Merge remote-tracking branch 'origin/main' into pr-2722

tests/agent/test_consolidate_offset.py

@@ -506,7 +506,7 @@ class TestNewCommandArchival:
 
     @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."""
+        """/new clears session immediately; archive is fire-and-forget."""
         from nanobot.bus.events import InboundMessage
 
         loop = self._make_loop(tmp_path)
@@ -518,12 +518,12 @@ class TestNewCommandArchival:
 
         call_count = 0
 
-        async def _failing_consolidate(_messages) -> bool:
+        async def _failing_summarize(_messages) -> bool:
             nonlocal call_count
             call_count += 1
             return False
 
-        loop.memory_consolidator.consolidate_messages = _failing_consolidate  # type: ignore[method-assign]
+        loop.consolidator.archive = _failing_summarize  # type: ignore[method-assign]
 
         new_msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="/new")
         response = await loop._process_message(new_msg)
@@ -535,7 +535,7 @@ class TestNewCommandArchival:
         assert len(session_after.messages) == 0
 
         await loop.close_mcp()
-        assert call_count == 3  # retried up to raw-archive threshold
+        assert call_count == 1
 
     @pytest.mark.asyncio
     async def test_new_archives_only_unconsolidated_messages(self, tmp_path: Path) -> None:
@@ -551,12 +551,12 @@ class TestNewCommandArchival:
 
         archived_count = -1
 
-        async def _fake_consolidate(messages) -> bool:
+        async def _fake_summarize(messages) -> bool:
             nonlocal archived_count
             archived_count = len(messages)
             return True
 
-        loop.memory_consolidator.consolidate_messages = _fake_consolidate  # type: ignore[method-assign]
+        loop.consolidator.archive = _fake_summarize  # type: ignore[method-assign]
 
         new_msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="/new")
         response = await loop._process_message(new_msg)
@@ -578,10 +578,10 @@ class TestNewCommandArchival:
             session.add_message("assistant", f"resp{i}")
         loop.sessions.save(session)
 
-        async def _ok_consolidate(_messages) -> bool:
+        async def _ok_summarize(_messages) -> bool:
             return True
 
-        loop.memory_consolidator.consolidate_messages = _ok_consolidate  # type: ignore[method-assign]
+        loop.consolidator.archive = _ok_summarize  # type: ignore[method-assign]
 
         new_msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="/new")
         response = await loop._process_message(new_msg)
@@ -604,12 +604,12 @@ class TestNewCommandArchival:
 
         archived = asyncio.Event()
 
-        async def _slow_consolidate(_messages) -> bool:
+        async def _slow_summarize(_messages) -> bool:
             await asyncio.sleep(0.1)
             archived.set()
             return True
 
-        loop.memory_consolidator.consolidate_messages = _slow_consolidate  # type: ignore[method-assign]
+        loop.consolidator.archive = _slow_summarize  # type: ignore[method-assign]
 
         new_msg = InboundMessage(channel="cli", sender_id="user", chat_id="test", content="/new")
         await loop._process_message(new_msg)

tests/agent/test_consolidator.py

@@ -0,0 +1,78 @@
+"""Tests for the lightweight Consolidator — append-only to HISTORY.md."""
+
+import pytest
+import asyncio
+from unittest.mock import AsyncMock, MagicMock, patch
+
+from nanobot.agent.memory import Consolidator, MemoryStore
+
+
+@pytest.fixture
+def store(tmp_path):
+    return MemoryStore(tmp_path)
+
+
+@pytest.fixture
+def mock_provider():
+    p = MagicMock()
+    p.chat_with_retry = AsyncMock()
+    return p
+
+
+@pytest.fixture
+def consolidator(store, mock_provider):
+    sessions = MagicMock()
+    sessions.save = MagicMock()
+    return Consolidator(
+        store=store,
+        provider=mock_provider,
+        model="test-model",
+        sessions=sessions,
+        context_window_tokens=1000,
+        build_messages=MagicMock(return_value=[]),
+        get_tool_definitions=MagicMock(return_value=[]),
+        max_completion_tokens=100,
+    )
+
+
+class TestConsolidatorSummarize:
+    async def test_summarize_appends_to_history(self, consolidator, mock_provider, store):
+        """Consolidator should call LLM to summarize, then append to HISTORY.md."""
+        mock_provider.chat_with_retry.return_value = MagicMock(
+            content="User fixed a bug in the auth module."
+        )
+        messages = [
+            {"role": "user", "content": "fix the auth bug"},
+            {"role": "assistant", "content": "Done, fixed the race condition."},
+        ]
+        result = await consolidator.archive(messages)
+        assert result is True
+        entries = store.read_unprocessed_history(since_cursor=0)
+        assert len(entries) == 1
+
+    async def test_summarize_raw_dumps_on_llm_failure(self, consolidator, mock_provider, store):
+        """On LLM failure, raw-dump messages to HISTORY.md."""
+        mock_provider.chat_with_retry.side_effect = Exception("API error")
+        messages = [{"role": "user", "content": "hello"}]
+        result = await consolidator.archive(messages)
+        assert result is True  # always succeeds
+        entries = store.read_unprocessed_history(since_cursor=0)
+        assert len(entries) == 1
+        assert "[RAW]" in entries[0]["content"]
+
+    async def test_summarize_skips_empty_messages(self, consolidator):
+        result = await consolidator.archive([])
+        assert result is False
+
+
+class TestConsolidatorTokenBudget:
+    async def test_prompt_below_threshold_does_not_consolidate(self, consolidator):
+        """No consolidation when tokens are within budget."""
+        session = MagicMock()
+        session.last_consolidated = 0
+        session.messages = [{"role": "user", "content": "hi"}]
+        session.key = "test:key"
+        consolidator.estimate_session_prompt_tokens = MagicMock(return_value=(100, "tiktoken"))
+        consolidator.archive = AsyncMock(return_value=True)
+        await consolidator.maybe_consolidate_by_tokens(session)
+        consolidator.archive.assert_not_called()

tests/agent/test_context_prompt_cache.py

@@ -47,6 +47,19 @@ def test_system_prompt_stays_stable_when_clock_changes(tmp_path, monkeypatch) ->
     assert prompt1 == prompt2
 
 
+def test_system_prompt_reflects_current_dream_memory_contract(tmp_path) -> None:
+    workspace = _make_workspace(tmp_path)
+    builder = ContextBuilder(workspace)
+
+    prompt = builder.build_system_prompt()
+
+    assert "memory/history.jsonl" in prompt
+    assert "automatically managed by Dream" in prompt
+    assert "do not edit directly" in prompt
+    assert "memory/HISTORY.md" not in prompt
+    assert "write important facts here" not in prompt
+
+
 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)
@@ -71,3 +84,19 @@ def test_runtime_context_is_separate_untrusted_user_message(tmp_path) -> None:
     assert "Channel: cli" in user_content
     assert "Chat ID: direct" in user_content
     assert "Return exactly: OK" in user_content
+
+
+def test_subagent_result_does_not_create_consecutive_assistant_messages(tmp_path) -> None:
+    workspace = _make_workspace(tmp_path)
+    builder = ContextBuilder(workspace)
+
+    messages = builder.build_messages(
+        history=[{"role": "assistant", "content": "previous result"}],
+        current_message="subagent result",
+        channel="cli",
+        chat_id="direct",
+        current_role="assistant",
+    )
+
+    for left, right in zip(messages, messages[1:]):
+        assert not (left.get("role") == right.get("role") == "assistant")

tests/agent/test_dream.py

@@ -0,0 +1,97 @@
+"""Tests for the Dream class — two-phase memory consolidation via AgentRunner."""
+
+import pytest
+
+from unittest.mock import AsyncMock, MagicMock
+
+from nanobot.agent.memory import Dream, MemoryStore
+from nanobot.agent.runner import AgentRunResult
+
+
+@pytest.fixture
+def store(tmp_path):
+    s = MemoryStore(tmp_path)
+    s.write_soul("# Soul\n- Helpful")
+    s.write_user("# User\n- Developer")
+    s.write_memory("# Memory\n- Project X active")
+    return s
+
+
+@pytest.fixture
+def mock_provider():
+    p = MagicMock()
+    p.chat_with_retry = AsyncMock()
+    return p
+
+
+@pytest.fixture
+def mock_runner():
+    return MagicMock()
+
+
+@pytest.fixture
+def dream(store, mock_provider, mock_runner):
+    d = Dream(store=store, provider=mock_provider, model="test-model", max_batch_size=5)
+    d._runner = mock_runner
+    return d
+
+
+def _make_run_result(
+    stop_reason="completed",
+    final_content=None,
+    tool_events=None,
+    usage=None,
+):
+    return AgentRunResult(
+        final_content=final_content or stop_reason,
+        stop_reason=stop_reason,
+        messages=[],
+        tools_used=[],
+        usage={},
+        tool_events=tool_events or [],
+    )
+
+
+class TestDreamRun:
+    async def test_noop_when_no_unprocessed_history(self, dream, mock_provider, mock_runner, store):
+        """Dream should not call LLM when there's nothing to process."""
+        result = await dream.run()
+        assert result is False
+        mock_provider.chat_with_retry.assert_not_called()
+        mock_runner.run.assert_not_called()
+
+    async def test_calls_runner_for_unprocessed_entries(self, dream, mock_provider, mock_runner, store):
+        """Dream should call AgentRunner when there are unprocessed history entries."""
+        store.append_history("User prefers dark mode")
+        mock_provider.chat_with_retry.return_value = MagicMock(content="New fact")
+        mock_runner.run = AsyncMock(return_value=_make_run_result(
+            tool_events=[{"name": "edit_file", "status": "ok", "detail": "memory/MEMORY.md"}],
+        ))
+        result = await dream.run()
+        assert result is True
+        mock_runner.run.assert_called_once()
+        spec = mock_runner.run.call_args[0][0]
+        assert spec.max_iterations == 10
+        assert spec.fail_on_tool_error is True
+
+    async def test_advances_dream_cursor(self, dream, mock_provider, mock_runner, store):
+        """Dream should advance the cursor after processing."""
+        store.append_history("event 1")
+        store.append_history("event 2")
+        mock_provider.chat_with_retry.return_value = MagicMock(content="Nothing new")
+        mock_runner.run = AsyncMock(return_value=_make_run_result())
+        await dream.run()
+        assert store.get_last_dream_cursor() == 2
+
+    async def test_compacts_processed_history(self, dream, mock_provider, mock_runner, store):
+        """Dream should compact history after processing."""
+        store.append_history("event 1")
+        store.append_history("event 2")
+        store.append_history("event 3")
+        mock_provider.chat_with_retry.return_value = MagicMock(content="Nothing new")
+        mock_runner.run = AsyncMock(return_value=_make_run_result())
+        await dream.run()
+        # After Dream, cursor is advanced and 3, compact keeps last max_history_entries
+        entries = store.read_unprocessed_history(since_cursor=0)
+        assert all(e["cursor"] > 0 for e in entries)
+

