20)
+        session1.last_consolidated = 15
+        manager.save(session1)
+
+        session2 = manager.get_or_create("test:persist")
+        assert session2.last_consolidated == 15
+        assert len(session2.messages) == 20
+
+    def test_clear_resets_last_consolidated(self) -> None:
+        """Test that clear() resets last_consolidated to 0."""
+        session = create_session_with_messages("test:clear", 10)
+        session.last_consolidated = 5
+
+        session.clear()
+        assert len(session.messages) == 0
+        assert session.last_consolidated == 0
+
+
+class TestSessionImmutableHistory:
+    """Test Session message immutability for cache efficiency."""
+
+    def test_initial_state(self) -> None:
+        """Test that new session has empty messages list."""
+        session = Session(key="test:initial")
+        assert len(session.messages) == 0
+
+    def test_add_messages_appends_only(self) -> None:
+        """Test that adding messages only appends, never modifies."""
+        session = Session(key="test:preserve")
+        session.add_message("user", "msg1")
+        session.add_message("assistant", "resp1")
+        session.add_message("user", "msg2")
+        assert len(session.messages) == 3
+        assert session.messages[0]["content"] == "msg1"
+
+    def test_get_history_returns_most_recent(self) -> None:
+        """Test get_history returns the most recent messages."""
+        session = Session(key="test:history")
+        for i in range(10):
+            session.add_message("user", f"msg{i}")
+            session.add_message("assistant", f"resp{i}")
+
+        history = session.get_history(max_messages=6)
+        assert len(history) == 6
+        assert history[0]["content"] == "msg7"
+        assert history[-1]["content"] == "resp9"
+
+    def test_get_history_with_all_messages(self) -> None:
+        """Test get_history with max_messages larger than actual."""
+        session = create_session_with_messages("test:all", 5)
+        history = session.get_history(max_messages=100)
+        assert len(history) == 5
+        assert history[0]["content"] == "msg0"
+
+    def test_get_history_stable_for_same_session(self) -> None:
+        """Test that get_history returns same content for same max_messages."""
+        session = create_session_with_messages("test:stable", 20)
+        history1 = session.get_history(max_messages=10)
+        history2 = session.get_history(max_messages=10)
+        assert history1 == history2
+
+    def test_messages_list_never_modified(self) -> None:
+        """Test that messages list is never modified after creation."""
+        session = create_session_with_messages("test:immutable", 5)
+        original_len = len(session.messages)
+
+        session.get_history(max_messages=2)
+        assert len(session.messages) == original_len
+
+        for _ in range(10):
+            session.get_history(max_messages=3)
+        assert len(session.messages) == original_len
+
+
+class TestSessionPersistence:
+    """Test Session persistence and reload."""
+
+    @pytest.fixture
+    def temp_manager(self, tmp_path):
+        return SessionManager(Path(tmp_path))
+
+    def test_persistence_roundtrip(self, temp_manager):
+        """Test that messages persist across save/load."""
+        session1 = create_session_with_messages("test:persistence", 20)
+        temp_manager.save(session1)
+
+        session2 = temp_manager.get_or_create("test:persistence")
+        assert len(session2.messages) == 20
+        assert session2.messages[0]["content"] == "msg0"
+        assert session2.messages[-1]["content"] == "msg19"
+
+    def test_get_history_after_reload(self, temp_manager):
+        """Test that get_history works correctly after reload."""
+        session1 = create_session_with_messages("test:reload", 30)
+        temp_manager.save(session1)
+
+        session2 = temp_manager.get_or_create("test:reload")
+        history = session2.get_history(max_messages=10)
+        assert len(history) == 10
+        assert history[0]["content"] == "msg20"
+        assert history[-1]["content"] == "msg29"
+
+    def test_clear_resets_session(self, temp_manager):
+        """Test that clear() properly resets session."""
+        session = create_session_with_messages("test:clear", 10)
+        assert len(session.messages) == 10
+
+        session.clear()
+        assert len(session.messages) == 0
+
+
+class TestConsolidationTriggerConditions:
+    """Test consolidation trigger conditions and logic."""
+
+    def test_consolidation_needed_when_messages_exceed_window(self):
+        """Test consolidation logic: should trigger when messages exceed the window."""
+        session = create_session_with_messages("test:trigger", 60)
+
+        total_messages = len(session.messages)
+        messages_to_process = total_messages - session.last_consolidated
+
+        assert total_messages > MEMORY_WINDOW
+        assert messages_to_process > 0
+
+        expected_consolidate_count = total_messages - KEEP_COUNT
+        assert expected_consolidate_count == 35
+
+    def test_consolidation_skipped_when_within_keep_count(self):
+        """Test consolidation skipped when total messages <= keep_count."""
+        session = create_session_with_messages("test:skip", 20)
+
+        total_messages = len(session.messages)
+        assert total_messages <= KEEP_COUNT
+
+        old_messages = get_old_messages(session, session.last_consolidated, KEEP_COUNT)
+        assert len(old_messages) == 0
+
+    def test_consolidation_skipped_when_no_new_messages(self):
+        """Test consolidation skipped when messages_to_process <= 0."""
+        session = create_session_with_messages("test:already_consolidated", 40)
+        session.last_consolidated = len(session.messages) - KEEP_COUNT  # 15
+
+        # Add a few more messages
+        for i in range(40, 42):
+            session.add_message("user", f"msg{i}")
+
+        total_messages = len(session.messages)
+        messages_to_process = total_messages - session.last_consolidated
+        assert messages_to_process > 0
+
+        # Simulate last_consolidated catching up
+        session.last_consolidated = total_messages - KEEP_COUNT
+        old_messages = get_old_messages(session, session.last_consolidated, KEEP_COUNT)
+        assert len(old_messages) == 0
+
+
+class TestLastConsolidatedEdgeCases:
+    """Test last_consolidated edge cases and data corruption scenarios."""
+
+    def test_last_consolidated_exceeds_message_count(self):
+        """Test behavior when last_consolidated > len(messages) (data corruption)."""
+        session = create_session_with_messages("test:corruption", 10)
+        session.last_consolidated = 20
+
+        total_messages = len(session.messages)
+        messages_to_process = total_messages - session.last_consolidated
+        assert messages_to_process <= 0
+
+        old_messages = get_old_messages(session, session.last_consolidated, 5)
+        assert len(old_messages) == 0
+
+    def test_last_consolidated_negative_value(self):
+        """Test behavior with negative last_consolidated (invalid state)."""
+        session = create_session_with_messages("test:negative", 10)
+        session.last_consolidated = -5
+
+        keep_count = 3
+        old_messages = get_old_messages(session, session.last_consolidated, keep_count)
+
+        # messages[-5:-3] with 10 messages gives indices 5,6
+        assert len(old_messages) == 2
+        assert old_messages[0]["content"] == "msg5"
+        assert old_messages[-1]["content"] == "msg6"
+
+    def test_messages_added_after_consolidation(self):
+        """Test correct behavior when new messages arrive after consolidation."""
+        session = create_session_with_messages("test:new_messages", 40)
+        session.last_consolidated = len(session.messages) - KEEP_COUNT  # 15
+
+        # Add new messages after consolidation
+        for i in range(40, 50):
+            session.add_message("user", f"msg{i}")
+
+        total_messages = len(session.messages)
+        old_messages = get_old_messages(session, session.last_consolidated, KEEP_COUNT)
+        expected_consolidate_count = total_messages - KEEP_COUNT - session.last_consolidated
+
+        assert len(old_messages) == expected_consolidate_count
+        assert_messages_content(old_messages, 15, 24)
+
+    def test_slice_behavior_when_indices_overlap(self):
+        """Test slice behavior when last_consolidated >= total - keep_count."""
+        session = create_session_with_messages("test:overlap", 30)
+        session.last_consolidated = 12
+
+        old_messages = get_old_messages(session, session.last_consolidated, 20)
+        assert len(old_messages) == 0
+
+
+class TestArchiveAllMode:
+    """Test archive_all mode (used by /new command)."""
+
+    def test_archive_all_consolidates_everything(self):
+        """Test archive_all=True consolidates all messages."""
+        session = create_session_with_messages("test:archive_all", 50)
+
+        archive_all = True
+        if archive_all:
+            old_messages = session.messages
+            assert len(old_messages) == 50
+
+        assert session.last_consolidated == 0
+
+    def test_archive_all_resets_last_consolidated(self):
+        """Test that archive_all mode resets last_consolidated to 0."""
+        session = create_session_with_messages("test:reset", 40)
+        session.last_consolidated = 15
+
+        archive_all = True
+        if archive_all:
+            session.last_consolidated = 0
+
+        assert session.last_consolidated == 0
+        assert len(session.messages) == 40
+
+    def test_archive_all_vs_normal_consolidation(self):
+        """Test difference between archive_all and normal consolidation."""
+        # Normal consolidation
+        session1 = create_session_with_messages("test:normal", 60)
+        session1.last_consolidated = len(session1.messages) - KEEP_COUNT
+
+        # archive_all mode
+        session2 = create_session_with_messages("test:all", 60)
+        session2.last_consolidated = 0
+
+        assert session1.last_consolidated == 35
+        assert len(session1.messages) == 60
+        assert session2.last_consolidated == 0
+        assert len(session2.messages) == 60
+
+
+class TestCacheImmutability:
+    """Test that consolidation doesn't modify session.messages (cache safety)."""
+
+    def test_consolidation_does_not_modify_messages_list(self):
+        """Test that consolidation leaves messages list unchanged."""
+        session = create_session_with_messages("test:immutable", 50)
+
+        original_messages = session.messages.copy()
+        original_len = len(session.messages)
+        session.last_consolidated = original_len - KEEP_COUNT
+
+        assert len(session.messages) == original_len
+        assert session.messages == original_messages
+
+    def test_get_history_does_not_modify_messages(self):
+        """Test that get_history doesn't modify messages list."""
+        session = create_session_with_messages("test:history_immutable", 40)
+        original_messages = [m.copy() for m in session.messages]
+
+        for _ in range(5):
+            history = session.get_history(max_messages=10)
+            assert len(history) == 10
+
+        assert len(session.messages) == 40
+        for i, msg in enumerate(session.messages):
+            assert msg["content"] == original_messages[i]["content"]
+
+    def test_consolidation_only_updates_last_consolidated(self):
+        """Test that consolidation only updates last_consolidated field."""
+        session = create_session_with_messages("test:field_only", 60)
+
+        original_messages = session.messages.copy()
+        original_key = session.key
+        original_metadata = session.metadata.copy()
+
+        session.last_consolidated = len(session.messages) - KEEP_COUNT
+
+        assert session.messages == original_messages
+        assert session.key == original_key
+        assert session.metadata == original_metadata
+        assert session.last_consolidated == 35
+
+
+class TestSliceLogic:
+    """Test the slice logic: messages[last_consolidated:-keep_count]."""
+
+    def test_slice_extracts_correct_range(self):
+        """Test that slice extracts the correct message range."""
+        session = create_session_with_messages("test:slice", 60)
+
+        old_messages = get_old_messages(session, 0, KEEP_COUNT)
+
+        assert len(old_messages) == 35
+        assert_messages_content(old_messages, 0, 34)
+
+        remaining = session.messages[-KEEP_COUNT:]
+        assert len(remaining) == 25
+        assert_messages_content(remaining, 35, 59)
+
+    def test_slice_with_partial_consolidation(self):
+        """Test slice when some messages already consolidated."""
+        session = create_session_with_messages("test:partial", 70)
+
+        last_consolidated = 30
+        old_messages = get_old_messages(session, last_consolidated, KEEP_COUNT)
+
+        assert len(old_messages) == 15
+        assert_messages_content(old_messages, 30, 44)
+
+    def test_slice_with_various_keep_counts(self):
+        """Test slice behavior with different keep_count values."""
+        session = create_session_with_messages("test:keep_counts", 50)
+
+        test_cases = [(10, 40), (20, 30), (30, 20), (40, 10)]
+
+        for keep_count, expected_count in test_cases:
+            old_messages = session.messages[0:-keep_count]
+            assert len(old_messages) == expected_count
+
+    def test_slice_when_keep_count_exceeds_messages(self):
+        """Test slice when keep_count > len(messages)."""
+        session = create_session_with_messages("test:exceed", 10)
+
+        old_messages = session.messages[0:-20]
+        assert len(old_messages) == 0
+
+
+class TestEmptyAndBoundarySessions:
+    """Test empty sessions and boundary conditions."""
+
+    def test_empty_session_consolidation(self):
+        """Test consolidation behavior with empty session."""
+        session = Session(key="test:empty")
+
+        assert len(session.messages) == 0
+        assert session.last_consolidated == 0
+
+        messages_to_process = len(session.messages) - session.last_consolidated
+        assert messages_to_process == 0
+
+        old_messages = get_old_messages(session, session.last_consolidated, KEEP_COUNT)
+        assert len(old_messages) == 0
+
+    def test_single_message_session(self):
+        """Test consolidation with single message."""
+        session = Session(key="test:single")
+        session.add_message("user", "only message")
+
+        assert len(session.messages) == 1
+
+        old_messages = get_old_messages(session, session.last_consolidated, KEEP_COUNT)
+        assert len(old_messages) == 0
+
+    def test_exactly_keep_count_messages(self):
+        """Test session with exactly keep_count messages."""
+        session = create_session_with_messages("test:exact", KEEP_COUNT)
+
+        assert len(session.messages) == KEEP_COUNT
+
+        old_messages = get_old_messages(session, session.last_consolidated, KEEP_COUNT)
+        assert len(old_messages) == 0
+
+    def test_just_over_keep_count(self):
+        """Test session with one message over keep_count."""
+        session = create_session_with_messages("test:over", KEEP_COUNT + 1)
+
+        assert len(session.messages) == 26
+
+        old_messages = get_old_messages(session, session.last_consolidated, KEEP_COUNT)
+        assert len(old_messages) == 1
+        assert old_messages[0]["content"] == "msg0"
+
+    def test_very_large_session(self):
+        """Test consolidation with very large message count."""
+        session = create_session_with_messages("test:large", 1000)
+
+        assert len(session.messages) == 1000
+
+        old_messages = get_old_messages(session, session.last_consolidated, KEEP_COUNT)
+        assert len(old_messages) == 975
+        assert_messages_content(old_messages, 0, 974)
+
+        remaining = session.messages[-KEEP_COUNT:]
+        assert len(remaining) == 25
+        assert_messages_content(remaining, 975, 999)
+
+    def test_session_with_gaps_in_consolidation(self):
+        """Test session with potential gaps in consolidation history."""
+        session = create_session_with_messages("test:gaps", 50)
+        session.last_consolidated = 10
+
+        # Add more messages
+        for i in range(50, 60):
+            session.add_message("user", f"msg{i}")
+
+        old_messages = get_old_messages(session, session.last_consolidated, KEEP_COUNT)
+
+        expected_count = 60 - KEEP_COUNT - 10
+        assert len(old_messages) == expected_count
+        assert_messages_content(old_messages, 10, 34)
+
+
+class TestNewCommandArchival:
+    """Test /new archival behavior with the simplified consolidation flow."""
+
+    @staticmethod
+    def _make_loop(tmp_path: Path):
+        from nanobot.agent.loop import AgentLoop
+        from nanobot.bus.queue import MessageBus
+        from nanobot.providers.base import LLMResponse
+
+        bus = MessageBus()
+        provider = MagicMock()
+        provider.get_default_model.return_value = "test-model"
+        provider.estimate_prompt_tokens.return_value = (10_000, "test")
+        loop = AgentLoop(
+            bus=bus,
+            provider=provider,
+            workspace=tmp_path,
+            model="test-model",
+            context_window_tokens=1,
+        )
+        loop.provider.chat_with_retry = AsyncMock(return_value=LLMResponse(content="ok", tool_calls=[]))
+        loop.tools.get_definitions = MagicMock(return_value=[])
+        return loop
+
+    @pytest.mark.asyncio
+    async def test_new_clears_session_immediately_even_if_archive_fails(self, tmp_path: Path) -> None:
+        """/new clears session immediately; archive_messages retries until raw dump."""
+        from nanobot.bus.events import InboundMessage
+
+        loop = self._make_loop(tmp_path)
+        session = loop.sessions.get_or_create("cli:test")
+        for i in range(5):
+            session.add_message("user", f"msg{i}")
+            session.add_message("assistant", f"resp{i}")
+        loop.sessions.save(session)
+
+        call_count = 0
+
+        async def _failing_consolidate(_messages) -> bool:
+            nonlocal call_count
+            call_count += 1
+            return False
+
+        loop.memory_consolidator.consolidate_messages = _failing_consolidate  # type: ignore[method-assign]
+
+        new_msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="/new")
+        response = await loop._process_message(new_msg)
+
+        assert response is not None
+        assert "new session started" in response.content.lower()
+
+        session_after = loop.sessions.get_or_create("cli:test")
+        assert len(session_after.messages) == 0
+
+        await loop.close_mcp()
+        assert call_count == 3  # retried up to raw-archive threshold
+
+    @pytest.mark.asyncio
+    async def test_new_archives_only_unconsolidated_messages(self, tmp_path: Path) -> None:
+        from nanobot.bus.events import InboundMessage
+
+        loop = self._make_loop(tmp_path)
+        session = loop.sessions.get_or_create("cli:test")
+        for i in range(15):
+            session.add_message("user", f"msg{i}")
+            session.add_message("assistant", f"resp{i}")
+        session.last_consolidated = len(session.messages) - 3
+        loop.sessions.save(session)
+
+        archived_count = -1
+
+        async def _fake_consolidate(messages) -> bool:
+            nonlocal archived_count
+            archived_count = len(messages)
+            return True
+
+        loop.memory_consolidator.consolidate_messages = _fake_consolidate  # type: ignore[method-assign]
+
+        new_msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="/new")
+        response = await loop._process_message(new_msg)
+
+        assert response is not None
+        assert "new session started" in response.content.lower()
+
+        await loop.close_mcp()
+        assert archived_count == 3
+
+    @pytest.mark.asyncio
+    async def test_new_clears_session_and_responds(self, tmp_path: Path) -> None:
+        from nanobot.bus.events import InboundMessage
+
+        loop = self._make_loop(tmp_path)
+        session = loop.sessions.get_or_create("cli:test")
+        for i in range(3):
+            session.add_message("user", f"msg{i}")
+            session.add_message("assistant", f"resp{i}")
+        loop.sessions.save(session)
+
+        async def _ok_consolidate(_messages) -> bool:
+            return True
+
+        loop.memory_consolidator.consolidate_messages = _ok_consolidate  # type: ignore[method-assign]
+
+        new_msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="/new")
+        response = await loop._process_message(new_msg)
+
+        assert response is not None
+        assert "new session started" in response.content.lower()
+        assert loop.sessions.get_or_create("cli:test").messages == []
+
+    @pytest.mark.asyncio
+    async def test_close_mcp_drains_background_tasks(self, tmp_path: Path) -> None:
+        """close_mcp waits for background tasks to complete."""
+        from nanobot.bus.events import InboundMessage
+
+        loop = self._make_loop(tmp_path)
+        session = loop.sessions.get_or_create("cli:test")
+        for i in range(3):
+            session.add_message("user", f"msg{i}")
+            session.add_message("assistant", f"resp{i}")
+        loop.sessions.save(session)
+
+        archived = asyncio.Event()
+
+        async def _slow_consolidate(_messages) -> bool:
+            await asyncio.sleep(0.1)
+            archived.set()
+            return True
+
+        loop.memory_consolidator.consolidate_messages = _slow_consolidate  # type: ignore[method-assign]
+
+        new_msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="/new")
+        await loop._process_message(new_msg)
+
+        assert not archived.is_set()
+        await loop.close_mcp()
+        assert archived.is_set()

tests/agent/test_context_prompt_cache.py

@@ -0,0 +1,73 @@
+"""Tests for cache-friendly prompt construction."""
+
+from __future__ import annotations
+
+from datetime import datetime as real_datetime
+from importlib.resources import files as pkg_files
+from pathlib import Path
+import datetime as datetime_module
+
+from nanobot.agent.context import ContextBuilder
+
+
+class _FakeDatetime(real_datetime):
+    current = real_datetime(2026, 2, 24, 13, 59)
+
+    @classmethod
+    def now(cls, tz=None):  # type: ignore[override]
+        return cls.current
+
+
+def _make_workspace(tmp_path: Path) -> Path:
+    workspace = tmp_path / "workspace"
+    workspace.mkdir(parents=True)
+    return workspace
+
+
+def test_bootstrap_files_are_backed_by_templates() -> None:
+    template_dir = pkg_files("nanobot") / "templates"
+
+    for filename in ContextBuilder.BOOTSTRAP_FILES:
+        assert (template_dir / filename).is_file(), f"missing bootstrap template: {filename}"
+
+
+def test_system_prompt_stays_stable_when_clock_changes(tmp_path, monkeypatch) -> None:
+    """System prompt should not change just because wall clock minute changes."""
+    monkeypatch.setattr(datetime_module, "datetime", _FakeDatetime)
+
+    workspace = _make_workspace(tmp_path)
+    builder = ContextBuilder(workspace)
+
+    _FakeDatetime.current = real_datetime(2026, 2, 24, 13, 59)
+    prompt1 = builder.build_system_prompt()
+
+    _FakeDatetime.current = real_datetime(2026, 2, 24, 14, 0)
+    prompt2 = builder.build_system_prompt()
+
+    assert prompt1 == prompt2
+
+
+def test_runtime_context_is_separate_untrusted_user_message(tmp_path) -> None:
+    """Runtime metadata should be merged with the user message."""
+    workspace = _make_workspace(tmp_path)
+    builder = ContextBuilder(workspace)
+
+    messages = builder.build_messages(
+        history=[],
+        current_message="Return exactly: OK",
+        channel="cli",
+        chat_id="direct",
+    )
+
+    assert messages[0]["role"] == "system"
+    assert "## Current Session" not in messages[0]["content"]
+
+    # Runtime context is now merged with user message into a single message
+    assert messages[-1]["role"] == "user"
+    user_content = messages[-1]["content"]
+    assert isinstance(user_content, str)
+    assert ContextBuilder._RUNTIME_CONTEXT_TAG in user_content
+    assert "Current Time:" in user_content
+    assert "Channel: cli" in user_content
+    assert "Chat ID: direct" in user_content
+    assert "Return exactly: OK" in user_content

tests/agent/test_evaluator.py

@@ -0,0 +1,63 @@
+import pytest
+
+from nanobot.utils.evaluator import evaluate_response
+from nanobot.providers.base import LLMProvider, LLMResponse, ToolCallRequest
+
+
+class DummyProvider(LLMProvider):
+    def __init__(self, responses: list[LLMResponse]):
+        super().__init__()
+        self._responses = list(responses)
+
+    async def chat(self, *args, **kwargs) -> LLMResponse:
+        if self._responses:
+            return self._responses.pop(0)
+        return LLMResponse(content="", tool_calls=[])
+
+    def get_default_model(self) -> str:
+        return "test-model"
+
+
+def _eval_tool_call(should_notify: bool, reason: str = "") -> LLMResponse:
+    return LLMResponse(
+        content="",
+        tool_calls=[
+            ToolCallRequest(
+                id="eval_1",
+                name="evaluate_notification",
+                arguments={"should_notify": should_notify, "reason": reason},
+            )
+        ],
+    )
+
+
+@pytest.mark.asyncio
+async def test_should_notify_true() -> None:
+    provider = DummyProvider([_eval_tool_call(True, "user asked to be reminded")])
+    result = await evaluate_response("Task completed with results", "check emails", provider, "m")
+    assert result is True
+
+
+@pytest.mark.asyncio
+async def test_should_notify_false() -> None:
+    provider = DummyProvider([_eval_tool_call(False, "routine check, nothing new")])
+    result = await evaluate_response("All clear, no updates", "check status", provider, "m")
+    assert result is False
+
+
+@pytest.mark.asyncio
+async def test_fallback_on_error() -> None:
+    class FailingProvider(DummyProvider):
+        async def chat(self, *args, **kwargs) -> LLMResponse:
+            raise RuntimeError("provider down")
+
+    provider = FailingProvider([])
+    result = await evaluate_response("some response", "some task", provider, "m")
+    assert result is True
+
+
+@pytest.mark.asyncio
+async def test_no_tool_call_fallback() -> None:
+    provider = DummyProvider([LLMResponse(content="I think you should notify", tool_calls=[])])
+    result = await evaluate_response("some response", "some task", provider, "m")
+    assert result is True