tests/agent/test_git_store.py

@@ -0,0 +1,234 @@
+"""Tests for GitStore — git-backed version control for memory files."""
+
+import pytest
+from pathlib import Path
+
+from nanobot.utils.gitstore import GitStore, CommitInfo
+
+
+TRACKED = ["SOUL.md", "USER.md", "memory/MEMORY.md"]
+
+
+@pytest.fixture
+def git(tmp_path):
+    """Uninitialized GitStore."""
+    return GitStore(tmp_path, tracked_files=TRACKED)
+
+
+@pytest.fixture
+def git_ready(git):
+    """Initialized GitStore with one initial commit."""
+    git.init()
+    return git
+
+
+class TestInit:
+    def test_not_initialized_by_default(self, git, tmp_path):
+        assert not git.is_initialized()
+        assert not (tmp_path / ".git").is_dir()
+
+    def test_init_creates_git_dir(self, git, tmp_path):
+        assert git.init()
+        assert (tmp_path / ".git").is_dir()
+
+    def test_init_idempotent(self, git_ready):
+        assert not git_ready.init()
+
+    def test_init_creates_gitignore(self, git_ready):
+        gi = git_ready._workspace / ".gitignore"
+        assert gi.exists()
+        content = gi.read_text(encoding="utf-8")
+        for f in TRACKED:
+            assert f"!{f}" in content
+
+    def test_init_touches_tracked_files(self, git_ready):
+        for f in TRACKED:
+            assert (git_ready._workspace / f).exists()
+
+    def test_init_makes_initial_commit(self, git_ready):
+        commits = git_ready.log()
+        assert len(commits) == 1
+        assert "init" in commits[0].message
+
+
+class TestBuildGitignore:
+    def test_subdirectory_dirs(self, git):
+        content = git._build_gitignore()
+        assert "!memory/\n" in content
+        for f in TRACKED:
+            assert f"!{f}\n" in content
+        assert content.startswith("/*\n")
+
+    def test_root_level_files_no_dir_entries(self, tmp_path):
+        gs = GitStore(tmp_path, tracked_files=["a.md", "b.md"])
+        content = gs._build_gitignore()
+        assert "!a.md\n" in content
+        assert "!b.md\n" in content
+        dir_lines = [l for l in content.split("\n") if l.startswith("!") and l.endswith("/")]
+        assert dir_lines == []
+
+
+class TestAutoCommit:
+    def test_returns_none_when_not_initialized(self, git):
+        assert git.auto_commit("test") is None
+
+    def test_commits_file_change(self, git_ready):
+        (git_ready._workspace / "SOUL.md").write_text("updated", encoding="utf-8")
+        sha = git_ready.auto_commit("update soul")
+        assert sha is not None
+        assert len(sha) == 8
+
+    def test_returns_none_when_no_changes(self, git_ready):
+        assert git_ready.auto_commit("no change") is None
+
+    def test_commit_appears_in_log(self, git_ready):
+        ws = git_ready._workspace
+        (ws / "SOUL.md").write_text("v2", encoding="utf-8")
+        sha = git_ready.auto_commit("update soul")
+        commits = git_ready.log()
+        assert len(commits) == 2
+        assert commits[0].sha == sha
+
+    def test_does_not_create_empty_commits(self, git_ready):
+        git_ready.auto_commit("nothing 1")
+        git_ready.auto_commit("nothing 2")
+        assert len(git_ready.log()) == 1  # only init commit
+
+
+class TestLog:
+    def test_empty_when_not_initialized(self, git):
+        assert git.log() == []
+
+    def test_newest_first(self, git_ready):
+        ws = git_ready._workspace
+        for i in range(3):
+            (ws / "SOUL.md").write_text(f"v{i}", encoding="utf-8")
+            git_ready.auto_commit(f"commit {i}")
+
+        commits = git_ready.log()
+        assert len(commits) == 4  # init + 3
+        assert "commit 2" in commits[0].message
+        assert "init" in commits[-1].message
+
+    def test_max_entries(self, git_ready):
+        ws = git_ready._workspace
+        for i in range(10):
+            (ws / "SOUL.md").write_text(f"v{i}", encoding="utf-8")
+            git_ready.auto_commit(f"c{i}")
+        assert len(git_ready.log(max_entries=3)) == 3
+
+    def test_commit_info_fields(self, git_ready):
+        c = git_ready.log()[0]
+        assert isinstance(c, CommitInfo)
+        assert len(c.sha) == 8
+        assert c.timestamp
+        assert c.message
+
+
+class TestDiffCommits:
+    def test_empty_when_not_initialized(self, git):
+        assert git.diff_commits("a", "b") == ""
+
+    def test_diff_between_two_commits(self, git_ready):
+        ws = git_ready._workspace
+        (ws / "SOUL.md").write_text("original", encoding="utf-8")
+        git_ready.auto_commit("v1")
+        (ws / "SOUL.md").write_text("modified", encoding="utf-8")
+        git_ready.auto_commit("v2")
+
+        commits = git_ready.log()
+        diff = git_ready.diff_commits(commits[1].sha, commits[0].sha)
+        assert "modified" in diff
+
+    def test_invalid_sha_returns_empty(self, git_ready):
+        assert git_ready.diff_commits("deadbeef", "cafebabe") == ""
+
+
+class TestFindCommit:
+    def test_finds_by_prefix(self, git_ready):
+        ws = git_ready._workspace
+        (ws / "SOUL.md").write_text("v2", encoding="utf-8")
+        sha = git_ready.auto_commit("v2")
+        found = git_ready.find_commit(sha[:4])
+        assert found is not None
+        assert found.sha == sha
+
+    def test_returns_none_for_unknown(self, git_ready):
+        assert git_ready.find_commit("deadbeef") is None
+
+
+class TestShowCommitDiff:
+    def test_returns_commit_with_diff(self, git_ready):
+        ws = git_ready._workspace
+        (ws / "SOUL.md").write_text("content", encoding="utf-8")
+        sha = git_ready.auto_commit("add content")
+        result = git_ready.show_commit_diff(sha)
+        assert result is not None
+        commit, diff = result
+        assert commit.sha == sha
+        assert "content" in diff
+
+    def test_first_commit_has_empty_diff(self, git_ready):
+        init_sha = git_ready.log()[-1].sha
+        result = git_ready.show_commit_diff(init_sha)
+        assert result is not None
+        _, diff = result
+        assert diff == ""
+
+    def test_returns_none_for_unknown(self, git_ready):
+        assert git_ready.show_commit_diff("deadbeef") is None
+
+
+class TestCommitInfoFormat:
+    def test_format_with_diff(self):
+        from nanobot.utils.gitstore import CommitInfo
+        c = CommitInfo(sha="abcd1234", message="test commit\nsecond line", timestamp="2026-04-02 12:00")
+        result = c.format(diff="some diff")
+        assert "test commit" in result
+        assert "`abcd1234`" in result
+        assert "some diff" in result
+
+    def test_format_without_diff(self):
+        from nanobot.utils.gitstore import CommitInfo
+        c = CommitInfo(sha="abcd1234", message="test", timestamp="2026-04-02 12:00")
+        result = c.format()
+        assert "(no file changes)" in result
+
+
+class TestRevert:
+    def test_returns_none_when_not_initialized(self, git):
+        assert git.revert("abc") is None
+
+    def test_undoes_commit_changes(self, git_ready):
+        """revert(sha) should undo the given commit by restoring to its parent."""
+        ws = git_ready._workspace
+        (ws / "SOUL.md").write_text("v2 content", encoding="utf-8")
+        git_ready.auto_commit("v2")
+
+        commits = git_ready.log()
+        # commits[0] = v2 (HEAD), commits[1] = init
+        # Revert v2 → restore to init's state (empty SOUL.md)
+        new_sha = git_ready.revert(commits[0].sha)
+        assert new_sha is not None
+        assert (ws / "SOUL.md").read_text(encoding="utf-8") == ""
+
+    def test_root_commit_returns_none(self, git_ready):
+        """Cannot revert the root commit (no parent to restore to)."""
+        commits = git_ready.log()
+        assert len(commits) == 1
+        assert git_ready.revert(commits[0].sha) is None
+
+    def test_invalid_sha_returns_none(self, git_ready):
+        assert git_ready.revert("deadbeef") is None
+
+
+class TestMemoryStoreGitProperty:
+    def test_git_property_exposes_gitstore(self, tmp_path):
+        from nanobot.agent.memory import MemoryStore
+        store = MemoryStore(tmp_path)
+        assert isinstance(store.git, GitStore)
+
+    def test_git_property_is_same_object(self, tmp_path):
+        from nanobot.agent.memory import MemoryStore
+        store = MemoryStore(tmp_path)
+        assert store.git is store._git

tests/agent/test_hook_composite.py

@@ -249,7 +249,8 @@ def _make_loop(tmp_path, hooks=None):
     with patch("nanobot.agent.loop.ContextBuilder"), \
          patch("nanobot.agent.loop.SessionManager"), \
          patch("nanobot.agent.loop.SubagentManager") as mock_sub_mgr, \
-         patch("nanobot.agent.loop.MemoryConsolidator"):
+         patch("nanobot.agent.loop.Consolidator"), \
+         patch("nanobot.agent.loop.Dream"):
         mock_sub_mgr.return_value.cancel_by_session = AsyncMock(return_value=0)
         loop = AgentLoop(
             bus=bus, provider=provider, workspace=tmp_path, hooks=hooks,

tests/agent/test_loop_consolidation_tokens.py

@@ -26,24 +26,24 @@ def _make_loop(tmp_path, *, estimated_tokens: int, context_window_tokens: int) -
         context_window_tokens=context_window_tokens,
     )
     loop.tools.get_definitions = MagicMock(return_value=[])
-    loop.memory_consolidator._SAFETY_BUFFER = 0
+    loop.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]
+    loop.consolidator.archive = 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()
+    loop.consolidator.archive.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]
+    loop.consolidator.archive = 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"},
@@ -55,13 +55,13 @@ async def test_prompt_above_threshold_triggers_consolidation(tmp_path, monkeypat
 
     await loop.process_direct("hello", session_key="cli:test")
 
-    assert loop.memory_consolidator.consolidate_messages.await_count >= 1
+    assert loop.consolidator.archive.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]
+    loop.consolidator.archive = AsyncMock(return_value=True)  # type: ignore[method-assign]
 
     session = loop.sessions.get_or_create("cli:test")
     session.messages = [
@@ -76,9 +76,9 @@ async def test_prompt_above_threshold_archives_until_next_user_boundary(tmp_path
     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)
+    await loop.consolidator.maybe_consolidate_by_tokens(session)
 