tests/agent/test_gemini_thought_signature.py

@@ -0,0 +1,53 @@
+from types import SimpleNamespace
+
+from nanobot.providers.base import ToolCallRequest
+from nanobot.providers.litellm_provider import LiteLLMProvider
+
+
+def test_litellm_parse_response_preserves_tool_call_provider_fields() -> None:
+    provider = LiteLLMProvider(default_model="gemini/gemini-3-flash")
+
+    response = SimpleNamespace(
+        choices=[
+            SimpleNamespace(
+                finish_reason="tool_calls",
+                message=SimpleNamespace(
+                    content=None,
+                    tool_calls=[
+                        SimpleNamespace(
+                            id="call_123",
+                            function=SimpleNamespace(
+                                name="read_file",
+                                arguments='{"path":"todo.md"}',
+                                provider_specific_fields={"inner": "value"},
+                            ),
+                            provider_specific_fields={"thought_signature": "signed-token"},
+                        )
+                    ],
+                ),
+            )
+        ],
+        usage=None,
+    )
+
+    parsed = provider._parse_response(response)
+
+    assert len(parsed.tool_calls) == 1
+    assert parsed.tool_calls[0].provider_specific_fields == {"thought_signature": "signed-token"}
+    assert parsed.tool_calls[0].function_provider_specific_fields == {"inner": "value"}
+
+
+def test_tool_call_request_serializes_provider_fields() -> None:
+    tool_call = ToolCallRequest(
+        id="abc123xyz",
+        name="read_file",
+        arguments={"path": "todo.md"},
+        provider_specific_fields={"thought_signature": "signed-token"},
+        function_provider_specific_fields={"inner": "value"},
+    )
+
+    message = tool_call.to_openai_tool_call()
+
+    assert message["provider_specific_fields"] == {"thought_signature": "signed-token"}
+    assert message["function"]["provider_specific_fields"] == {"inner": "value"}
+    assert message["function"]["arguments"] == '{"path": "todo.md"}'

tests/agent/test_heartbeat_service.py

@@ -0,0 +1,289 @@
+import asyncio
+
+import pytest
+
+from nanobot.heartbeat.service import HeartbeatService
+from nanobot.providers.base import LLMProvider, LLMResponse, ToolCallRequest
+
+
+class DummyProvider(LLMProvider):
+    def __init__(self, responses: list[LLMResponse]):
+        super().__init__()
+        self._responses = list(responses)
+        self.calls = 0
+
+    async def chat(self, *args, **kwargs) -> LLMResponse:
+        self.calls += 1
+        if self._responses:
+            return self._responses.pop(0)
+        return LLMResponse(content="", tool_calls=[])
+
+    def get_default_model(self) -> str:
+        return "test-model"
+
+
+@pytest.mark.asyncio
+async def test_start_is_idempotent(tmp_path) -> None:
+    provider = DummyProvider([])
+
+    service = HeartbeatService(
+        workspace=tmp_path,
+        provider=provider,
+        model="openai/gpt-4o-mini",
+        interval_s=9999,
+        enabled=True,
+    )
+
+    await service.start()
+    first_task = service._task
+    await service.start()
+
+    assert service._task is first_task
+
+    service.stop()
+    await asyncio.sleep(0)
+
+
+@pytest.mark.asyncio
+async def test_decide_returns_skip_when_no_tool_call(tmp_path) -> None:
+    provider = DummyProvider([LLMResponse(content="no tool call", tool_calls=[])])
+    service = HeartbeatService(
+        workspace=tmp_path,
+        provider=provider,
+        model="openai/gpt-4o-mini",
+    )
+
+    action, tasks = await service._decide("heartbeat content")
+    assert action == "skip"
+    assert tasks == ""
+
+
+@pytest.mark.asyncio
+async def test_trigger_now_executes_when_decision_is_run(tmp_path) -> None:
+    (tmp_path / "HEARTBEAT.md").write_text("- [ ] do thing", encoding="utf-8")
+
+    provider = DummyProvider([
+        LLMResponse(
+            content="",
+            tool_calls=[
+                ToolCallRequest(
+                    id="hb_1",
+                    name="heartbeat",
+                    arguments={"action": "run", "tasks": "check open tasks"},
+                )
+            ],
+        )
+    ])
+
+    called_with: list[str] = []
+
+    async def _on_execute(tasks: str) -> str:
+        called_with.append(tasks)
+        return "done"
+
+    service = HeartbeatService(
+        workspace=tmp_path,
+        provider=provider,
+        model="openai/gpt-4o-mini",
+        on_execute=_on_execute,
+    )
+
+    result = await service.trigger_now()
+    assert result == "done"
+    assert called_with == ["check open tasks"]
+
+
+@pytest.mark.asyncio
+async def test_trigger_now_returns_none_when_decision_is_skip(tmp_path) -> None:
+    (tmp_path / "HEARTBEAT.md").write_text("- [ ] do thing", encoding="utf-8")
+
+    provider = DummyProvider([
+        LLMResponse(
+            content="",
+            tool_calls=[
+                ToolCallRequest(
+                    id="hb_1",
+                    name="heartbeat",
+                    arguments={"action": "skip"},
+                )
+            ],
+        )
+    ])
+
+    async def _on_execute(tasks: str) -> str:
+        return tasks
+
+    service = HeartbeatService(
+        workspace=tmp_path,
+        provider=provider,
+        model="openai/gpt-4o-mini",
+        on_execute=_on_execute,
+    )
+
+    assert await service.trigger_now() is None
+
+
+@pytest.mark.asyncio
+async def test_tick_notifies_when_evaluator_says_yes(tmp_path, monkeypatch) -> None:
+    """Phase 1 run -> Phase 2 execute -> Phase 3 evaluate=notify -> on_notify called."""
+    (tmp_path / "HEARTBEAT.md").write_text("- [ ] check deployments", encoding="utf-8")
+
+    provider = DummyProvider([
+        LLMResponse(
+            content="",
+            tool_calls=[
+                ToolCallRequest(
+                    id="hb_1",
+                    name="heartbeat",
+                    arguments={"action": "run", "tasks": "check deployments"},
+                )
+            ],
+        ),
+    ])
+
+    executed: list[str] = []
+    notified: list[str] = []
+
+    async def _on_execute(tasks: str) -> str:
+        executed.append(tasks)
+        return "deployment failed on staging"
+
+    async def _on_notify(response: str) -> None:
+        notified.append(response)
+
+    service = HeartbeatService(
+        workspace=tmp_path,
+        provider=provider,
+        model="openai/gpt-4o-mini",
+        on_execute=_on_execute,
+        on_notify=_on_notify,
+    )
+
+    async def _eval_notify(*a, **kw):
+        return True
+
+    monkeypatch.setattr("nanobot.utils.evaluator.evaluate_response", _eval_notify)
+
+    await service._tick()
+    assert executed == ["check deployments"]
+    assert notified == ["deployment failed on staging"]
+
+
+@pytest.mark.asyncio
+async def test_tick_suppresses_when_evaluator_says_no(tmp_path, monkeypatch) -> None:
+    """Phase 1 run -> Phase 2 execute -> Phase 3 evaluate=silent -> on_notify NOT called."""
+    (tmp_path / "HEARTBEAT.md").write_text("- [ ] check status", encoding="utf-8")
+
+    provider = DummyProvider([
+        LLMResponse(
+            content="",
+            tool_calls=[
+                ToolCallRequest(
+                    id="hb_1",
+                    name="heartbeat",
+                    arguments={"action": "run", "tasks": "check status"},
+                )
+            ],
+        ),
+    ])
+
+    executed: list[str] = []
+    notified: list[str] = []
+
+    async def _on_execute(tasks: str) -> str:
+        executed.append(tasks)
+        return "everything is fine, no issues"
+
+    async def _on_notify(response: str) -> None:
+        notified.append(response)
+
+    service = HeartbeatService(
+        workspace=tmp_path,
+        provider=provider,
+        model="openai/gpt-4o-mini",
+        on_execute=_on_execute,
+        on_notify=_on_notify,
+    )
+
+    async def _eval_silent(*a, **kw):
+        return False
+
+    monkeypatch.setattr("nanobot.utils.evaluator.evaluate_response", _eval_silent)
+
+    await service._tick()
+    assert executed == ["check status"]
+    assert notified == []
+
+
+@pytest.mark.asyncio
+async def test_decide_retries_transient_error_then_succeeds(tmp_path, monkeypatch) -> None:
+    provider = DummyProvider([
+        LLMResponse(content="429 rate limit", finish_reason="error"),
+        LLMResponse(
+            content="",
+            tool_calls=[
+                ToolCallRequest(
+                    id="hb_1",
+                    name="heartbeat",
+                    arguments={"action": "run", "tasks": "check open tasks"},
+                )
+            ],
+        ),
+    ])
+
+    delays: list[int] = []
+
+    async def _fake_sleep(delay: int) -> None:
+        delays.append(delay)
+
+    monkeypatch.setattr(asyncio, "sleep", _fake_sleep)
+
+    service = HeartbeatService(
+        workspace=tmp_path,
+        provider=provider,
+        model="openai/gpt-4o-mini",
+    )
+
+    action, tasks = await service._decide("heartbeat content")
+
+    assert action == "run"
+    assert tasks == "check open tasks"
+    assert provider.calls == 2
+    assert delays == [1]
+
+
+@pytest.mark.asyncio
+async def test_decide_prompt_includes_current_time(tmp_path) -> None:
+    """Phase 1 user prompt must contain current time so the LLM can judge task urgency."""
+
+    captured_messages: list[dict] = []
+
+    class CapturingProvider(LLMProvider):
+        async def chat(self, *, messages=None, **kwargs) -> LLMResponse:
+            if messages:
+                captured_messages.extend(messages)
+            return LLMResponse(
+                content="",
+                tool_calls=[
+                    ToolCallRequest(
+                        id="hb_1", name="heartbeat",
+                        arguments={"action": "skip"},
+                    )
+                ],
+            )
+
+        def get_default_model(self) -> str:
+            return "test-model"
+
+    service = HeartbeatService(
+        workspace=tmp_path,
+        provider=CapturingProvider(),
+        model="test-model",
+    )
+
+    await service._decide("- [ ] check servers at 10:00 UTC")
+
+    user_msg = captured_messages[1]
+    assert user_msg["role"] == "user"
+    assert "Current Time:" in user_msg["content"]
+

tests/agent/test_loop_consolidation_tokens.py

@@ -0,0 +1,196 @@
+from unittest.mock import AsyncMock, MagicMock
+
+import pytest
+
+from nanobot.agent.loop import AgentLoop
+import nanobot.agent.memory as memory_module
+from nanobot.bus.queue import MessageBus
+from nanobot.providers.base import LLMResponse
+
+
+def _make_loop(tmp_path, *, estimated_tokens: int, context_window_tokens: int) -> AgentLoop:
+    from nanobot.providers.base import GenerationSettings
+    provider = MagicMock()
+    provider.get_default_model.return_value = "test-model"
+    provider.generation = GenerationSettings(max_tokens=0)
+    provider.estimate_prompt_tokens.return_value = (estimated_tokens, "test-counter")
+    _response = LLMResponse(content="ok", tool_calls=[])
+    provider.chat_with_retry = AsyncMock(return_value=_response)
+    provider.chat_stream_with_retry = AsyncMock(return_value=_response)
+
+    loop = AgentLoop(
+        bus=MessageBus(),
+        provider=provider,
+        workspace=tmp_path,
+        model="test-model",
+        context_window_tokens=context_window_tokens,
+    )
+    loop.tools.get_definitions = MagicMock(return_value=[])
+    loop.memory_consolidator._SAFETY_BUFFER = 0
+    return loop
+
+
+@pytest.mark.asyncio
+async def test_prompt_below_threshold_does_not_consolidate(tmp_path) -> None:
+    loop = _make_loop(tmp_path, estimated_tokens=100, context_window_tokens=200)
+    loop.memory_consolidator.consolidate_messages = AsyncMock(return_value=True)  # type: ignore[method-assign]
+
+    await loop.process_direct("hello", session_key="cli:test")
+
+    loop.memory_consolidator.consolidate_messages.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_prompt_above_threshold_triggers_consolidation(tmp_path, monkeypatch) -> None:
+    loop = _make_loop(tmp_path, estimated_tokens=1000, context_window_tokens=200)
+    loop.memory_consolidator.consolidate_messages = AsyncMock(return_value=True)  # type: ignore[method-assign]
+    session = loop.sessions.get_or_create("cli:test")
+    session.messages = [
+        {"role": "user", "content": "u1", "timestamp": "2026-01-01T00:00:00"},
+        {"role": "assistant", "content": "a1", "timestamp": "2026-01-01T00:00:01"},
+        {"role": "user", "content": "u2", "timestamp": "2026-01-01T00:00:02"},
+    ]
+    loop.sessions.save(session)
+    monkeypatch.setattr(memory_module, "estimate_message_tokens", lambda _message: 500)
+
+    await loop.process_direct("hello", session_key="cli:test")
+
+    assert loop.memory_consolidator.consolidate_messages.await_count >= 1
+
+
+@pytest.mark.asyncio
+async def test_prompt_above_threshold_archives_until_next_user_boundary(tmp_path, monkeypatch) -> None:
+    loop = _make_loop(tmp_path, estimated_tokens=1000, context_window_tokens=200)
+    loop.memory_consolidator.consolidate_messages = AsyncMock(return_value=True)  # type: ignore[method-assign]
+
+    session = loop.sessions.get_or_create("cli:test")
+    session.messages = [
+        {"role": "user", "content": "u1", "timestamp": "2026-01-01T00:00:00"},
+        {"role": "assistant", "content": "a1", "timestamp": "2026-01-01T00:00:01"},
+        {"role": "user", "content": "u2", "timestamp": "2026-01-01T00:00:02"},
+        {"role": "assistant", "content": "a2", "timestamp": "2026-01-01T00:00:03"},
+        {"role": "user", "content": "u3", "timestamp": "2026-01-01T00:00:04"},
+    ]
+    loop.sessions.save(session)
+
+    token_map = {"u1": 120, "a1": 120, "u2": 120, "a2": 120, "u3": 120}
+    monkeypatch.setattr(memory_module, "estimate_message_tokens", lambda message: token_map[message["content"]])
+
+    await loop.memory_consolidator.maybe_consolidate_by_tokens(session)
+
+    archived_chunk = loop.memory_consolidator.consolidate_messages.await_args.args[0]
+    assert [message["content"] for message in archived_chunk] == ["u1", "a1", "u2", "a2"]
+    assert session.last_consolidated == 4
+
+
+@pytest.mark.asyncio
+async def test_consolidation_loops_until_target_met(tmp_path, monkeypatch) -> None:
+    """Verify maybe_consolidate_by_tokens keeps looping until under threshold."""
+    loop = _make_loop(tmp_path, estimated_tokens=0, context_window_tokens=200)
+    loop.memory_consolidator.consolidate_messages = AsyncMock(return_value=True)  # type: ignore[method-assign]
+
+    session = loop.sessions.get_or_create("cli:test")
+    session.messages = [
+        {"role": "user", "content": "u1", "timestamp": "2026-01-01T00:00:00"},
+        {"role": "assistant", "content": "a1", "timestamp": "2026-01-01T00:00:01"},
+        {"role": "user", "content": "u2", "timestamp": "2026-01-01T00:00:02"},
+        {"role": "assistant", "content": "a2", "timestamp": "2026-01-01T00:00:03"},
+        {"role": "user", "content": "u3", "timestamp": "2026-01-01T00:00:04"},
+        {"role": "assistant", "content": "a3", "timestamp": "2026-01-01T00:00:05"},
+        {"role": "user", "content": "u4", "timestamp": "2026-01-01T00:00:06"},
+    ]
+    loop.sessions.save(session)
+
+    call_count = [0]
+    def mock_estimate(_session):
+        call_count[0] += 1
+        if call_count[0] == 1:
+            return (500, "test")
+        if call_count[0] == 2:
+            return (300, "test")
+        return (80, "test")
+
+    loop.memory_consolidator.estimate_session_prompt_tokens = mock_estimate  # type: ignore[method-assign]
+    monkeypatch.setattr(memory_module, "estimate_message_tokens", lambda _m: 100)
+
+    await loop.memory_consolidator.maybe_consolidate_by_tokens(session)
+
+    assert loop.memory_consolidator.consolidate_messages.await_count == 2
+    assert session.last_consolidated == 6
+
+
+@pytest.mark.asyncio
+async def test_consolidation_continues_below_trigger_until_half_target(tmp_path, monkeypatch) -> None:
+    """Once triggered, consolidation should continue until it drops below half threshold."""
+    loop = _make_loop(tmp_path, estimated_tokens=0, context_window_tokens=200)
+    loop.memory_consolidator.consolidate_messages = AsyncMock(return_value=True)  # type: ignore[method-assign]
+
+    session = loop.sessions.get_or_create("cli:test")
+    session.messages = [
+        {"role": "user", "content": "u1", "timestamp": "2026-01-01T00:00:00"},
+        {"role": "assistant", "content": "a1", "timestamp": "2026-01-01T00:00:01"},
+        {"role": "user", "content": "u2", "timestamp": "2026-01-01T00:00:02"},
+        {"role": "assistant", "content": "a2", "timestamp": "2026-01-01T00:00:03"},
+        {"role": "user", "content": "u3", "timestamp": "2026-01-01T00:00:04"},
+        {"role": "assistant", "content": "a3", "timestamp": "2026-01-01T00:00:05"},
+        {"role": "user", "content": "u4", "timestamp": "2026-01-01T00:00:06"},
+    ]
+    loop.sessions.save(session)
+
+    call_count = [0]
+
+    def mock_estimate(_session):
+        call_count[0] += 1
+        if call_count[0] == 1:
+            return (500, "test")
+        if call_count[0] == 2:
+            return (150, "test")
+        return (80, "test")
+
+    loop.memory_consolidator.estimate_session_prompt_tokens = mock_estimate  # type: ignore[method-assign]
+    monkeypatch.setattr(memory_module, "estimate_message_tokens", lambda _m: 100)
+
+    await loop.memory_consolidator.maybe_consolidate_by_tokens(session)
+
+    assert loop.memory_consolidator.consolidate_messages.await_count == 2
+    assert session.last_consolidated == 6
+
+
+@pytest.mark.asyncio
+async def test_preflight_consolidation_before_llm_call(tmp_path, monkeypatch) -> None:
+    """Verify preflight consolidation runs before the LLM call in process_direct."""
+    order: list[str] = []
+
+    loop = _make_loop(tmp_path, estimated_tokens=0, context_window_tokens=200)
+
+    async def track_consolidate(messages):
+        order.append("consolidate")
+        return True
+    loop.memory_consolidator.consolidate_messages = track_consolidate  # type: ignore[method-assign]
+
+    async def track_llm(*args, **kwargs):
+        order.append("llm")
+        return LLMResponse(content="ok", tool_calls=[])
+    loop.provider.chat_with_retry = track_llm
+    loop.provider.chat_stream_with_retry = track_llm
+
+    session = loop.sessions.get_or_create("cli:test")
+    session.messages = [
+        {"role": "user", "content": "u1", "timestamp": "2026-01-01T00:00:00"},
+        {"role": "assistant", "content": "a1", "timestamp": "2026-01-01T00:00:01"},
+        {"role": "user", "content": "u2", "timestamp": "2026-01-01T00:00:02"},
+    ]
+    loop.sessions.save(session)
+    monkeypatch.setattr(memory_module, "estimate_message_tokens", lambda _m: 500)
+
+    call_count = [0]
+    def mock_estimate(_session):
+        call_count[0] += 1
+        return (1000 if call_count[0] <= 1 else 80, "test")
+    loop.memory_consolidator.estimate_session_prompt_tokens = mock_estimate  # type: ignore[method-assign]
+
+    await loop.process_direct("hello", session_key="cli:test")
+
+    assert "consolidate" in order
+    assert "llm" in order
+    assert order.index("consolidate") < order.index("llm")

tests/agent/test_loop_save_turn.py

@@ -0,0 +1,74 @@
+from nanobot.agent.context import ContextBuilder
+from nanobot.agent.loop import AgentLoop
+from nanobot.session.manager import Session
+
+
+def _mk_loop() -> AgentLoop:
+    loop = AgentLoop.__new__(AgentLoop)
+    loop._TOOL_RESULT_MAX_CHARS = AgentLoop._TOOL_RESULT_MAX_CHARS
+    return loop
+
+
+def test_save_turn_skips_multimodal_user_when_only_runtime_context() -> None:
+    loop = _mk_loop()
+    session = Session(key="test:runtime-only")
+    runtime = ContextBuilder._RUNTIME_CONTEXT_TAG + "\nCurrent Time: now (UTC)"
+
+    loop._save_turn(
+        session,
+        [{"role": "user", "content": [{"type": "text", "text": runtime}]}],
+        skip=0,
+    )
+    assert session.messages == []
+
+
+def test_save_turn_keeps_image_placeholder_with_path_after_runtime_strip() -> None:
+    loop = _mk_loop()
+    session = Session(key="test:image")
+    runtime = ContextBuilder._RUNTIME_CONTEXT_TAG + "\nCurrent Time: now (UTC)"
+
+    loop._save_turn(
+        session,
+        [{
+            "role": "user",
+            "content": [
+                {"type": "text", "text": runtime},
+                {"type": "image_url", "image_url": {"url": "data:image/png;base64,abc"}, "_meta": {"path": "/media/feishu/photo.jpg"}},
+            ],
+        }],
+        skip=0,
+    )
+    assert session.messages[0]["content"] == [{"type": "text", "text": "[image: /media/feishu/photo.jpg]"}]
+
+
+def test_save_turn_keeps_image_placeholder_without_meta() -> None:
+    loop = _mk_loop()
+    session = Session(key="test:image-no-meta")
+    runtime = ContextBuilder._RUNTIME_CONTEXT_TAG + "\nCurrent Time: now (UTC)"
+
+    loop._save_turn(
+        session,
+        [{
+            "role": "user",
+            "content": [
+                {"type": "text", "text": runtime},
+                {"type": "image_url", "image_url": {"url": "data:image/png;base64,abc"}},
+            ],
+        }],
+        skip=0,
+    )
+    assert session.messages[0]["content"] == [{"type": "text", "text": "[image]"}]
+
+
+def test_save_turn_keeps_tool_results_under_16k() -> None:
+    loop = _mk_loop()
+    session = Session(key="test:tool-result")
+    content = "x" * 12_000
+
+    loop._save_turn(
+        session,
+        [{"role": "tool", "tool_call_id": "call_1", "name": "read_file", "content": content}],
+        skip=0,
+    )
+
+    assert session.messages[0]["content"] == content