-    archived_chunk = loop.memory_consolidator.consolidate_messages.await_args.args[0]
+    archived_chunk = loop.consolidator.archive.await_args.args[0]
     assert [message["content"] for message in archived_chunk] == ["u1", "a1", "u2", "a2"]
     assert session.last_consolidated == 4
 
@@ -87,7 +87,7 @@ async def test_prompt_above_threshold_archives_until_next_user_boundary(tmp_path
 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]
+    loop.consolidator.archive = AsyncMock(return_value=True)  # type: ignore[method-assign]
 
     session = loop.sessions.get_or_create("cli:test")
     session.messages = [
@@ -110,12 +110,12 @@ async def test_consolidation_loops_until_target_met(tmp_path, monkeypatch) -> No
             return (300, "test")
         return (80, "test")
 
-    loop.memory_consolidator.estimate_session_prompt_tokens = mock_estimate  # type: ignore[method-assign]
+    loop.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)
+    await loop.consolidator.maybe_consolidate_by_tokens(session)
 
-    assert loop.memory_consolidator.consolidate_messages.await_count == 2
+    assert loop.consolidator.archive.await_count == 2
     assert session.last_consolidated == 6
 
 
@@ -123,7 +123,7 @@ async def test_consolidation_loops_until_target_met(tmp_path, monkeypatch) -> No
 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]
+    loop.consolidator.archive = AsyncMock(return_value=True)  # type: ignore[method-assign]
 
     session = loop.sessions.get_or_create("cli:test")
     session.messages = [
@@ -147,12 +147,12 @@ async def test_consolidation_continues_below_trigger_until_half_target(tmp_path,
             return (150, "test")
         return (80, "test")
 
-    loop.memory_consolidator.estimate_session_prompt_tokens = mock_estimate  # type: ignore[method-assign]
+    loop.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)
+    await loop.consolidator.maybe_consolidate_by_tokens(session)
 
-    assert loop.memory_consolidator.consolidate_messages.await_count == 2
+    assert loop.consolidator.archive.await_count == 2
     assert session.last_consolidated == 6
 
 
@@ -166,7 +166,7 @@ async def test_preflight_consolidation_before_llm_call(tmp_path, monkeypatch) ->
     async def track_consolidate(messages):
         order.append("consolidate")
         return True
-    loop.memory_consolidator.consolidate_messages = track_consolidate  # type: ignore[method-assign]
+    loop.consolidator.archive = track_consolidate  # type: ignore[method-assign]
 
     async def track_llm(*args, **kwargs):
         order.append("llm")
@@ -187,7 +187,7 @@ async def test_preflight_consolidation_before_llm_call(tmp_path, monkeypatch) ->
     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]
+    loop.consolidator.estimate_session_prompt_tokens = mock_estimate  # type: ignore[method-assign]
 
     await loop.process_direct("hello", session_key="cli:test")
 

tests/agent/test_loop_save_turn.py

@@ -5,7 +5,9 @@ from nanobot.session.manager import Session
 
 def _mk_loop() -> AgentLoop:
     loop = AgentLoop.__new__(AgentLoop)
-    loop._TOOL_RESULT_MAX_CHARS = AgentLoop._TOOL_RESULT_MAX_CHARS
+    from nanobot.config.schema import AgentDefaults
+
+    loop.max_tool_result_chars = AgentDefaults().max_tool_result_chars
     return loop
 
 
@@ -72,3 +74,129 @@ def test_save_turn_keeps_tool_results_under_16k() -> None:
     )
 
     assert session.messages[0]["content"] == content
+
+
+def test_restore_runtime_checkpoint_rehydrates_completed_and_pending_tools() -> None:
+    loop = _mk_loop()
+    session = Session(
+        key="test:checkpoint",
+        metadata={
+            AgentLoop._RUNTIME_CHECKPOINT_KEY: {
+                "assistant_message": {
+                    "role": "assistant",
+                    "content": "working",
+                    "tool_calls": [
+                        {
+                            "id": "call_done",
+                            "type": "function",
+                            "function": {"name": "read_file", "arguments": "{}"},
+                        },
+                        {
+                            "id": "call_pending",
+                            "type": "function",
+                            "function": {"name": "exec", "arguments": "{}"},
+                        },
+                    ],
+                },
+                "completed_tool_results": [
+                    {
+                        "role": "tool",
+                        "tool_call_id": "call_done",
+                        "name": "read_file",
+                        "content": "ok",
+                    }
+                ],
+                "pending_tool_calls": [
+                    {
+                        "id": "call_pending",
+                        "type": "function",
+                        "function": {"name": "exec", "arguments": "{}"},
+                    }
+                ],
+            }
+        },
+    )
+
+    restored = loop._restore_runtime_checkpoint(session)
+
+    assert restored is True
+    assert session.metadata.get(AgentLoop._RUNTIME_CHECKPOINT_KEY) is None
+    assert session.messages[0]["role"] == "assistant"
+    assert session.messages[1]["tool_call_id"] == "call_done"
+    assert session.messages[2]["tool_call_id"] == "call_pending"
+    assert "interrupted before this tool finished" in session.messages[2]["content"].lower()
+
+
+def test_restore_runtime_checkpoint_dedupes_overlapping_tail() -> None:
+    loop = _mk_loop()
+    session = Session(
+        key="test:checkpoint-overlap",
+        messages=[
+            {
+                "role": "assistant",
+                "content": "working",
+                "tool_calls": [
+                    {
+                        "id": "call_done",
+                        "type": "function",
+                        "function": {"name": "read_file", "arguments": "{}"},
+                    },
+                    {
+                        "id": "call_pending",
+                        "type": "function",
+                        "function": {"name": "exec", "arguments": "{}"},
+                    },
+                ],
+            },
+            {
+                "role": "tool",
+                "tool_call_id": "call_done",
+                "name": "read_file",
+                "content": "ok",
+            },
+        ],
+        metadata={
+            AgentLoop._RUNTIME_CHECKPOINT_KEY: {
+                "assistant_message": {
+                    "role": "assistant",
+                    "content": "working",
+                    "tool_calls": [
+                        {
+                            "id": "call_done",
+                            "type": "function",
+                            "function": {"name": "read_file", "arguments": "{}"},
+                        },
+                        {
+                            "id": "call_pending",
+                            "type": "function",
+                            "function": {"name": "exec", "arguments": "{}"},
+                        },
+                    ],
+                },
+                "completed_tool_results": [
+                    {
+                        "role": "tool",
+                        "tool_call_id": "call_done",
+                        "name": "read_file",
+                        "content": "ok",
+                    }
+                ],
+                "pending_tool_calls": [
+                    {
+                        "id": "call_pending",
+                        "type": "function",
+                        "function": {"name": "exec", "arguments": "{}"},
+                    }
+                ],
+            }
+        },
+    )
+
+    restored = loop._restore_runtime_checkpoint(session)
+
+    assert restored is True
+    assert session.metadata.get(AgentLoop._RUNTIME_CHECKPOINT_KEY) is None
+    assert len(session.messages) == 3
+    assert session.messages[0]["role"] == "assistant"
+    assert session.messages[1]["tool_call_id"] == "call_done"
+    assert session.messages[2]["tool_call_id"] == "call_pending"

tests/agent/test_memory_consolidation_types.py

@@ -1,478 +0,0 @@
-"""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: 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_memory_store.py