tests/agent/test_memory_consolidation_types.py

@@ -0,0 +1,478 @@
+"""Test MemoryStore.consolidate() handles non-string tool call arguments.
+
+Regression test for https://github.com/HKUDS/nanobot/issues/1042
+When memory consolidation receives dict values instead of strings from the LLM
+tool call response, it should serialize them to JSON instead of raising TypeError.
+"""
+
+import json
+from pathlib import Path
+from unittest.mock import AsyncMock
+
+import pytest
+
+from nanobot.agent.memory import MemoryStore
+from nanobot.providers.base import LLMProvider, LLMResponse, ToolCallRequest
+
+
+def _make_messages(message_count: int = 30):
+    """Create a list of mock messages."""
+    return [
+        {"role": "user", "content": f"msg{i}", "timestamp": "2026-01-01 00:00"}
+        for i in range(message_count)
+    ]
+
+
+def _make_tool_response(history_entry, memory_update):
+    """Create an LLMResponse with a save_memory tool call."""
+    return LLMResponse(
+        content=None,
+        tool_calls=[
+            ToolCallRequest(
+                id="call_1",
+                name="save_memory",
+                arguments={
+                    "history_entry": history_entry,
+                    "memory_update": memory_update,
+                },
+            )
+        ],
+    )
+
+
+class ScriptedProvider(LLMProvider):
+    def __init__(self, responses: list[LLMResponse]):
+        super().__init__()
+        self._responses = list(responses)
+        self.calls = 0
+
+    async def chat(self, *args, **kwargs) -> LLMResponse:
+        self.calls += 1
+        if self._responses:
+            return self._responses.pop(0)
+        return LLMResponse(content="", tool_calls=[])
+
+    def get_default_model(self) -> str:
+        return "test-model"
+
+
+class TestMemoryConsolidationTypeHandling:
+    """Test that consolidation handles various argument types correctly."""
+
+    @pytest.mark.asyncio
+    async def test_string_arguments_work(self, tmp_path: Path) -> None:
+        """Normal case: LLM returns string arguments."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+        provider.chat = AsyncMock(
+            return_value=_make_tool_response(
+                history_entry="[2026-01-01] User discussed testing.",
+                memory_update="# Memory\nUser likes testing.",
+            )
+        )
+        provider.chat_with_retry = provider.chat
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is True
+        assert store.history_file.exists()
+        assert "[2026-01-01] User discussed testing." in store.history_file.read_text()
+        assert "User likes testing." in store.memory_file.read_text()
+
+    @pytest.mark.asyncio
+    async def test_dict_arguments_serialized_to_json(self, tmp_path: Path) -> None:
+        """Issue #1042: LLM returns dict instead of string — must not raise TypeError."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+        provider.chat = AsyncMock(
+            return_value=_make_tool_response(
+                history_entry={"timestamp": "2026-01-01", "summary": "User discussed testing."},
+                memory_update={"facts": ["User likes testing"], "topics": ["testing"]},
+            )
+        )
+        provider.chat_with_retry = provider.chat
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is True
+        assert store.history_file.exists()
+        history_content = store.history_file.read_text()
+        parsed = json.loads(history_content.strip())
+        assert parsed["summary"] == "User discussed testing."
+
+        memory_content = store.memory_file.read_text()
+        parsed_mem = json.loads(memory_content)
+        assert "User likes testing" in parsed_mem["facts"]
+
+    @pytest.mark.asyncio
+    async def test_string_arguments_as_raw_json(self, tmp_path: Path) -> None:
+        """Some providers return arguments as a JSON string instead of parsed dict."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+
+        response = LLMResponse(
+            content=None,
+            tool_calls=[
+                ToolCallRequest(
+                    id="call_1",
+                    name="save_memory",
+                    arguments=json.dumps({
+                        "history_entry": "[2026-01-01] User discussed testing.",
+                        "memory_update": "# Memory\nUser likes testing.",
+                    }),
+                )
+            ],
+        )
+        provider.chat = AsyncMock(return_value=response)
+        provider.chat_with_retry = provider.chat
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is True
+        assert "User discussed testing." in store.history_file.read_text()
+
+    @pytest.mark.asyncio
+    async def test_no_tool_call_returns_false(self, tmp_path: Path) -> None:
+        """When LLM doesn't use the save_memory tool, return False."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+        provider.chat = AsyncMock(
+            return_value=LLMResponse(content="I summarized the conversation.", tool_calls=[])
+        )
+        provider.chat_with_retry = provider.chat
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is False
+        assert not store.history_file.exists()
+
+    @pytest.mark.asyncio
+    async def test_skips_when_message_chunk_is_empty(self, tmp_path: Path) -> None:
+        """Consolidation should be a no-op when the selected chunk is empty."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+        provider.chat_with_retry = provider.chat
+        messages: list[dict] = []
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is True
+        provider.chat.assert_not_called()
+
+    @pytest.mark.asyncio
+    async def test_list_arguments_extracts_first_dict(self, tmp_path: Path) -> None:
+        """Some providers return arguments as a list - extract first element if it's a dict."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+
+        response = LLMResponse(
+            content=None,
+            tool_calls=[
+                ToolCallRequest(
+                    id="call_1",
+                    name="save_memory",
+                    arguments=[{
+                        "history_entry": "[2026-01-01] User discussed testing.",
+                        "memory_update": "# Memory\nUser likes testing.",
+                    }],
+                )
+            ],
+        )
+        provider.chat = AsyncMock(return_value=response)
+        provider.chat_with_retry = provider.chat
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is True
+        assert "User discussed testing." in store.history_file.read_text()
+        assert "User likes testing." in store.memory_file.read_text()
+
+    @pytest.mark.asyncio
+    async def test_list_arguments_empty_list_returns_false(self, tmp_path: Path) -> None:
+        """Empty list arguments should return False."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+
+        response = LLMResponse(
+            content=None,
+            tool_calls=[
+                ToolCallRequest(
+                    id="call_1",
+                    name="save_memory",
+                    arguments=[],
+                )
+            ],
+        )
+        provider.chat = AsyncMock(return_value=response)
+        provider.chat_with_retry = provider.chat
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is False
+
+    @pytest.mark.asyncio
+    async def test_list_arguments_non_dict_content_returns_false(self, tmp_path: Path) -> None:
+        """List with non-dict content should return False."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+
+        response = LLMResponse(
+            content=None,
+            tool_calls=[
+                ToolCallRequest(
+                    id="call_1",
+                    name="save_memory",
+                    arguments=["string", "content"],
+                )
+            ],
+        )
+        provider.chat = AsyncMock(return_value=response)
+        provider.chat_with_retry = provider.chat
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is False
+
+    @pytest.mark.asyncio
+    async def test_missing_history_entry_returns_false_without_writing(self, tmp_path: Path) -> None:
+        """Do not persist partial results when required fields are missing."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+        provider.chat_with_retry = AsyncMock(
+            return_value=LLMResponse(
+                content=None,
+                tool_calls=[
+                    ToolCallRequest(
+                        id="call_1",
+                        name="save_memory",
+                        arguments={"memory_update": "# Memory\nOnly memory update"},
+                    )
+                ],
+            )
+        )
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is False
+        assert not store.history_file.exists()
+        assert not store.memory_file.exists()
+
+    @pytest.mark.asyncio
+    async def test_missing_memory_update_returns_false_without_writing(self, tmp_path: Path) -> None:
+        """Do not append history if memory_update is missing."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+        provider.chat_with_retry = AsyncMock(
+            return_value=LLMResponse(
+                content=None,
+                tool_calls=[
+                    ToolCallRequest(
+                        id="call_1",
+                        name="save_memory",
+                        arguments={"history_entry": "[2026-01-01] Partial output."},
+                    )
+                ],
+            )
+        )
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is False
+        assert not store.history_file.exists()
+        assert not store.memory_file.exists()
+
+    @pytest.mark.asyncio
+    async def test_null_required_field_returns_false_without_writing(self, tmp_path: Path) -> None:
+        """Null required fields should be rejected before persistence."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+        provider.chat_with_retry = AsyncMock(
+            return_value=_make_tool_response(
+                history_entry=None,
+                memory_update="# Memory\nUser likes testing.",
+            )
+        )
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is False
+        assert not store.history_file.exists()
+        assert not store.memory_file.exists()
+
+    @pytest.mark.asyncio
+    async def test_empty_history_entry_returns_false_without_writing(self, tmp_path: Path) -> None:
+        """Empty history entries should be rejected to avoid blank archival records."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+        provider.chat_with_retry = AsyncMock(
+            return_value=_make_tool_response(
+                history_entry="   ",
+                memory_update="# Memory\nUser likes testing.",
+            )
+        )
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is False
+        assert not store.history_file.exists()
+        assert not store.memory_file.exists()
+
+    @pytest.mark.asyncio
+    async def test_retries_transient_error_then_succeeds(self, tmp_path: Path, monkeypatch) -> None:
+        store = MemoryStore(tmp_path)
+        provider = ScriptedProvider([
+            LLMResponse(content="503 server error", finish_reason="error"),
+            _make_tool_response(
+                history_entry="[2026-01-01] User discussed testing.",
+                memory_update="# Memory\nUser likes testing.",
+            ),
+        ])
+        messages = _make_messages(message_count=60)
+        delays: list[int] = []
+
+        async def _fake_sleep(delay: int) -> None:
+            delays.append(delay)
+
+        monkeypatch.setattr("nanobot.providers.base.asyncio.sleep", _fake_sleep)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is True
+        assert provider.calls == 2
+        assert delays == [1]
+
+    @pytest.mark.asyncio
+    async def test_consolidation_delegates_to_provider_defaults(self, tmp_path: Path) -> None:
+        """Consolidation no longer passes generation params — the provider owns them."""
+        store = MemoryStore(tmp_path)
+        provider = AsyncMock()
+        provider.chat_with_retry = AsyncMock(
+            return_value=_make_tool_response(
+                history_entry="[2026-01-01] User discussed testing.",
+                memory_update="# Memory\nUser likes testing.",
+            )
+        )
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is True
+        provider.chat_with_retry.assert_awaited_once()
+        _, kwargs = provider.chat_with_retry.await_args
+        assert kwargs["model"] == "test-model"
+        assert "temperature" not in kwargs
+        assert "max_tokens" not in kwargs
+        assert "reasoning_effort" not in kwargs
+
+    @pytest.mark.asyncio
+    async def test_tool_choice_fallback_on_unsupported_error(self, tmp_path: Path) -> None:
+        """Forced tool_choice rejected by provider -> retry with auto and succeed."""
+        store = MemoryStore(tmp_path)
+        error_resp = LLMResponse(
+            content="Error calling LLM: litellm.BadRequestError: "
+            "The tool_choice parameter does not support being set to required or object",
+            finish_reason="error",
+            tool_calls=[],
+        )
+        ok_resp = _make_tool_response(
+            history_entry="[2026-01-01] Fallback worked.",
+            memory_update="# Memory\nFallback OK.",
+        )
+
+        call_log: list[dict] = []
+
+        async def _tracking_chat(**kwargs):
+            call_log.append(kwargs)
+            return error_resp if len(call_log) == 1 else ok_resp
+
+        provider = AsyncMock()
+        provider.chat_with_retry = AsyncMock(side_effect=_tracking_chat)
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is True
+        assert len(call_log) == 2
+        assert isinstance(call_log[0]["tool_choice"], dict)
+        assert call_log[1]["tool_choice"] == "auto"
+        assert "Fallback worked." in store.history_file.read_text()
+
+    @pytest.mark.asyncio
+    async def test_tool_choice_fallback_auto_no_tool_call(self, tmp_path: Path) -> None:
+        """Forced rejected, auto retry also produces no tool call -> return False."""
+        store = MemoryStore(tmp_path)
+        error_resp = LLMResponse(
+            content="Error: tool_choice must be none or auto",
+            finish_reason="error",
+            tool_calls=[],
+        )
+        no_tool_resp = LLMResponse(
+            content="Here is a summary.",
+            finish_reason="stop",
+            tool_calls=[],
+        )
+
+        provider = AsyncMock()
+        provider.chat_with_retry = AsyncMock(side_effect=[error_resp, no_tool_resp])
+        messages = _make_messages(message_count=60)
+
+        result = await store.consolidate(messages, provider, "test-model")
+
+        assert result is False
+        assert not store.history_file.exists()
+
+    @pytest.mark.asyncio
+    async def test_raw_archive_after_consecutive_failures(self, tmp_path: Path) -> None:
+        """After 3 consecutive failures, raw-archive messages and return True."""
+        store = MemoryStore(tmp_path)
+        no_tool = LLMResponse(content="No tool call.", finish_reason="stop", tool_calls=[])
+        provider = AsyncMock()
+        provider.chat_with_retry = AsyncMock(return_value=no_tool)
+        messages = _make_messages(message_count=10)
+
+        assert await store.consolidate(messages, provider, "m") is False
+        assert await store.consolidate(messages, provider, "m") is False
+        assert await store.consolidate(messages, provider, "m") is True
+
+        assert store.history_file.exists()
+        content = store.history_file.read_text()
+        assert "[RAW]" in content
+        assert "10 messages" in content
+        assert "msg0" in content
+        assert not store.memory_file.exists()
+
+    @pytest.mark.asyncio
+    async def test_raw_archive_counter_resets_on_success(self, tmp_path: Path) -> None:
+        """A successful consolidation resets the failure counter."""
+        store = MemoryStore(tmp_path)
+        no_tool = LLMResponse(content="Nope.", finish_reason="stop", tool_calls=[])
+        ok_resp = _make_tool_response(
+            history_entry="[2026-01-01] OK.",
+            memory_update="# Memory\nOK.",
+        )
+        messages = _make_messages(message_count=10)
+
+        provider = AsyncMock()
+        provider.chat_with_retry = AsyncMock(return_value=no_tool)
+        assert await store.consolidate(messages, provider, "m") is False
+        assert await store.consolidate(messages, provider, "m") is False
+        assert store._consecutive_failures == 2
+
+        provider.chat_with_retry = AsyncMock(return_value=ok_resp)
+        assert await store.consolidate(messages, provider, "m") is True
+        assert store._consecutive_failures == 0
+
+        provider.chat_with_retry = AsyncMock(return_value=no_tool)
+        assert await store.consolidate(messages, provider, "m") is False
+        assert store._consecutive_failures == 1