@@ -0,0 +1,267 @@
+"""Tests for the restructured MemoryStore — pure file I/O layer."""
+
+from datetime import datetime
+import json
+from pathlib import Path
+
+import pytest
+
+from nanobot.agent.memory import MemoryStore
+
+
+@pytest.fixture
+def store(tmp_path):
+    return MemoryStore(tmp_path)
+
+
+class TestMemoryStoreBasicIO:
+    def test_read_memory_returns_empty_when_missing(self, store):
+        assert store.read_memory() == ""
+
+    def test_write_and_read_memory(self, store):
+        store.write_memory("hello")
+        assert store.read_memory() == "hello"
+
+    def test_read_soul_returns_empty_when_missing(self, store):
+        assert store.read_soul() == ""
+
+    def test_write_and_read_soul(self, store):
+        store.write_soul("soul content")
+        assert store.read_soul() == "soul content"
+
+    def test_read_user_returns_empty_when_missing(self, store):
+        assert store.read_user() == ""
+
+    def test_write_and_read_user(self, store):
+        store.write_user("user content")
+        assert store.read_user() == "user content"
+
+    def test_get_memory_context_returns_empty_when_missing(self, store):
+        assert store.get_memory_context() == ""
+
+    def test_get_memory_context_returns_formatted_content(self, store):
+        store.write_memory("important fact")
+        ctx = store.get_memory_context()
+        assert "Long-term Memory" in ctx
+        assert "important fact" in ctx
+
+
+class TestHistoryWithCursor:
+    def test_append_history_returns_cursor(self, store):
+        cursor = store.append_history("event 1")
+        assert cursor == 1
+        cursor2 = store.append_history("event 2")
+        assert cursor2 == 2
+
+    def test_append_history_includes_cursor_in_file(self, store):
+        store.append_history("event 1")
+        content = store.read_file(store.history_file)
+        data = json.loads(content)
+        assert data["cursor"] == 1
+
+    def test_cursor_persists_across_appends(self, store):
+        store.append_history("event 1")
+        store.append_history("event 2")
+        cursor = store.append_history("event 3")
+        assert cursor == 3
+
+    def test_read_unprocessed_history(self, store):
+        store.append_history("event 1")
+        store.append_history("event 2")
+        store.append_history("event 3")
+        entries = store.read_unprocessed_history(since_cursor=1)
+        assert len(entries) == 2
+        assert entries[0]["cursor"] == 2
+
+    def test_read_unprocessed_history_returns_all_when_cursor_zero(self, store):
+        store.append_history("event 1")
+        store.append_history("event 2")
+        entries = store.read_unprocessed_history(since_cursor=0)
+        assert len(entries) == 2
+
+    def test_compact_history_drops_oldest(self, tmp_path):
+        store = MemoryStore(tmp_path, max_history_entries=2)
+        store.append_history("event 1")
+        store.append_history("event 2")
+        store.append_history("event 3")
+        store.append_history("event 4")
+        store.append_history("event 5")
+        store.compact_history()
+        entries = store.read_unprocessed_history(since_cursor=0)
+        assert len(entries) == 2
+        assert entries[0]["cursor"] in {4, 5}
+
+
+class TestDreamCursor:
+    def test_initial_cursor_is_zero(self, store):
+        assert store.get_last_dream_cursor() == 0
+
+    def test_set_and_get_cursor(self, store):
+        store.set_last_dream_cursor(5)
+        assert store.get_last_dream_cursor() == 5
+
+    def test_cursor_persists(self, store):
+        store.set_last_dream_cursor(3)
+        store2 = MemoryStore(store.workspace)
+        assert store2.get_last_dream_cursor() == 3
+
+
+class TestLegacyHistoryMigration:
+    def test_read_unprocessed_history_handles_entries_without_cursor(self, store):
+        """JSONL entries with cursor=1 are correctly parsed and returned."""
+        store.history_file.write_text(
+            '{"cursor": 1, "timestamp": "2026-03-30 14:30", "content": "Old event"}\n',
+            encoding="utf-8")
+        entries = store.read_unprocessed_history(since_cursor=0)
+        assert len(entries) == 1
+        assert entries[0]["cursor"] == 1
+
+    def test_migrates_legacy_history_md_preserving_partial_entries(self, tmp_path):
+        memory_dir = tmp_path / "memory"
+        memory_dir.mkdir()
+        legacy_file = memory_dir / "HISTORY.md"
+        legacy_content = (
+            "[2026-04-01 10:00] User prefers dark mode.\n\n"
+            "[2026-04-01 10:05] [RAW] 2 messages\n"
+            "[2026-04-01 10:04] USER: hello\n"
+            "[2026-04-01 10:04] ASSISTANT: hi\n\n"
+            "Legacy chunk without timestamp.\n"
+            "Keep whatever content we can recover.\n"
+        )
+        legacy_file.write_text(legacy_content, encoding="utf-8")
+
+        store = MemoryStore(tmp_path)
+        fallback_timestamp = datetime.fromtimestamp(
+            (memory_dir / "HISTORY.md.bak").stat().st_mtime,
+        ).strftime("%Y-%m-%d %H:%M")
+
+        entries = store.read_unprocessed_history(since_cursor=0)
+        assert [entry["cursor"] for entry in entries] == [1, 2, 3]
+        assert entries[0]["timestamp"] == "2026-04-01 10:00"
+        assert entries[0]["content"] == "User prefers dark mode."
+        assert entries[1]["timestamp"] == "2026-04-01 10:05"
+        assert entries[1]["content"].startswith("[RAW] 2 messages")
+        assert "USER: hello" in entries[1]["content"]
+        assert entries[2]["timestamp"] == fallback_timestamp
+        assert entries[2]["content"].startswith("Legacy chunk without timestamp.")
+        assert store.read_file(store._cursor_file).strip() == "3"
+        assert store.read_file(store._dream_cursor_file).strip() == "3"
+        assert not legacy_file.exists()
+        assert (memory_dir / "HISTORY.md.bak").read_text(encoding="utf-8") == legacy_content
+
+    def test_migrates_consecutive_entries_without_blank_lines(self, tmp_path):
+        memory_dir = tmp_path / "memory"
+        memory_dir.mkdir()
+        legacy_file = memory_dir / "HISTORY.md"
+        legacy_content = (
+            "[2026-04-01 10:00] First event.\n"
+            "[2026-04-01 10:01] Second event.\n"
+            "[2026-04-01 10:02] Third event.\n"
+        )
+        legacy_file.write_text(legacy_content, encoding="utf-8")
+
+        store = MemoryStore(tmp_path)
+
+        entries = store.read_unprocessed_history(since_cursor=0)
+        assert len(entries) == 3
+        assert [entry["content"] for entry in entries] == [
+            "First event.",
+            "Second event.",
+            "Third event.",
+        ]
+
+    def test_raw_archive_stays_single_entry_while_following_events_split(self, tmp_path):
+        memory_dir = tmp_path / "memory"
+        memory_dir.mkdir()
+        legacy_file = memory_dir / "HISTORY.md"
+        legacy_content = (
+            "[2026-04-01 10:05] [RAW] 2 messages\n"
+            "[2026-04-01 10:04] USER: hello\n"
+            "[2026-04-01 10:04] ASSISTANT: hi\n"
+            "[2026-04-01 10:06] Normal event after raw block.\n"
+        )
+        legacy_file.write_text(legacy_content, encoding="utf-8")
+
+        store = MemoryStore(tmp_path)
+
+        entries = store.read_unprocessed_history(since_cursor=0)
+        assert len(entries) == 2
+        assert entries[0]["content"].startswith("[RAW] 2 messages")
+        assert "USER: hello" in entries[0]["content"]
+        assert entries[1]["content"] == "Normal event after raw block."
+
+    def test_nonstandard_date_headers_still_start_new_entries(self, tmp_path):
+        memory_dir = tmp_path / "memory"
+        memory_dir.mkdir()
+        legacy_file = memory_dir / "HISTORY.md"
+        legacy_content = (
+            "[2026-03-25–2026-04-02] Multi-day summary.\n"
+            "[2026-03-26/27] Cross-day summary.\n"
+        )
+        legacy_file.write_text(legacy_content, encoding="utf-8")
+
+        store = MemoryStore(tmp_path)
+        fallback_timestamp = datetime.fromtimestamp(
+            (memory_dir / "HISTORY.md.bak").stat().st_mtime,
+        ).strftime("%Y-%m-%d %H:%M")
+
+        entries = store.read_unprocessed_history(since_cursor=0)
+        assert len(entries) == 2
+        assert entries[0]["timestamp"] == fallback_timestamp
+        assert entries[0]["content"] == "[2026-03-25–2026-04-02] Multi-day summary."
+        assert entries[1]["timestamp"] == fallback_timestamp
+        assert entries[1]["content"] == "[2026-03-26/27] Cross-day summary."
+
+    def test_existing_history_jsonl_skips_legacy_migration(self, tmp_path):
+        memory_dir = tmp_path / "memory"
+        memory_dir.mkdir()
+        history_file = memory_dir / "history.jsonl"
+        history_file.write_text(
+            '{"cursor": 7, "timestamp": "2026-04-01 12:00", "content": "existing"}\n',
+            encoding="utf-8",
+        )
+        legacy_file = memory_dir / "HISTORY.md"
+        legacy_file.write_text("[2026-04-01 10:00] legacy\n\n", encoding="utf-8")
+
+        store = MemoryStore(tmp_path)
+
+        entries = store.read_unprocessed_history(since_cursor=0)
+        assert len(entries) == 1
+        assert entries[0]["cursor"] == 7
+        assert entries[0]["content"] == "existing"
+        assert legacy_file.exists()
+        assert not (memory_dir / "HISTORY.md.bak").exists()
+
+    def test_empty_history_jsonl_still_allows_legacy_migration(self, tmp_path):
+        memory_dir = tmp_path / "memory"
+        memory_dir.mkdir()
+        history_file = memory_dir / "history.jsonl"
+        history_file.write_text("", encoding="utf-8")
+        legacy_file = memory_dir / "HISTORY.md"
+        legacy_file.write_text("[2026-04-01 10:00] legacy\n\n", encoding="utf-8")
+
+        store = MemoryStore(tmp_path)
+
+        entries = store.read_unprocessed_history(since_cursor=0)
+        assert len(entries) == 1
+        assert entries[0]["cursor"] == 1
+        assert entries[0]["timestamp"] == "2026-04-01 10:00"
+        assert entries[0]["content"] == "legacy"
+        assert not legacy_file.exists()
+        assert (memory_dir / "HISTORY.md.bak").exists()
+
+    def test_migrates_legacy_history_with_invalid_utf8_bytes(self, tmp_path):
+        memory_dir = tmp_path / "memory"
+        memory_dir.mkdir()
+        legacy_file = memory_dir / "HISTORY.md"
+        legacy_file.write_bytes(
+            b"[2026-04-01 10:00] Broken \xff data still needs migration.\n\n"
+        )
+
+        store = MemoryStore(tmp_path)
+
+        entries = store.read_unprocessed_history(since_cursor=0)
+        assert len(entries) == 1
+        assert entries[0]["timestamp"] == "2026-04-01 10:00"
+        assert "Broken" in entries[0]["content"]
+        assert "migration." in entries[0]["content"]

tests/agent/test_runner.py

@@ -2,12 +2,20 @@
 
 from __future__ import annotations
 
+import asyncio
+import os
+import time
 from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
+from nanobot.config.schema import AgentDefaults
+from nanobot.agent.tools.base import Tool
+from nanobot.agent.tools.registry import ToolRegistry
 from nanobot.providers.base import LLMResponse, ToolCallRequest
 
+_MAX_TOOL_RESULT_CHARS = AgentDefaults().max_tool_result_chars
+
 
 def _make_loop(tmp_path):
     from nanobot.agent.loop import AgentLoop
@@ -60,6 +68,7 @@ async def test_runner_preserves_reasoning_fields_and_tool_results():
         tools=tools,
         model="test-model",
         max_iterations=3,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
     ))
 
     assert result.final_content == "done"
@@ -135,6 +144,7 @@ async def test_runner_calls_hooks_in_order():
         tools=tools,
         model="test-model",
         max_iterations=3,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
         hook=RecordingHook(),
     ))
 
@@ -191,6 +201,7 @@ async def test_runner_streaming_hook_receives_deltas_and_end_signal():
         tools=tools,
         model="test-model",
         max_iterations=1,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
         hook=StreamingHook(),
     ))
 
@@ -219,6 +230,7 @@ async def test_runner_returns_max_iterations_fallback():
         tools=tools,
         model="test-model",
         max_iterations=2,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
     ))
 
     assert result.stop_reason == "max_iterations"
@@ -226,7 +238,8 @@ async def test_runner_returns_max_iterations_fallback():
         "I reached the maximum number of tool call iterations (2) "
         "without completing the task. You can try breaking the task into smaller steps."
     )
-
+    assert result.messages[-1]["role"] == "assistant"
+    assert result.messages[-1]["content"] == result.final_content
 
 @pytest.mark.asyncio
 async def test_runner_returns_structured_tool_error():
@@ -248,6 +261,7 @@ async def test_runner_returns_structured_tool_error():
         tools=tools,
         model="test-model",
         max_iterations=2,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
         fail_on_tool_error=True,
     ))
 
@@ -258,6 +272,457 @@ async def test_runner_returns_structured_tool_error():
     ]
 
 
+@pytest.mark.asyncio
+async def test_runner_persists_large_tool_results_for_follow_up_calls(tmp_path):
+    from nanobot.agent.runner import AgentRunSpec, AgentRunner
+
+    provider = MagicMock()
+    captured_second_call: list[dict] = []
+    call_count = {"n": 0}
+
+    async def chat_with_retry(*, messages, **kwargs):
+        call_count["n"] += 1
+        if call_count["n"] == 1:
+            return LLMResponse(
+                content="working",
+                tool_calls=[ToolCallRequest(id="call_big", name="list_dir", arguments={"path": "."})],
+                usage={"prompt_tokens": 5, "completion_tokens": 3},
+            )
+        captured_second_call[:] = messages
+        return LLMResponse(content="done", tool_calls=[], usage={})
+
+    provider.chat_with_retry = chat_with_retry
+    tools = MagicMock()
+    tools.get_definitions.return_value = []
+    tools.execute = AsyncMock(return_value="x" * 20_000)
+
+    runner = AgentRunner(provider)
+    result = await runner.run(AgentRunSpec(
+        initial_messages=[{"role": "user", "content": "do task"}],
+        tools=tools,
+        model="test-model",
+        max_iterations=2,
+        workspace=tmp_path,
+        session_key="test:runner",
+        max_tool_result_chars=2048,
+    ))
+
+    assert result.final_content == "done"
+    tool_message = next(msg for msg in captured_second_call if msg.get("role") == "tool")
+    assert "[tool output persisted]" in tool_message["content"]
+    assert "tool-results" in tool_message["content"]
+    assert (tmp_path / ".nanobot" / "tool-results" / "test_runner" / "call_big.txt").exists()
+
+
+def test_persist_tool_result_prunes_old_session_buckets(tmp_path):
+    from nanobot.utils.helpers import maybe_persist_tool_result
+
+    root = tmp_path / ".nanobot" / "tool-results"
+    old_bucket = root / "old_session"
+    recent_bucket = root / "recent_session"
+    old_bucket.mkdir(parents=True)
+    recent_bucket.mkdir(parents=True)
+    (old_bucket / "old.txt").write_text("old", encoding="utf-8")
+    (recent_bucket / "recent.txt").write_text("recent", encoding="utf-8")
+
+    stale = time.time() - (8 * 24 * 60 * 60)
+    os.utime(old_bucket, (stale, stale))
+    os.utime(old_bucket / "old.txt", (stale, stale))
+
+    persisted = maybe_persist_tool_result(
+        tmp_path,
+        "current:session",
+        "call_big",
+        "x" * 5000,
+        max_chars=64,
+    )
+
+    assert "[tool output persisted]" in persisted
+    assert not old_bucket.exists()
+    assert recent_bucket.exists()
+    assert (root / "current_session" / "call_big.txt").exists()
+
+
+def test_persist_tool_result_leaves_no_temp_files(tmp_path):
+    from nanobot.utils.helpers import maybe_persist_tool_result
+
+    root = tmp_path / ".nanobot" / "tool-results"
+    maybe_persist_tool_result(
+        tmp_path,
+        "current:session",
+        "call_big",
+        "x" * 5000,
+        max_chars=64,
+    )
+
+    assert (root / "current_session" / "call_big.txt").exists()
+    assert list((root / "current_session").glob("*.tmp")) == []
+
+
+def test_persist_tool_result_logs_cleanup_failures(monkeypatch, tmp_path):
+    from nanobot.utils.helpers import maybe_persist_tool_result
+
+    warnings: list[str] = []
+
+    monkeypatch.setattr(
+        "nanobot.utils.helpers._cleanup_tool_result_buckets",
+        lambda *_args, **_kwargs: (_ for _ in ()).throw(OSError("busy")),
+    )
+    monkeypatch.setattr(
+        "nanobot.utils.helpers.logger.warning",
+        lambda message, *args: warnings.append(message.format(*args)),
+    )
+
+    persisted = maybe_persist_tool_result(
+        tmp_path,
+        "current:session",
+        "call_big",
+        "x" * 5000,
+        max_chars=64,
+    )
+
+    assert "[tool output persisted]" in persisted
+    assert warnings and "Failed to clean stale tool result buckets" in warnings[0]
+
+
+@pytest.mark.asyncio
+async def test_runner_replaces_empty_tool_result_with_marker():
+    from nanobot.agent.runner import AgentRunSpec, AgentRunner
+
+    provider = MagicMock()
+    captured_second_call: list[dict] = []
+    call_count = {"n": 0}
+
+    async def chat_with_retry(*, messages, **kwargs):
+        call_count["n"] += 1
+        if call_count["n"] == 1:
+            return LLMResponse(
+                content="working",
+                tool_calls=[ToolCallRequest(id="call_1", name="noop", arguments={})],
+                usage={},
+            )
+        captured_second_call[:] = messages
+        return LLMResponse(content="done", tool_calls=[], usage={})
+
+    provider.chat_with_retry = chat_with_retry
+    tools = MagicMock()
+    tools.get_definitions.return_value = []
+    tools.execute = AsyncMock(return_value="")
+
+    runner = AgentRunner(provider)
+    result = await runner.run(AgentRunSpec(
+        initial_messages=[{"role": "user", "content": "do task"}],
+        tools=tools,
+        model="test-model",
+        max_iterations=2,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+    ))
+
+    assert result.final_content == "done"
+    tool_message = next(msg for msg in captured_second_call if msg.get("role") == "tool")
+    assert tool_message["content"] == "(noop completed with no output)"
+
+
+@pytest.mark.asyncio
+async def test_runner_uses_raw_messages_when_context_governance_fails():
+    from nanobot.agent.runner import AgentRunSpec, AgentRunner
+
+    provider = MagicMock()
+    captured_messages: list[dict] = []
+
+    async def chat_with_retry(*, messages, **kwargs):
+        captured_messages[:] = messages
+        return LLMResponse(content="done", tool_calls=[], usage={})
+
+    provider.chat_with_retry = chat_with_retry
+    tools = MagicMock()
+    tools.get_definitions.return_value = []
+    initial_messages = [
+        {"role": "system", "content": "system"},
+        {"role": "user", "content": "hello"},
+    ]
+
+    runner = AgentRunner(provider)
+    runner._snip_history = MagicMock(side_effect=RuntimeError("boom"))  # type: ignore[method-assign]
+    result = await runner.run(AgentRunSpec(
+        initial_messages=initial_messages,
+        tools=tools,
+        model="test-model",
+        max_iterations=1,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+    ))
+
+    assert result.final_content == "done"
+    assert captured_messages == initial_messages
+
+
+@pytest.mark.asyncio
+async def test_runner_retries_empty_final_response_with_summary_prompt():
+    from nanobot.agent.runner import AgentRunSpec, AgentRunner
+
+    provider = MagicMock()
+    calls: list[dict] = []
+
+    async def chat_with_retry(*, messages, tools=None, **kwargs):
+        calls.append({"messages": messages, "tools": tools})
+        if len(calls) == 1:
+            return LLMResponse(
+                content=None,
+                tool_calls=[],
+                usage={"prompt_tokens": 10, "completion_tokens": 1},
+            )
+        return LLMResponse(
+            content="final answer",
+            tool_calls=[],
+            usage={"prompt_tokens": 3, "completion_tokens": 7},
+        )
+
+    provider.chat_with_retry = chat_with_retry
+    tools = MagicMock()
+    tools.get_definitions.return_value = []
+
+    runner = AgentRunner(provider)
+    result = await runner.run(AgentRunSpec(
+        initial_messages=[{"role": "user", "content": "do task"}],
+        tools=tools,
+        model="test-model",
+        max_iterations=1,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+    ))
+
+    assert result.final_content == "final answer"
+    assert len(calls) == 2
+    assert calls[1]["tools"] is None
+    assert "Do not call any more tools" in calls[1]["messages"][-1]["content"]
+    assert result.usage["prompt_tokens"] == 13
+    assert result.usage["completion_tokens"] == 8
+
+
+@pytest.mark.asyncio
+async def test_runner_uses_specific_message_after_empty_finalization_retry():
+    from nanobot.agent.runner import AgentRunSpec, AgentRunner
+    from nanobot.utils.runtime import EMPTY_FINAL_RESPONSE_MESSAGE
+
+    provider = MagicMock()
+
+    async def chat_with_retry(*, messages, **kwargs):
+        return LLMResponse(content=None, tool_calls=[], usage={})
+
+    provider.chat_with_retry = chat_with_retry
+    tools = MagicMock()
+    tools.get_definitions.return_value = []
+
+    runner = AgentRunner(provider)
+    result = await runner.run(AgentRunSpec(
+        initial_messages=[{"role": "user", "content": "do task"}],
+        tools=tools,
+        model="test-model",
+        max_iterations=1,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+    ))
+
+    assert result.final_content == EMPTY_FINAL_RESPONSE_MESSAGE
+    assert result.stop_reason == "empty_final_response"
+
+
+def test_snip_history_drops_orphaned_tool_results_from_trimmed_slice(monkeypatch):
+    from nanobot.agent.runner import AgentRunSpec, AgentRunner
+
+    provider = MagicMock()
+    tools = MagicMock()
+    tools.get_definitions.return_value = []
+    runner = AgentRunner(provider)
+    messages = [
+        {"role": "system", "content": "system"},
+        {"role": "user", "content": "old user"},
+        {
+            "role": "assistant",
+            "content": "tool call",
+            "tool_calls": [{"id": "call_1", "type": "function", "function": {"name": "ls", "arguments": "{}"}}],
+        },
+        {"role": "tool", "tool_call_id": "call_1", "content": "tool output"},
+        {"role": "assistant", "content": "after tool"},
+    ]
+    spec = AgentRunSpec(
+        initial_messages=messages,
+        tools=tools,
+        model="test-model",
+        max_iterations=1,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+        context_window_tokens=2000,
+        context_block_limit=100,
+    )
+
+    monkeypatch.setattr("nanobot.agent.runner.estimate_prompt_tokens_chain", lambda *_args, **_kwargs: (500, None))
+    token_sizes = {
+        "old user": 120,
+        "tool call": 120,
+        "tool output": 40,
+        "after tool": 40,
+        "system": 0,
+    }
+    monkeypatch.setattr(
+        "nanobot.agent.runner.estimate_message_tokens",
+        lambda msg: token_sizes.get(str(msg.get("content")), 40),
+    )
+
+    trimmed = runner._snip_history(spec, messages)
+
+    assert trimmed == [
+        {"role": "system", "content": "system"},
+        {"role": "assistant", "content": "after tool"},
+    ]
+
+
+@pytest.mark.asyncio
+async def test_runner_keeps_going_when_tool_result_persistence_fails():
+    from nanobot.agent.runner import AgentRunSpec, AgentRunner
+
+    provider = MagicMock()
+    captured_second_call: list[dict] = []
+    call_count = {"n": 0}
+
+    async def chat_with_retry(*, messages, **kwargs):
+        call_count["n"] += 1
+        if call_count["n"] == 1:
+            return LLMResponse(
+                content="working",
+                tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={"path": "."})],
+                usage={"prompt_tokens": 5, "completion_tokens": 3},
+            )
+        captured_second_call[:] = messages
+        return LLMResponse(content="done", tool_calls=[], usage={})
+
+    provider.chat_with_retry = chat_with_retry
+    tools = MagicMock()
+    tools.get_definitions.return_value = []
+    tools.execute = AsyncMock(return_value="tool result")
+
+    runner = AgentRunner(provider)
+    with patch("nanobot.agent.runner.maybe_persist_tool_result", side_effect=RuntimeError("disk full")):
+        result = await runner.run(AgentRunSpec(
+            initial_messages=[{"role": "user", "content": "do task"}],
+            tools=tools,
+            model="test-model",
+            max_iterations=2,
+            max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+        ))
+
+    assert result.final_content == "done"
+    tool_message = next(msg for msg in captured_second_call if msg.get("role") == "tool")
+    assert tool_message["content"] == "tool result"
+
+
+class _DelayTool(Tool):
+    def __init__(self, name: str, *, delay: float, read_only: bool, shared_events: list[str]):
+        self._name = name
+        self._delay = delay
+        self._read_only = read_only
+        self._shared_events = shared_events
+
+    @property
+    def name(self) -> str:
+        return self._name
+
+    @property
+    def description(self) -> str:
+        return self._name
+
+    @property
+    def parameters(self) -> dict:
+        return {"type": "object", "properties": {}, "required": []}
+
+    @property
+    def read_only(self) -> bool:
+        return self._read_only
+
+    async def execute(self, **kwargs):
+        self._shared_events.append(f"start:{self._name}")
+        await asyncio.sleep(self._delay)
+        self._shared_events.append(f"end:{self._name}")
+        return self._name
+
+
+@pytest.mark.asyncio
+async def test_runner_batches_read_only_tools_before_exclusive_work():
+    from nanobot.agent.runner import AgentRunSpec, AgentRunner
+
+    tools = ToolRegistry()
+    shared_events: list[str] = []
+    read_a = _DelayTool("read_a", delay=0.05, read_only=True, shared_events=shared_events)
+    read_b = _DelayTool("read_b", delay=0.05, read_only=True, shared_events=shared_events)
+    write_a = _DelayTool("write_a", delay=0.01, read_only=False, shared_events=shared_events)
+    tools.register(read_a)
+    tools.register(read_b)
+    tools.register(write_a)
+
+    runner = AgentRunner(MagicMock())
+    await runner._execute_tools(
+        AgentRunSpec(
+            initial_messages=[],
+            tools=tools,
+            model="test-model",
+            max_iterations=1,
+            max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+            concurrent_tools=True,
+        ),
+        [
+            ToolCallRequest(id="ro1", name="read_a", arguments={}),
+            ToolCallRequest(id="ro2", name="read_b", arguments={}),
+            ToolCallRequest(id="rw1", name="write_a", arguments={}),
+        ],
+        {},
+    )
+
+    assert shared_events[0:2] == ["start:read_a", "start:read_b"]
+    assert "end:read_a" in shared_events and "end:read_b" in shared_events
+    assert shared_events.index("end:read_a") < shared_events.index("start:write_a")
+    assert shared_events.index("end:read_b") < shared_events.index("start:write_a")
+    assert shared_events[-2:] == ["start:write_a", "end:write_a"]
+
+
+@pytest.mark.asyncio
+async def test_runner_blocks_repeated_external_fetches():
+    from nanobot.agent.runner import AgentRunSpec, AgentRunner
+
+    provider = MagicMock()
+    captured_final_call: list[dict] = []
+    call_count = {"n": 0}
+
+    async def chat_with_retry(*, messages, **kwargs):
+        call_count["n"] += 1
+        if call_count["n"] <= 3:
+            return LLMResponse(
+                content="working",
+                tool_calls=[ToolCallRequest(id=f"call_{call_count['n']}", name="web_fetch", arguments={"url": "https://example.com"})],
+                usage={},
+            )
+        captured_final_call[:] = messages
+        return LLMResponse(content="done", tool_calls=[], usage={})
+
+    provider.chat_with_retry = chat_with_retry
+    tools = MagicMock()
+    tools.get_definitions.return_value = []
+    tools.execute = AsyncMock(return_value="page content")
+
+    runner = AgentRunner(provider)
+    result = await runner.run(AgentRunSpec(
+        initial_messages=[{"role": "user", "content": "research task"}],
+        tools=tools,
+        model="test-model",
+        max_iterations=4,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+    ))
+
+    assert result.final_content == "done"
+    assert tools.execute.await_count == 2
+    blocked_tool_message = [
+        msg for msg in captured_final_call
+        if msg.get("role") == "tool" and msg.get("tool_call_id") == "call_3"
+    ][0]
+    assert "repeated external lookup blocked" in blocked_tool_message["content"]
+
+
 @pytest.mark.asyncio
 async def test_loop_max_iterations_message_stays_stable(tmp_path):
     loop = _make_loop(tmp_path)
@@ -307,6 +772,57 @@ async def test_loop_stream_filter_handles_think_only_prefix_without_crashing(tmp
     assert endings == [False]
 