tests/agent/test_onboard_logic.py

@@ -0,0 +1,495 @@
+"""Unit tests for onboard core logic functions.
+
+These tests focus on the business logic behind the onboard wizard,
+without testing the interactive UI components.
+"""
+
+import json
+from pathlib import Path
+from types import SimpleNamespace
+from typing import Any, cast
+
+import pytest
+from pydantic import BaseModel, Field
+
+from nanobot.cli import onboard as onboard_wizard
+
+# Import functions to test
+from nanobot.cli.commands import _merge_missing_defaults
+from nanobot.cli.onboard import (
+    _BACK_PRESSED,
+    _configure_pydantic_model,
+    _format_value,
+    _get_field_display_name,
+    _get_field_type_info,
+    run_onboard,
+)
+from nanobot.config.schema import Config
+from nanobot.utils.helpers import sync_workspace_templates
+
+
+class TestMergeMissingDefaults:
+    """Tests for _merge_missing_defaults recursive config merging."""
+
+    def test_adds_missing_top_level_keys(self):
+        existing = {"a": 1}
+        defaults = {"a": 1, "b": 2, "c": 3}
+
+        result = _merge_missing_defaults(existing, defaults)
+
+        assert result == {"a": 1, "b": 2, "c": 3}
+
+    def test_preserves_existing_values(self):
+        existing = {"a": "custom_value"}
+        defaults = {"a": "default_value"}
+
+        result = _merge_missing_defaults(existing, defaults)
+
+        assert result == {"a": "custom_value"}
+
+    def test_merges_nested_dicts_recursively(self):
+        existing = {
+            "level1": {
+                "level2": {
+                    "existing": "kept",
+                }
+            }
+        }
+        defaults = {
+            "level1": {
+                "level2": {
+                    "existing": "replaced",
+                    "added": "new",
+                },
+                "level2b": "also_new",
+            }
+        }
+
+        result = _merge_missing_defaults(existing, defaults)
+
+        assert result == {
+            "level1": {
+                "level2": {
+                    "existing": "kept",
+                    "added": "new",
+                },
+                "level2b": "also_new",
+            }
+        }
+
+    def test_returns_existing_if_not_dict(self):
+        assert _merge_missing_defaults("string", {"a": 1}) == "string"
+        assert _merge_missing_defaults([1, 2, 3], {"a": 1}) == [1, 2, 3]
+        assert _merge_missing_defaults(None, {"a": 1}) is None
+        assert _merge_missing_defaults(42, {"a": 1}) == 42
+
+    def test_returns_existing_if_defaults_not_dict(self):
+        assert _merge_missing_defaults({"a": 1}, "string") == {"a": 1}
+        assert _merge_missing_defaults({"a": 1}, None) == {"a": 1}
+
+    def test_handles_empty_dicts(self):
+        assert _merge_missing_defaults({}, {"a": 1}) == {"a": 1}
+        assert _merge_missing_defaults({"a": 1}, {}) == {"a": 1}
+        assert _merge_missing_defaults({}, {}) == {}
+
+    def test_backfills_channel_config(self):
+        """Real-world scenario: backfill missing channel fields."""
+        existing_channel = {
+            "enabled": False,
+            "appId": "",
+            "secret": "",
+        }
+        default_channel = {
+            "enabled": False,
+            "appId": "",
+            "secret": "",
+            "msgFormat": "plain",
+            "allowFrom": [],
+        }
+
+        result = _merge_missing_defaults(existing_channel, default_channel)
+
+        assert result["msgFormat"] == "plain"
+        assert result["allowFrom"] == []
+
+
+class TestGetFieldTypeInfo:
+    """Tests for _get_field_type_info type extraction."""
+
+    def test_extracts_str_type(self):
+        class Model(BaseModel):
+            field: str
+
+        type_name, inner = _get_field_type_info(Model.model_fields["field"])
+        assert type_name == "str"
+        assert inner is None
+
+    def test_extracts_int_type(self):
+        class Model(BaseModel):
+            count: int
+
+        type_name, inner = _get_field_type_info(Model.model_fields["count"])
+        assert type_name == "int"
+        assert inner is None
+
+    def test_extracts_bool_type(self):
+        class Model(BaseModel):
+            enabled: bool
+
+        type_name, inner = _get_field_type_info(Model.model_fields["enabled"])
+        assert type_name == "bool"
+        assert inner is None
+
+    def test_extracts_float_type(self):
+        class Model(BaseModel):
+            ratio: float
+
+        type_name, inner = _get_field_type_info(Model.model_fields["ratio"])
+        assert type_name == "float"
+        assert inner is None
+
+    def test_extracts_list_type_with_item_type(self):
+        class Model(BaseModel):
+            items: list[str]
+
+        type_name, inner = _get_field_type_info(Model.model_fields["items"])
+        assert type_name == "list"
+        assert inner is str
+
+    def test_extracts_list_type_without_item_type(self):
+        # Plain list without type param falls back to str
+        class Model(BaseModel):
+            items: list  # type: ignore
+
+        # Plain list annotation doesn't match list check, returns str
+        type_name, inner = _get_field_type_info(Model.model_fields["items"])
+        assert type_name == "str"  # Falls back to str for untyped list
+        assert inner is None
+
+    def test_extracts_dict_type(self):
+        # Plain dict without type param falls back to str
+        class Model(BaseModel):
+            data: dict  # type: ignore
+
+        # Plain dict annotation doesn't match dict check, returns str
+        type_name, inner = _get_field_type_info(Model.model_fields["data"])
+        assert type_name == "str"  # Falls back to str for untyped dict
+        assert inner is None
+
+    def test_extracts_optional_type(self):
+        class Model(BaseModel):
+            optional: str | None = None
+
+        type_name, inner = _get_field_type_info(Model.model_fields["optional"])
+        # Should unwrap Optional and get str
+        assert type_name == "str"
+        assert inner is None
+
+    def test_extracts_nested_model_type(self):
+        class Inner(BaseModel):
+            x: int
+
+        class Outer(BaseModel):
+            nested: Inner
+
+        type_name, inner = _get_field_type_info(Outer.model_fields["nested"])
+        assert type_name == "model"
+        assert inner is Inner
+
+    def test_handles_none_annotation(self):
+        """Field with None annotation defaults to str."""
+        class Model(BaseModel):
+            field: Any = None
+
+        # Create a mock field_info with None annotation
+        field_info = SimpleNamespace(annotation=None)
+        type_name, inner = _get_field_type_info(field_info)
+        assert type_name == "str"
+        assert inner is None
+
+
+class TestGetFieldDisplayName:
+    """Tests for _get_field_display_name human-readable name generation."""
+
+    def test_uses_description_if_present(self):
+        class Model(BaseModel):
+            api_key: str = Field(description="API Key for authentication")
+
+        name = _get_field_display_name("api_key", Model.model_fields["api_key"])
+        assert name == "API Key for authentication"
+
+    def test_converts_snake_case_to_title(self):
+        field_info = SimpleNamespace(description=None)
+        name = _get_field_display_name("user_name", field_info)
+        assert name == "User Name"
+
+    def test_adds_url_suffix(self):
+        field_info = SimpleNamespace(description=None)
+        name = _get_field_display_name("api_url", field_info)
+        # Title case: "Api Url"
+        assert "Url" in name and "Api" in name
+
+    def test_adds_path_suffix(self):
+        field_info = SimpleNamespace(description=None)
+        name = _get_field_display_name("file_path", field_info)
+        assert "Path" in name and "File" in name
+
+    def test_adds_id_suffix(self):
+        field_info = SimpleNamespace(description=None)
+        name = _get_field_display_name("user_id", field_info)
+        # Title case: "User Id"
+        assert "Id" in name and "User" in name
+
+    def test_adds_key_suffix(self):
+        field_info = SimpleNamespace(description=None)
+        name = _get_field_display_name("api_key", field_info)
+        assert "Key" in name and "Api" in name
+
+    def test_adds_token_suffix(self):
+        field_info = SimpleNamespace(description=None)
+        name = _get_field_display_name("auth_token", field_info)
+        assert "Token" in name and "Auth" in name
+
+    def test_adds_seconds_suffix(self):
+        field_info = SimpleNamespace(description=None)
+        name = _get_field_display_name("timeout_s", field_info)
+        # Contains "(Seconds)" with title case
+        assert "(Seconds)" in name or "(seconds)" in name
+
+    def test_adds_ms_suffix(self):
+        field_info = SimpleNamespace(description=None)
+        name = _get_field_display_name("delay_ms", field_info)
+        # Contains "(Ms)" or "(ms)"
+        assert "(Ms)" in name or "(ms)" in name
+
+
+class TestFormatValue:
+    """Tests for _format_value display formatting."""
+
+    def test_formats_none_as_not_set(self):
+        assert "not set" in _format_value(None)
+
+    def test_formats_empty_string_as_not_set(self):
+        assert "not set" in _format_value("")
+
+    def test_formats_empty_dict_as_not_set(self):
+        assert "not set" in _format_value({})
+
+    def test_formats_empty_list_as_not_set(self):
+        assert "not set" in _format_value([])
+
+    def test_formats_string_value(self):
+        result = _format_value("hello")
+        assert "hello" in result
+
+    def test_formats_list_value(self):
+        result = _format_value(["a", "b"])
+        assert "a" in result or "b" in result
+
+    def test_formats_dict_value(self):
+        result = _format_value({"key": "value"})
+        assert "key" in result or "value" in result
+
+    def test_formats_int_value(self):
+        result = _format_value(42)
+        assert "42" in result
+
+    def test_formats_bool_true(self):
+        result = _format_value(True)
+        assert "true" in result.lower() or "✓" in result
+
+    def test_formats_bool_false(self):
+        result = _format_value(False)
+        assert "false" in result.lower() or "✗" in result
+
+
+class TestSyncWorkspaceTemplates:
+    """Tests for sync_workspace_templates file synchronization."""
+
+    def test_creates_missing_files(self, tmp_path):
+        """Should create template files that don't exist."""
+        workspace = tmp_path / "workspace"
+
+        added = sync_workspace_templates(workspace, silent=True)
+
+        # Check that some files were created
+        assert isinstance(added, list)
+        # The actual files depend on the templates directory
+
+    def test_does_not_overwrite_existing_files(self, tmp_path):
+        """Should not overwrite files that already exist."""
+        workspace = tmp_path / "workspace"
+        workspace.mkdir(parents=True)
+        (workspace / "AGENTS.md").write_text("existing content")
+
+        sync_workspace_templates(workspace, silent=True)
+
+        # Existing file should not be changed
+        content = (workspace / "AGENTS.md").read_text()
+        assert content == "existing content"
+
+    def test_creates_memory_directory(self, tmp_path):
+        """Should create memory directory structure."""
+        workspace = tmp_path / "workspace"
+
+        sync_workspace_templates(workspace, silent=True)
+
+        assert (workspace / "memory").exists() or (workspace / "skills").exists()
+
+    def test_returns_list_of_added_files(self, tmp_path):
+        """Should return list of relative paths for added files."""
+        workspace = tmp_path / "workspace"
+
+        added = sync_workspace_templates(workspace, silent=True)
+
+        assert isinstance(added, list)
+        # All paths should be relative to workspace
+        for path in added:
+            assert not Path(path).is_absolute()
+
+
+class TestProviderChannelInfo:
+    """Tests for provider and channel info retrieval."""
+
+    def test_get_provider_names_returns_dict(self):
+        from nanobot.cli.onboard import _get_provider_names
+
+        names = _get_provider_names()
+        assert isinstance(names, dict)
+        assert len(names) > 0
+        # Should include common providers
+        assert "openai" in names or "anthropic" in names
+        assert "openai_codex" not in names
+        assert "github_copilot" not in names
+
+    def test_get_channel_names_returns_dict(self):
+        from nanobot.cli.onboard import _get_channel_names
+
+        names = _get_channel_names()
+        assert isinstance(names, dict)
+        # Should include at least some channels
+        assert len(names) >= 0
+
+    def test_get_provider_info_returns_valid_structure(self):
+        from nanobot.cli.onboard import _get_provider_info
+
+        info = _get_provider_info()
+        assert isinstance(info, dict)
+        # Each value should be a tuple with expected structure
+        for provider_name, value in info.items():
+            assert isinstance(value, tuple)
+            assert len(value) == 4  # (display_name, needs_api_key, needs_api_base, env_var)
+
+
+class _SimpleDraftModel(BaseModel):
+    api_key: str = ""
+
+
+class _NestedDraftModel(BaseModel):
+    api_key: str = ""
+
+
+class _OuterDraftModel(BaseModel):
+    nested: _NestedDraftModel = Field(default_factory=_NestedDraftModel)
+
+
+class TestConfigurePydanticModelDrafts:
+    @staticmethod
+    def _patch_prompt_helpers(monkeypatch, tokens, text_value="secret"):
+        sequence = iter(tokens)
+
+        def fake_select(_prompt, choices, default=None):
+            token = next(sequence)
+            if token == "first":
+                return choices[0]
+            if token == "done":
+                return "[Done]"
+            if token == "back":
+                return _BACK_PRESSED
+            return token
+
+        monkeypatch.setattr(onboard_wizard, "_select_with_back", fake_select)
+        monkeypatch.setattr(onboard_wizard, "_show_config_panel", lambda *_args, **_kwargs: None)
+        monkeypatch.setattr(
+            onboard_wizard, "_input_with_existing", lambda *_args, **_kwargs: text_value
+        )
+
+    def test_discarding_section_keeps_original_model_unchanged(self, monkeypatch):
+        model = _SimpleDraftModel()
+        self._patch_prompt_helpers(monkeypatch, ["first", "back"])
+
+        result = _configure_pydantic_model(model, "Simple")
+
+        assert result is None
+        assert model.api_key == ""
+
+    def test_completing_section_returns_updated_draft(self, monkeypatch):
+        model = _SimpleDraftModel()
+        self._patch_prompt_helpers(monkeypatch, ["first", "done"])
+
+        result = _configure_pydantic_model(model, "Simple")
+
+        assert result is not None
+        updated = cast(_SimpleDraftModel, result)
+        assert updated.api_key == "secret"
+        assert model.api_key == ""
+
+    def test_nested_section_back_discards_nested_edits(self, monkeypatch):
+        model = _OuterDraftModel()
+        self._patch_prompt_helpers(monkeypatch, ["first", "first", "back", "done"])
+
+        result = _configure_pydantic_model(model, "Outer")
+
+        assert result is not None
+        updated = cast(_OuterDraftModel, result)
+        assert updated.nested.api_key == ""
+        assert model.nested.api_key == ""
+
+    def test_nested_section_done_commits_nested_edits(self, monkeypatch):
+        model = _OuterDraftModel()
+        self._patch_prompt_helpers(monkeypatch, ["first", "first", "done", "done"])
+
+        result = _configure_pydantic_model(model, "Outer")
+
+        assert result is not None
+        updated = cast(_OuterDraftModel, result)
+        assert updated.nested.api_key == "secret"
+        assert model.nested.api_key == ""
+
+
+class TestRunOnboardExitBehavior:
+    def test_main_menu_interrupt_can_discard_unsaved_session_changes(self, monkeypatch):
+        initial_config = Config()
+
+        responses = iter(
+            [
+                "[A] Agent Settings",
+                KeyboardInterrupt(),
+                "[X] Exit Without Saving",
+            ]
+        )
+
+        class FakePrompt:
+            def __init__(self, response):
+                self.response = response
+
+            def ask(self):
+                if isinstance(self.response, BaseException):
+                    raise self.response
+                return self.response
+
+        def fake_select(*_args, **_kwargs):
+            return FakePrompt(next(responses))
+
+        def fake_configure_general_settings(config, section):
+            if section == "Agent Settings":
+                config.agents.defaults.model = "test/provider-model"
+
+        monkeypatch.setattr(onboard_wizard, "_show_main_menu_header", lambda: None)
+        monkeypatch.setattr(onboard_wizard, "questionary", SimpleNamespace(select=fake_select))
+        monkeypatch.setattr(onboard_wizard, "_configure_general_settings", fake_configure_general_settings)
+
+        result = run_onboard(initial_config=initial_config)
+
+        assert result.should_save is False
+        assert result.config.model_dump(by_alias=True) == initial_config.model_dump(by_alias=True)