 
+@pytest.mark.asyncio
+async def test_loop_retries_think_only_final_response(tmp_path):
+    loop = _make_loop(tmp_path)
+    call_count = {"n": 0}
+
+    async def chat_with_retry(**kwargs):
+        call_count["n"] += 1
+        if call_count["n"] == 1:
+            return LLMResponse(content="<think>hidden</think>", tool_calls=[], usage={})
+        return LLMResponse(content="Recovered answer", tool_calls=[], usage={})
+
+    loop.provider.chat_with_retry = chat_with_retry
+
+    final_content, _, _ = await loop._run_agent_loop([])
+
+    assert final_content == "Recovered answer"
+    assert call_count["n"] == 2
+
+
+@pytest.mark.asyncio
+async def test_runner_tool_error_sets_final_content():
+    from nanobot.agent.runner import AgentRunSpec, AgentRunner
+
+    provider = MagicMock()
+
+    async def chat_with_retry(*, messages, **kwargs):
+        return LLMResponse(
+            content="working",
+            tool_calls=[ToolCallRequest(id="call_1", name="read_file", arguments={"path": "x"})],
+            usage={},
+        )
+
+    provider.chat_with_retry = chat_with_retry
+    tools = MagicMock()
+    tools.get_definitions.return_value = []
+    tools.execute = AsyncMock(side_effect=RuntimeError("boom"))
+
+    runner = AgentRunner(provider)
+    result = await runner.run(AgentRunSpec(
+        initial_messages=[{"role": "user", "content": "do task"}],
+        tools=tools,
+        model="test-model",
+        max_iterations=1,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+        fail_on_tool_error=True,
+    ))
+
+    assert result.final_content == "Error: RuntimeError: boom"
+    assert result.stop_reason == "tool_error"
+
+
 @pytest.mark.asyncio
 async def test_subagent_max_iterations_announces_existing_fallback(tmp_path, monkeypatch):
     from nanobot.agent.subagent import SubagentManager
@@ -317,15 +833,20 @@ async def test_subagent_max_iterations_announces_existing_fallback(tmp_path, mon
     provider.get_default_model.return_value = "test-model"
     provider.chat_with_retry = AsyncMock(return_value=LLMResponse(
         content="working",
-        tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={})],
+        tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={"path": "."})],
     ))
-    mgr = SubagentManager(provider=provider, workspace=tmp_path, bus=bus)
+    mgr = SubagentManager(
+        provider=provider,
+        workspace=tmp_path,
+        bus=bus,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+    )
     mgr._announce_result = AsyncMock()
 
-    async def fake_execute(self, name, arguments):
+    async def fake_execute(self, **kwargs):
         return "tool result"
 
-    monkeypatch.setattr("nanobot.agent.tools.registry.ToolRegistry.execute", fake_execute)
+    monkeypatch.setattr("nanobot.agent.tools.filesystem.ListDirTool.execute", fake_execute)
 
     await mgr._run_subagent("sub-1", "do task", "label", {"channel": "test", "chat_id": "c1"})
 
@@ -333,3 +854,84 @@ async def test_subagent_max_iterations_announces_existing_fallback(tmp_path, mon
     args = mgr._announce_result.await_args.args
     assert args[3] == "Task completed but no final response was generated."
     assert args[5] == "ok"
+
+
+@pytest.mark.asyncio
+async def test_runner_accumulates_usage_and_preserves_cached_tokens():
+    """Runner should accumulate prompt/completion tokens across iterations
+    and preserve cached_tokens from provider responses."""
+    from nanobot.agent.runner import AgentRunSpec, AgentRunner
+
+    provider = MagicMock()
+    call_count = {"n": 0}
+
+    async def 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="read_file", arguments={"path": "x"})],
+                usage={"prompt_tokens": 100, "completion_tokens": 10, "cached_tokens": 80},
+            )
+        return LLMResponse(
+            content="done",
+            tool_calls=[],
+            usage={"prompt_tokens": 200, "completion_tokens": 20, "cached_tokens": 150},
+        )
+
+    provider.chat_with_retry = chat_with_retry
+    tools = MagicMock()
+    tools.get_definitions.return_value = []
+    tools.execute = AsyncMock(return_value="file content")
+
+    runner = AgentRunner(provider)
+    result = await runner.run(AgentRunSpec(
+        initial_messages=[{"role": "user", "content": "do task"}],
+        tools=tools,
+        model="test-model",
+        max_iterations=3,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+    ))
+
+    # Usage should be accumulated across iterations
+    assert result.usage["prompt_tokens"] == 300  # 100 + 200
+    assert result.usage["completion_tokens"] == 30  # 10 + 20
+    assert result.usage["cached_tokens"] == 230  # 80 + 150
+
+
+@pytest.mark.asyncio
+async def test_runner_passes_cached_tokens_to_hook_context():
+    """Hook context.usage should contain cached_tokens."""
+    from nanobot.agent.hook import AgentHook, AgentHookContext
+    from nanobot.agent.runner import AgentRunSpec, AgentRunner
+
+    provider = MagicMock()
+    captured_usage: list[dict] = []
+
+    class UsageHook(AgentHook):
+        async def after_iteration(self, context: AgentHookContext) -> None:
+            captured_usage.append(dict(context.usage))
+
+    async def chat_with_retry(**kwargs):
+        return LLMResponse(
+            content="done",
+            tool_calls=[],
+            usage={"prompt_tokens": 200, "completion_tokens": 20, "cached_tokens": 150},
+        )
+
+    provider.chat_with_retry = chat_with_retry
+    tools = MagicMock()
+    tools.get_definitions.return_value = []
+
+    runner = AgentRunner(provider)
+    await runner.run(AgentRunSpec(
+        initial_messages=[],
+        tools=tools,
+        model="test-model",
+        max_iterations=1,
+        max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+        hook=UsageHook(),
+    ))
+
+    assert len(captured_usage) == 1
+    assert captured_usage[0]["cached_tokens"] == 150

tests/agent/test_session_manager_history.py

@@ -173,6 +173,27 @@ def test_empty_session_history():
     assert history == []
 