tests/agent/test_session_manager_history.py

@@ -0,0 +1,198 @@
+from nanobot.session.manager import Session
+
+
+def _assert_no_orphans(history: list[dict]) -> None:
+    """Assert every tool result in history has a matching assistant tool_call."""
+    declared = {
+        tc["id"]
+        for m in history if m.get("role") == "assistant"
+        for tc in (m.get("tool_calls") or [])
+    }
+    orphans = [
+        m.get("tool_call_id") for m in history
+        if m.get("role") == "tool" and m.get("tool_call_id") not in declared
+    ]
+    assert orphans == [], f"orphan tool_call_ids: {orphans}"
+
+
+def _tool_turn(prefix: str, idx: int) -> list[dict]:
+    """Helper: one assistant with 2 tool_calls + 2 tool results."""
+    return [
+        {
+            "role": "assistant",
+            "content": None,
+            "tool_calls": [
+                {"id": f"{prefix}_{idx}_a", "type": "function", "function": {"name": "x", "arguments": "{}"}},
+                {"id": f"{prefix}_{idx}_b", "type": "function", "function": {"name": "y", "arguments": "{}"}},
+            ],
+        },
+        {"role": "tool", "tool_call_id": f"{prefix}_{idx}_a", "name": "x", "content": "ok"},
+        {"role": "tool", "tool_call_id": f"{prefix}_{idx}_b", "name": "y", "content": "ok"},
+    ]
+
+
+# --- Original regression test (from PR 2075) ---
+
+def test_get_history_drops_orphan_tool_results_when_window_cuts_tool_calls():
+    session = Session(key="telegram:test")
+    session.messages.append({"role": "user", "content": "old turn"})
+    for i in range(20):
+        session.messages.extend(_tool_turn("old", i))
+    session.messages.append({"role": "user", "content": "problem turn"})
+    for i in range(25):
+        session.messages.extend(_tool_turn("cur", i))
+    session.messages.append({"role": "user", "content": "new telegram question"})
+
+    history = session.get_history(max_messages=100)
+    _assert_no_orphans(history)
+
+
+# --- Positive test: legitimate pairs survive trimming ---
+
+def test_legitimate_tool_pairs_preserved_after_trim():
+    """Complete tool-call groups within the window must not be dropped."""
+    session = Session(key="test:positive")
+    session.messages.append({"role": "user", "content": "hello"})
+    for i in range(5):
+        session.messages.extend(_tool_turn("ok", i))
+    session.messages.append({"role": "assistant", "content": "done"})
+
+    history = session.get_history(max_messages=500)
+    _assert_no_orphans(history)
+    tool_ids = [m["tool_call_id"] for m in history if m.get("role") == "tool"]
+    assert len(tool_ids) == 10
+    assert history[0]["role"] == "user"
+
+
+def test_retain_recent_legal_suffix_keeps_recent_messages():
+    session = Session(key="test:trim")
+    for i in range(10):
+        session.messages.append({"role": "user", "content": f"msg{i}"})
+
+    session.retain_recent_legal_suffix(4)
+
+    assert len(session.messages) == 4
+    assert session.messages[0]["content"] == "msg6"
+    assert session.messages[-1]["content"] == "msg9"
+
+
+def test_retain_recent_legal_suffix_adjusts_last_consolidated():
+    session = Session(key="test:trim-cons")
+    for i in range(10):
+        session.messages.append({"role": "user", "content": f"msg{i}"})
+    session.last_consolidated = 7
+
+    session.retain_recent_legal_suffix(4)
+
+    assert len(session.messages) == 4
+    assert session.last_consolidated == 1
+
+
+def test_retain_recent_legal_suffix_zero_clears_session():
+    session = Session(key="test:trim-zero")
+    for i in range(10):
+        session.messages.append({"role": "user", "content": f"msg{i}"})
+    session.last_consolidated = 5
+
+    session.retain_recent_legal_suffix(0)
+
+    assert session.messages == []
+    assert session.last_consolidated == 0
+
+
+def test_retain_recent_legal_suffix_keeps_legal_tool_boundary():
+    session = Session(key="test:trim-tools")
+    session.messages.append({"role": "user", "content": "old"})
+    session.messages.extend(_tool_turn("old", 0))
+    session.messages.append({"role": "user", "content": "keep"})
+    session.messages.extend(_tool_turn("keep", 0))
+    session.messages.append({"role": "assistant", "content": "done"})
+
+    session.retain_recent_legal_suffix(4)
+
+    history = session.get_history(max_messages=500)
+    _assert_no_orphans(history)
+    assert history[0]["role"] == "user"
+    assert history[0]["content"] == "keep"
+
+
+# --- last_consolidated > 0 ---
+
+def test_orphan_trim_with_last_consolidated():
+    """Orphan trimming works correctly when session is partially consolidated."""
+    session = Session(key="test:consolidated")
+    for i in range(10):
+        session.messages.append({"role": "user", "content": f"old {i}"})
+        session.messages.extend(_tool_turn("cons", i))
+    session.last_consolidated = 30
+
+    session.messages.append({"role": "user", "content": "recent"})
+    for i in range(15):
+        session.messages.extend(_tool_turn("new", i))
+    session.messages.append({"role": "user", "content": "latest"})
+
+    history = session.get_history(max_messages=20)
+    _assert_no_orphans(history)
+    assert all(m.get("role") != "tool" or m["tool_call_id"].startswith("new_") for m in history)
+
+
+# --- Edge: no tool messages at all ---
+
+def test_no_tool_messages_unchanged():
+    session = Session(key="test:plain")
+    for i in range(5):
+        session.messages.append({"role": "user", "content": f"q{i}"})
+        session.messages.append({"role": "assistant", "content": f"a{i}"})
+
+    history = session.get_history(max_messages=6)
+    assert len(history) == 6
+    _assert_no_orphans(history)
+
+
+# --- Edge: all leading messages are orphan tool results ---
+
+def test_all_orphan_prefix_stripped():
+    """If the window starts with orphan tool results and nothing else, they're all dropped."""
+    session = Session(key="test:all-orphan")
+    session.messages.append({"role": "tool", "tool_call_id": "gone_1", "name": "x", "content": "ok"})
+    session.messages.append({"role": "tool", "tool_call_id": "gone_2", "name": "y", "content": "ok"})
+    session.messages.append({"role": "user", "content": "fresh start"})
+    session.messages.append({"role": "assistant", "content": "hi"})
+
+    history = session.get_history(max_messages=500)
+    _assert_no_orphans(history)
+    assert history[0]["role"] == "user"
+    assert len(history) == 2
+
+
+# --- Edge: empty session ---
+
+def test_empty_session_history():
+    session = Session(key="test:empty")
+    history = session.get_history(max_messages=500)
+    assert history == []
+
+
+# --- Window cuts mid-group: assistant present but some tool results orphaned ---
+
+def test_window_cuts_mid_tool_group():
+    """If the window starts between an assistant's tool results, the partial group is trimmed."""
+    session = Session(key="test:mid-cut")
+    session.messages.append({"role": "user", "content": "setup"})
+    session.messages.append({
+        "role": "assistant", "content": None,
+        "tool_calls": [
+            {"id": "split_a", "type": "function", "function": {"name": "x", "arguments": "{}"}},
+            {"id": "split_b", "type": "function", "function": {"name": "y", "arguments": "{}"}},
+        ],
+    })
+    session.messages.append({"role": "tool", "tool_call_id": "split_a", "name": "x", "content": "ok"})
+    session.messages.append({"role": "tool", "tool_call_id": "split_b", "name": "y", "content": "ok"})
+    session.messages.append({"role": "user", "content": "next"})
+    session.messages.extend(_tool_turn("intact", 0))
+    session.messages.append({"role": "assistant", "content": "final"})
+
+    # Window of 6 should cut off the "setup" user msg and the assistant with split_a/split_b,
+    # leaving orphan tool results for split_a at the front.
+    history = session.get_history(max_messages=6)
+    _assert_no_orphans(history)