 
+def test_get_history_preserves_reasoning_content():
+    session = Session(key="test:reasoning")
+    session.messages.append({"role": "user", "content": "hi"})
+    session.messages.append({
+        "role": "assistant",
+        "content": "done",
+        "reasoning_content": "hidden chain of thought",
+    })
+
+    history = session.get_history(max_messages=500)
+
+    assert history == [
+        {"role": "user", "content": "hi"},
+        {
+            "role": "assistant",
+            "content": "done",
+            "reasoning_content": "hidden chain of thought",
+        },
+    ]
+
+
 # --- Window cuts mid-group: assistant present but some tool results orphaned ---
 
 def test_window_cuts_mid_tool_group():

tests/agent/test_task_cancel.py

@@ -8,6 +8,10 @@ from unittest.mock import AsyncMock, MagicMock, patch
 
 import pytest
 
+from nanobot.config.schema import AgentDefaults
+
+_MAX_TOOL_RESULT_CHARS = AgentDefaults().max_tool_result_chars
+
 
 def _make_loop(*, exec_config=None):
     """Create a minimal AgentLoop with mocked dependencies."""
@@ -186,7 +190,12 @@ class TestSubagentCancellation:
         bus = MessageBus()
         provider = MagicMock()
         provider.get_default_model.return_value = "test-model"
-        mgr = SubagentManager(provider=provider, workspace=MagicMock(), bus=bus)
+        mgr = SubagentManager(
+            provider=provider,
+            workspace=MagicMock(),
+            bus=bus,
+            max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+        )
 
         cancelled = asyncio.Event()
 
@@ -214,7 +223,12 @@ class TestSubagentCancellation:
         bus = MessageBus()
         provider = MagicMock()
         provider.get_default_model.return_value = "test-model"
-        mgr = SubagentManager(provider=provider, workspace=MagicMock(), bus=bus)
+        mgr = SubagentManager(
+            provider=provider,
+            workspace=MagicMock(),
+            bus=bus,
+            max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+        )
         assert await mgr.cancel_by_session("nonexistent") == 0
 
     @pytest.mark.asyncio
@@ -236,19 +250,24 @@ class TestSubagentCancellation:
             if call_count["n"] == 1:
                 return LLMResponse(
                     content="thinking",
-                    tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={})],
+                    tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={"path": "."})],
                     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)
+        mgr = SubagentManager(
+            provider=provider,
+            workspace=tmp_path,
+            bus=bus,
+            max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+        )
 
-        async def fake_execute(self, name, arguments):
+        async def fake_execute(self, **kwargs):
             return "tool result"
 
-        monkeypatch.setattr("nanobot.agent.tools.registry.ToolRegistry.execute", fake_execute)
+        monkeypatch.setattr("nanobot.agent.tools.filesystem.ListDirTool.execute", fake_execute)
 
         await mgr._run_subagent("sub-1", "do task", "label", {"channel": "test", "chat_id": "c1"})
 
@@ -273,6 +292,7 @@ class TestSubagentCancellation:
             provider=provider,
             workspace=tmp_path,
             bus=bus,
+            max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
             exec_config=ExecToolConfig(enable=False),
         )
         mgr._announce_result = AsyncMock()
@@ -304,20 +324,25 @@ class TestSubagentCancellation:
         provider.get_default_model.return_value = "test-model"
         provider.chat_with_retry = AsyncMock(return_value=LLMResponse(
             content="thinking",
-            tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={})],
+            tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={"path": "."})],
         ))
-        mgr = SubagentManager(provider=provider, workspace=tmp_path, bus=bus)
+        mgr = SubagentManager(
+            provider=provider,
+            workspace=tmp_path,
+            bus=bus,
+            max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+        )
         mgr._announce_result = AsyncMock()
 
         calls = {"n": 0}
 
-        async def fake_execute(self, name, arguments):
+        async def fake_execute(self, **kwargs):
             calls["n"] += 1
             if calls["n"] == 1:
                 return "first result"
             raise RuntimeError("boom")
 
-        monkeypatch.setattr("nanobot.agent.tools.registry.ToolRegistry.execute", fake_execute)
+        monkeypatch.setattr("nanobot.agent.tools.filesystem.ListDirTool.execute", fake_execute)
 
         await mgr._run_subagent("sub-1", "do task", "label", {"channel": "test", "chat_id": "c1"})
 
@@ -340,15 +365,20 @@ class TestSubagentCancellation:
         provider.get_default_model.return_value = "test-model"
         provider.chat_with_retry = AsyncMock(return_value=LLMResponse(
             content="thinking",
-            tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={})],
+            tool_calls=[ToolCallRequest(id="call_1", name="list_dir", arguments={"path": "."})],
         ))
-        mgr = SubagentManager(provider=provider, workspace=tmp_path, bus=bus)
+        mgr = SubagentManager(
+            provider=provider,
+            workspace=tmp_path,
+            bus=bus,
+            max_tool_result_chars=_MAX_TOOL_RESULT_CHARS,
+        )
         mgr._announce_result = AsyncMock()
 
         started = asyncio.Event()
         cancelled = asyncio.Event()
 
-        async def fake_execute(self, name, arguments):
+        async def fake_execute(self, **kwargs):
             started.set()
             try:
                 await asyncio.sleep(60)
@@ -356,7 +386,7 @@ class TestSubagentCancellation:
                 cancelled.set()
                 raise
 
-        monkeypatch.setattr("nanobot.agent.tools.registry.ToolRegistry.execute", fake_execute)
+        monkeypatch.setattr("nanobot.agent.tools.filesystem.ListDirTool.execute", fake_execute)
 
         task = asyncio.create_task(
             mgr._run_subagent("sub-1", "do task", "label", {"channel": "test", "chat_id": "c1"})
@@ -364,7 +394,7 @@ class TestSubagentCancellation:
         mgr._running_tasks["sub-1"] = task
         mgr._session_tasks["test:c1"] = {"sub-1"}
 
-        await started.wait()
+        await asyncio.wait_for(started.wait(), timeout=1.0)
 
         count = await mgr.cancel_by_session("test:c1")
 

tests/channels/test_channel_plugins.py

@@ -13,6 +13,7 @@ from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.channels.manager import ChannelManager
 from nanobot.config.schema import ChannelsConfig
+from nanobot.utils.restart import RestartNotice
 
 
 # ---------------------------------------------------------------------------
@@ -208,7 +209,7 @@ def test_channels_login_uses_discovered_plugin_class(monkeypatch):
             seen["config"] = self.config
             return True
 
-    monkeypatch.setattr("nanobot.config.loader.load_config", lambda: Config())
+    monkeypatch.setattr("nanobot.config.loader.load_config", lambda config_path=None: Config())
     monkeypatch.setattr(
         "nanobot.channels.registry.discover_all",
         lambda: {"fakeplugin": _LoginPlugin},
@@ -220,6 +221,57 @@ def test_channels_login_uses_discovered_plugin_class(monkeypatch):
     assert seen["force"] is True
 
 
+def test_channels_login_sets_custom_config_path(monkeypatch, tmp_path):
+    from nanobot.cli.commands import app
+    from nanobot.config.schema import Config
+    from typer.testing import CliRunner
+
+    runner = CliRunner()
+    seen: dict[str, object] = {}
+    config_path = tmp_path / "custom-config.json"
+
+    class _LoginPlugin(_FakePlugin):
+        async def login(self, force: bool = False) -> bool:
+            return True
+
+    monkeypatch.setattr("nanobot.config.loader.load_config", lambda config_path=None: Config())
+    monkeypatch.setattr(
+        "nanobot.config.loader.set_config_path",
+        lambda path: seen.__setitem__("config_path", path),
+    )
+    monkeypatch.setattr(
+        "nanobot.channels.registry.discover_all",
+        lambda: {"fakeplugin": _LoginPlugin},
+    )
+
+    result = runner.invoke(app, ["channels", "login", "fakeplugin", "--config", str(config_path)])
+
+    assert result.exit_code == 0
+    assert seen["config_path"] == config_path.resolve()
+
+
+def test_channels_status_sets_custom_config_path(monkeypatch, tmp_path):
+    from nanobot.cli.commands import app
+    from nanobot.config.schema import Config
+    from typer.testing import CliRunner
+
+    runner = CliRunner()
+    seen: dict[str, object] = {}
+    config_path = tmp_path / "custom-config.json"
+
+    monkeypatch.setattr("nanobot.config.loader.load_config", lambda config_path=None: Config())
+    monkeypatch.setattr(
+        "nanobot.config.loader.set_config_path",
+        lambda path: seen.__setitem__("config_path", path),
+    )
+    monkeypatch.setattr("nanobot.channels.registry.discover_all", lambda: {})
+
+    result = runner.invoke(app, ["channels", "status", "--config", str(config_path)])
+
+    assert result.exit_code == 0
+    assert seen["config_path"] == config_path.resolve()
+
+
 @pytest.mark.asyncio
 async def test_manager_skips_disabled_plugin():
     fake_config = SimpleNamespace(
@@ -878,3 +930,30 @@ async def test_start_all_creates_dispatch_task():
     # Dispatch task should have been created
     assert mgr._dispatch_task is not None
 
+
+@pytest.mark.asyncio
+async def test_notify_restart_done_enqueues_outbound_message():
+    """Restart notice should schedule send_with_retry for target channel."""
+    fake_config = SimpleNamespace(
+        channels=ChannelsConfig(),
+        providers=SimpleNamespace(groq=SimpleNamespace(api_key="")),
+    )
+
+    mgr = ChannelManager.__new__(ChannelManager)
+    mgr.config = fake_config
+    mgr.bus = MessageBus()
+    mgr.channels = {"feishu": _StartableChannel(fake_config, mgr.bus)}
+    mgr._dispatch_task = None
+    mgr._send_with_retry = AsyncMock()
+
+    notice = RestartNotice(channel="feishu", chat_id="oc_123", started_at_raw="100.0")
+    with patch("nanobot.channels.manager.consume_restart_notice_from_env", return_value=notice):
+        mgr._notify_restart_done_if_needed()
+
+    await asyncio.sleep(0)
+    mgr._send_with_retry.assert_awaited_once()
+    sent_channel, sent_msg = mgr._send_with_retry.await_args.args
+    assert sent_channel is mgr.channels["feishu"]
+    assert sent_msg.channel == "feishu"
+    assert sent_msg.chat_id == "oc_123"
+    assert sent_msg.content.startswith("Restart completed")

tests/channels/test_discord_channel.py

@@ -594,7 +594,7 @@ async def test_send_stops_typing_after_send() -> None:
     typing_channel.typing_enter_hook = slow_typing
 
     await channel._start_typing(typing_channel)
-    await start.wait()
+    await asyncio.wait_for(start.wait(), timeout=1.0)
 