tests/agent/test_skill_creator_scripts.py

@@ -0,0 +1,127 @@
+import importlib
+import shutil
+import sys
+import zipfile
+from pathlib import Path
+
+
+SCRIPT_DIR = Path("nanobot/skills/skill-creator/scripts").resolve()
+if str(SCRIPT_DIR) not in sys.path:
+    sys.path.insert(0, str(SCRIPT_DIR))
+
+init_skill = importlib.import_module("init_skill")
+package_skill = importlib.import_module("package_skill")
+quick_validate = importlib.import_module("quick_validate")
+
+
+def test_init_skill_creates_expected_files(tmp_path: Path) -> None:
+    skill_dir = init_skill.init_skill(
+        "demo-skill",
+        tmp_path,
+        ["scripts", "references", "assets"],
+        include_examples=True,
+    )
+
+    assert skill_dir == tmp_path / "demo-skill"
+    assert (skill_dir / "SKILL.md").exists()
+    assert (skill_dir / "scripts" / "example.py").exists()
+    assert (skill_dir / "references" / "api_reference.md").exists()
+    assert (skill_dir / "assets" / "example_asset.txt").exists()
+
+
+def test_validate_skill_accepts_existing_skill_creator() -> None:
+    valid, message = quick_validate.validate_skill(
+        Path("nanobot/skills/skill-creator").resolve()
+    )
+
+    assert valid, message
+
+
+def test_validate_skill_rejects_placeholder_description(tmp_path: Path) -> None:
+    skill_dir = tmp_path / "placeholder-skill"
+    skill_dir.mkdir()
+    (skill_dir / "SKILL.md").write_text(
+        "---\n"
+        "name: placeholder-skill\n"
+        'description: "[TODO: fill me in]"\n'
+        "---\n"
+        "# Placeholder\n",
+        encoding="utf-8",
+    )
+
+    valid, message = quick_validate.validate_skill(skill_dir)
+
+    assert not valid
+    assert "TODO placeholder" in message
+
+
+def test_validate_skill_rejects_root_files_outside_allowed_dirs(tmp_path: Path) -> None:
+    skill_dir = tmp_path / "bad-root-skill"
+    skill_dir.mkdir()
+    (skill_dir / "SKILL.md").write_text(
+        "---\n"
+        "name: bad-root-skill\n"
+        "description: Valid description\n"
+        "---\n"
+        "# Skill\n",
+        encoding="utf-8",
+    )
+    (skill_dir / "README.md").write_text("extra\n", encoding="utf-8")
+
+    valid, message = quick_validate.validate_skill(skill_dir)
+
+    assert not valid
+    assert "Unexpected file or directory in skill root" in message
+
+
+def test_package_skill_creates_archive(tmp_path: Path) -> None:
+    skill_dir = tmp_path / "package-me"
+    skill_dir.mkdir()
+    (skill_dir / "SKILL.md").write_text(
+        "---\n"
+        "name: package-me\n"
+        "description: Package this skill.\n"
+        "---\n"
+        "# Skill\n",
+        encoding="utf-8",
+    )
+    scripts_dir = skill_dir / "scripts"
+    scripts_dir.mkdir()
+    (scripts_dir / "helper.py").write_text("print('ok')\n", encoding="utf-8")
+
+    archive_path = package_skill.package_skill(skill_dir, tmp_path / "dist")
+
+    assert archive_path == (tmp_path / "dist" / "package-me.skill")
+    assert archive_path.exists()
+    with zipfile.ZipFile(archive_path, "r") as archive:
+        names = set(archive.namelist())
+    assert "package-me/SKILL.md" in names
+    assert "package-me/scripts/helper.py" in names
+
+
+def test_package_skill_rejects_symlink(tmp_path: Path) -> None:
+    skill_dir = tmp_path / "symlink-skill"
+    skill_dir.mkdir()
+    (skill_dir / "SKILL.md").write_text(
+        "---\n"
+        "name: symlink-skill\n"
+        "description: Reject symlinks during packaging.\n"
+        "---\n"
+        "# Skill\n",
+        encoding="utf-8",
+    )
+    scripts_dir = skill_dir / "scripts"
+    scripts_dir.mkdir()
+    target = tmp_path / "outside.txt"
+    target.write_text("secret\n", encoding="utf-8")
+    link = scripts_dir / "outside.txt"
+
+    try:
+        link.symlink_to(target)
+    except (OSError, NotImplementedError):
+        return
+
+    archive_path = package_skill.package_skill(skill_dir, tmp_path / "dist")
+
+    assert archive_path is None
+    assert not (tmp_path / "dist" / "symlink-skill.skill").exists()

tests/agent/test_task_cancel.py

@@ -0,0 +1,223 @@
+"""Tests for /stop task cancellation."""
+
+from __future__ import annotations
+
+import asyncio
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import pytest
+
+
+def _make_loop(*, exec_config=None):
+    """Create a minimal AgentLoop with mocked dependencies."""
+    from nanobot.agent.loop import AgentLoop
+    from nanobot.bus.queue import MessageBus
+
+    bus = MessageBus()
+    provider = MagicMock()
+    provider.get_default_model.return_value = "test-model"
+    workspace = MagicMock()
+    workspace.__truediv__ = MagicMock(return_value=MagicMock())
+
+    with patch("nanobot.agent.loop.ContextBuilder"), \
+         patch("nanobot.agent.loop.SessionManager"), \
+         patch("nanobot.agent.loop.SubagentManager") as MockSubMgr:
+        MockSubMgr.return_value.cancel_by_session = AsyncMock(return_value=0)
+        loop = AgentLoop(bus=bus, provider=provider, workspace=workspace, exec_config=exec_config)
+    return loop, bus
+
+
+class TestHandleStop:
+    @pytest.mark.asyncio
+    async def test_stop_no_active_task(self):
+        from nanobot.bus.events import InboundMessage
+        from nanobot.command.builtin import cmd_stop
+        from nanobot.command.router import CommandContext
+
+        loop, bus = _make_loop()
+        msg = InboundMessage(channel="test", sender_id="u1", chat_id="c1", content="/stop")
+        ctx = CommandContext(msg=msg, session=None, key=msg.session_key, raw="/stop", loop=loop)
+        out = await cmd_stop(ctx)
+        assert "No active task" in out.content
+
+    @pytest.mark.asyncio
+    async def test_stop_cancels_active_task(self):
+        from nanobot.bus.events import InboundMessage
+        from nanobot.command.builtin import cmd_stop
+        from nanobot.command.router import CommandContext
+
+        loop, bus = _make_loop()
+        cancelled = asyncio.Event()
+
+        async def slow_task():
+            try:
+                await asyncio.sleep(60)
+            except asyncio.CancelledError:
+                cancelled.set()
+                raise
+
+        task = asyncio.create_task(slow_task())
+        await asyncio.sleep(0)
+        loop._active_tasks["test:c1"] = [task]
+
+        msg = InboundMessage(channel="test", sender_id="u1", chat_id="c1", content="/stop")
+        ctx = CommandContext(msg=msg, session=None, key=msg.session_key, raw="/stop", loop=loop)
+        out = await cmd_stop(ctx)
+
+        assert cancelled.is_set()
+        assert "stopped" in out.content.lower()
+
+    @pytest.mark.asyncio
+    async def test_stop_cancels_multiple_tasks(self):
+        from nanobot.bus.events import InboundMessage
+        from nanobot.command.builtin import cmd_stop
+        from nanobot.command.router import CommandContext
+
+        loop, bus = _make_loop()
+        events = [asyncio.Event(), asyncio.Event()]
+
+        async def slow(idx):
+            try:
+                await asyncio.sleep(60)
+            except asyncio.CancelledError:
+                events[idx].set()
+                raise
+
+        tasks = [asyncio.create_task(slow(i)) for i in range(2)]
+        await asyncio.sleep(0)
+        loop._active_tasks["test:c1"] = tasks
+
+        msg = InboundMessage(channel="test", sender_id="u1", chat_id="c1", content="/stop")
+        ctx = CommandContext(msg=msg, session=None, key=msg.session_key, raw="/stop", loop=loop)
+        out = await cmd_stop(ctx)
+
+        assert all(e.is_set() for e in events)
+        assert "2 task" in out.content
+
+
+class TestDispatch:
+    def test_exec_tool_not_registered_when_disabled(self):
+        from nanobot.config.schema import ExecToolConfig
+
+        loop, _bus = _make_loop(exec_config=ExecToolConfig(enable=False))
+
+        assert loop.tools.get("exec") is None
+
+    @pytest.mark.asyncio
+    async def test_dispatch_processes_and_publishes(self):
+        from nanobot.bus.events import InboundMessage, OutboundMessage
+
+        loop, bus = _make_loop()
+        msg = InboundMessage(channel="test", sender_id="u1", chat_id="c1", content="hello")
+        loop._process_message = AsyncMock(
+            return_value=OutboundMessage(channel="test", chat_id="c1", content="hi")
+        )
+        await loop._dispatch(msg)
+        out = await asyncio.wait_for(bus.consume_outbound(), timeout=1.0)
+        assert out.content == "hi"
+
+    @pytest.mark.asyncio
+    async def test_processing_lock_serializes(self):
+        from nanobot.bus.events import InboundMessage, OutboundMessage
+
+        loop, bus = _make_loop()
+        order = []
+
+        async def mock_process(m, **kwargs):
+            order.append(f"start-{m.content}")
+            await asyncio.sleep(0.05)
+            order.append(f"end-{m.content}")
+            return OutboundMessage(channel="test", chat_id="c1", content=m.content)
+
+        loop._process_message = mock_process
+        msg1 = InboundMessage(channel="test", sender_id="u1", chat_id="c1", content="a")
+        msg2 = InboundMessage(channel="test", sender_id="u1", chat_id="c1", content="b")
+
+        t1 = asyncio.create_task(loop._dispatch(msg1))
+        t2 = asyncio.create_task(loop._dispatch(msg2))
+        await asyncio.gather(t1, t2)
+        assert order == ["start-a", "end-a", "start-b", "end-b"]
+
+
+class TestSubagentCancellation:
+    @pytest.mark.asyncio
+    async def test_cancel_by_session(self):
+        from nanobot.agent.subagent import SubagentManager
+        from nanobot.bus.queue import MessageBus
+
+        bus = MessageBus()
+        provider = MagicMock()
+        provider.get_default_model.return_value = "test-model"
+        mgr = SubagentManager(provider=provider, workspace=MagicMock(), bus=bus)
+
+        cancelled = asyncio.Event()
+
+        async def slow():
+            try:
+                await asyncio.sleep(60)
+            except asyncio.CancelledError:
+                cancelled.set()
+                raise
+
+        task = asyncio.create_task(slow())
+        await asyncio.sleep(0)
+        mgr._running_tasks["sub-1"] = task
+        mgr._session_tasks["test:c1"] = {"sub-1"}
+
+        count = await mgr.cancel_by_session("test:c1")
+        assert count == 1
+        assert cancelled.is_set()
+
+    @pytest.mark.asyncio
+    async def test_cancel_by_session_no_tasks(self):
+        from nanobot.agent.subagent import SubagentManager
+        from nanobot.bus.queue import MessageBus
+
+        bus = MessageBus()
+        provider = MagicMock()
+        provider.get_default_model.return_value = "test-model"
+        mgr = SubagentManager(provider=provider, workspace=MagicMock(), bus=bus)
+        assert await mgr.cancel_by_session("nonexistent") == 0
+
+    @pytest.mark.asyncio
+    async def test_subagent_preserves_reasoning_fields_in_tool_turn(self, monkeypatch, tmp_path):
+        from nanobot.agent.subagent import SubagentManager
+        from nanobot.bus.queue import MessageBus
+        from nanobot.providers.base import LLMResponse, ToolCallRequest
+
+        bus = MessageBus()
+        provider = MagicMock()
+        provider.get_default_model.return_value = "test-model"
+
+        captured_second_call: list[dict] = []
+
+        call_count = {"n": 0}
+
+        async def scripted_chat_with_retry(*, messages, **kwargs):
+            call_count["n"] += 1
+            if call_count["n"] == 1:
+                return LLMResponse(
+                    content="thinking",
+                    tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={})],
+                    reasoning_content="hidden reasoning",
+                    thinking_blocks=[{"type": "thinking", "thinking": "step"}],
+                )
+            captured_second_call[:] = messages
+            return LLMResponse(content="done", tool_calls=[])
+        provider.chat_with_retry = scripted_chat_with_retry
+        mgr = SubagentManager(provider=provider, workspace=tmp_path, bus=bus)
+
+        async def fake_execute(self, name, arguments):
+            return "tool result"
+
+        monkeypatch.setattr("nanobot.agent.tools.registry.ToolRegistry.execute", fake_execute)
+
+        await mgr._run_subagent("sub-1", "do task", "label", {"channel": "test", "chat_id": "c1"})
+
+        assistant_messages = [
+            msg for msg in captured_second_call
+            if msg.get("role") == "assistant" and msg.get("tool_calls")
+        ]
+        assert len(assistant_messages) == 1
+        assert assistant_messages[0]["reasoning_content"] == "hidden reasoning"
+        assert assistant_messages[0]["thinking_blocks"] == [{"type": "thinking", "thinking": "step"}]