     await channel.send(OutboundMessage(channel="discord", chat_id="123", content="hello"))
     release.set()
@@ -614,7 +614,7 @@ async def test_send_stops_typing_after_send() -> None:
     typing_channel.typing_enter_hook = slow_typing_progress
 
     await channel._start_typing(typing_channel)
-    await start.wait()
+    await asyncio.wait_for(start.wait(), timeout=1.0)
 
     await channel.send(
         OutboundMessage(
@@ -665,7 +665,7 @@ async def test_start_typing_uses_typing_context_when_trigger_typing_missing() ->
 
     typing_channel = _NoTriggerChannel(channel_id=123)
     await channel._start_typing(typing_channel)  # type: ignore[arg-type]
-    await entered.wait()
+    await asyncio.wait_for(entered.wait(), timeout=1.0)
 
     assert "123" in channel._typing_tasks
 

tests/channels/test_matrix_channel.py

@@ -3,16 +3,14 @@ from pathlib import Path
 from types import SimpleNamespace
 
 import pytest
+
+pytest.importorskip("nio")
+pytest.importorskip("nh3")
+pytest.importorskip("mistune")
 from nio import RoomSendResponse
 
 from nanobot.channels.matrix import _build_matrix_text_content
 
-# Check optional matrix dependencies before importing
-try:
-    import nh3  # noqa: F401
-except ImportError:
-    pytest.skip("Matrix dependencies not installed (nh3)", allow_module_level=True)
-
 import nanobot.channels.matrix as matrix_module
 from nanobot.bus.events import OutboundMessage
 from nanobot.bus.queue import MessageBus

tests/channels/test_qq_ack_message.py

@@ -0,0 +1,172 @@
+"""Tests for QQ channel ack_message feature.
+
+Covers the four verification points from the PR:
+1. C2C message: ack appears instantly
+2. Group message: ack appears instantly
+3. ack_message set to "": no ack sent
+4. Custom ack_message text: correct text delivered
+Each test also verifies that normal message processing is not blocked.
+"""
+
+from types import SimpleNamespace
+
+import pytest
+
+try:
+    from nanobot.channels import qq
+
+    QQ_AVAILABLE = getattr(qq, "QQ_AVAILABLE", False)
+except ImportError:
+    QQ_AVAILABLE = False
+
+if not QQ_AVAILABLE:
+    pytest.skip("QQ dependencies not installed (qq-botpy)", allow_module_level=True)
+
+from nanobot.bus.queue import MessageBus
+from nanobot.channels.qq import QQChannel, QQConfig
+
+
+class _FakeApi:
+    def __init__(self) -> None:
+        self.c2c_calls: list[dict] = []
+        self.group_calls: list[dict] = []
+
+    async def post_c2c_message(self, **kwargs) -> None:
+        self.c2c_calls.append(kwargs)
+
+    async def post_group_message(self, **kwargs) -> None:
+        self.group_calls.append(kwargs)
+
+
+class _FakeClient:
+    def __init__(self) -> None:
+        self.api = _FakeApi()
+
+
+@pytest.mark.asyncio
+async def test_ack_sent_on_c2c_message() -> None:
+    """Ack is sent immediately for C2C messages, then normal processing continues."""
+    channel = QQChannel(
+        QQConfig(
+            app_id="app",
+            secret="secret",
+            allow_from=["*"],
+            ack_message="⏳ Processing...",
+        ),
+        MessageBus(),
+    )
+    channel._client = _FakeClient()
+
+    data = SimpleNamespace(
+        id="msg1",
+        content="hello",
+        author=SimpleNamespace(user_openid="user1"),
+        attachments=[],
+    )
+    await channel._on_message(data, is_group=False)
+
+    assert len(channel._client.api.c2c_calls) >= 1
+    ack_call = channel._client.api.c2c_calls[0]
+    assert ack_call["content"] == "⏳ Processing..."
+    assert ack_call["openid"] == "user1"
+    assert ack_call["msg_id"] == "msg1"
+    assert ack_call["msg_type"] == 0
+
+    msg = await channel.bus.consume_inbound()
+    assert msg.content == "hello"
+    assert msg.sender_id == "user1"
+
+
+@pytest.mark.asyncio
+async def test_ack_sent_on_group_message() -> None:
+    """Ack is sent immediately for group messages, then normal processing continues."""
+    channel = QQChannel(
+        QQConfig(
+            app_id="app",
+            secret="secret",
+            allow_from=["*"],
+            ack_message="⏳ Processing...",
+        ),
+        MessageBus(),
+    )
+    channel._client = _FakeClient()
+
+    data = SimpleNamespace(
+        id="msg2",
+        content="hello group",
+        group_openid="group123",
+        author=SimpleNamespace(member_openid="user1"),
+        attachments=[],
+    )
+    await channel._on_message(data, is_group=True)
+
+    assert len(channel._client.api.group_calls) >= 1
+    ack_call = channel._client.api.group_calls[0]
+    assert ack_call["content"] == "⏳ Processing..."
+    assert ack_call["group_openid"] == "group123"
+    assert ack_call["msg_id"] == "msg2"
+    assert ack_call["msg_type"] == 0
+
+    msg = await channel.bus.consume_inbound()
+    assert msg.content == "hello group"
+    assert msg.chat_id == "group123"
+
+
+@pytest.mark.asyncio
+async def test_no_ack_when_ack_message_empty() -> None:
+    """Setting ack_message to empty string disables the ack entirely."""
+    channel = QQChannel(
+        QQConfig(
+            app_id="app",
+            secret="secret",
+            allow_from=["*"],
+            ack_message="",
+        ),
+        MessageBus(),
+    )
+    channel._client = _FakeClient()
+
+    data = SimpleNamespace(
+        id="msg3",
+        content="hello",
+        author=SimpleNamespace(user_openid="user1"),
+        attachments=[],
+    )
+    await channel._on_message(data, is_group=False)
+
+    assert len(channel._client.api.c2c_calls) == 0
+    assert len(channel._client.api.group_calls) == 0
+
+    msg = await channel.bus.consume_inbound()
+    assert msg.content == "hello"
+
+
+@pytest.mark.asyncio
+async def test_custom_ack_message_text() -> None:
+    """Custom Chinese ack_message text is delivered correctly."""
+    custom = "正在处理中，请稍候..."
+    channel = QQChannel(
+        QQConfig(
+            app_id="app",
+            secret="secret",
+            allow_from=["*"],
+            ack_message=custom,
+        ),
+        MessageBus(),
+    )
+    channel._client = _FakeClient()
+
+    data = SimpleNamespace(
+        id="msg4",
+        content="test input",
+        author=SimpleNamespace(user_openid="user1"),
+        attachments=[],
+    )
+    await channel._on_message(data, is_group=False)
+
+    assert len(channel._client.api.c2c_calls) >= 1
+    ack_call = channel._client.api.c2c_calls[0]
+    assert ack_call["content"] == custom
+
+    msg = await channel.bus.consume_inbound()
+    assert msg.content == "test input"

tests/channels/test_telegram_channel.py

@@ -32,8 +32,10 @@ class _FakeHTTPXRequest:
 class _FakeUpdater:
     def __init__(self, on_start_polling) -> None:
         self._on_start_polling = on_start_polling
+        self.start_polling_kwargs = None
 
     async def start_polling(self, **kwargs) -> None:
+        self.start_polling_kwargs = kwargs
         self._on_start_polling()
 
 
@@ -184,7 +186,11 @@ async def test_start_creates_separate_pools_with_proxy(monkeypatch) -> None:
     assert poll_req.kwargs["connection_pool_size"] == 4
     assert builder.request_value is api_req
     assert builder.get_updates_request_value is poll_req
+    assert callable(app.updater.start_polling_kwargs["error_callback"])
     assert any(cmd.command == "status" for cmd in app.bot.commands)
+    assert any(cmd.command == "dream" for cmd in app.bot.commands)
+    assert any(cmd.command == "dream_log" for cmd in app.bot.commands)
+    assert any(cmd.command == "dream_restore" for cmd in app.bot.commands)
 
 
 @pytest.mark.asyncio
@@ -304,6 +310,26 @@ async def test_on_error_logs_network_issues_as_warning(monkeypatch) -> None:
     assert recorded == [("warning", "Telegram network issue: proxy disconnected")]
 
 
+@pytest.mark.asyncio
+async def test_on_error_summarizes_empty_network_error(monkeypatch) -> None:
+    from telegram.error import NetworkError
+
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"]),
+        MessageBus(),
+    )
+    recorded: list[tuple[str, str]] = []
+
+    monkeypatch.setattr(
+        "nanobot.channels.telegram.logger.warning",
+        lambda message, error: recorded.append(("warning", message.format(error))),
+    )
+
+    await channel._on_error(object(), SimpleNamespace(error=NetworkError("")))
+
+    assert recorded == [("warning", "Telegram network issue: NetworkError")]
+
+
 @pytest.mark.asyncio
 async def test_on_error_keeps_non_network_exceptions_as_error(monkeypatch) -> None:
     channel = TelegramChannel(
@@ -647,43 +673,56 @@ async def test_group_policy_open_accepts_plain_group_message() -> None:
     assert channel._app.bot.get_me_calls == 0
 
 
-def test_extract_reply_context_no_reply() -> None:
+@pytest.mark.asyncio
+async def test_extract_reply_context_no_reply() -> None:
     """When there is no reply_to_message, _extract_reply_context returns None."""
+    channel = TelegramChannel(TelegramConfig(enabled=True, token="123:abc"), MessageBus())
     message = SimpleNamespace(reply_to_message=None)
-    assert TelegramChannel._extract_reply_context(message) is None
+    assert await channel._extract_reply_context(message) is None
 
 
-def test_extract_reply_context_with_text() -> None:
+@pytest.mark.asyncio
+async def test_extract_reply_context_with_text() -> None:
     """When reply has text, return prefixed string."""
-    reply = SimpleNamespace(text="Hello world", caption=None)
+    channel = TelegramChannel(TelegramConfig(enabled=True, token="123:abc"), MessageBus())
+    channel._app = _FakeApp(lambda: None)
+    reply = SimpleNamespace(text="Hello world", caption=None, from_user=SimpleNamespace(id=2, username="testuser", first_name="Test"))
     message = SimpleNamespace(reply_to_message=reply)
-    assert TelegramChannel._extract_reply_context(message) == "[Reply to: Hello world]"
+    assert await channel._extract_reply_context(message) == "[Reply to @testuser: Hello world]"
 
 
-def test_extract_reply_context_with_caption_only() -> None:
+@pytest.mark.asyncio
+async def test_extract_reply_context_with_caption_only() -> None:
     """When reply has only caption (no text), caption is used."""
-    reply = SimpleNamespace(text=None, caption="Photo caption")
+    channel = TelegramChannel(TelegramConfig(enabled=True, token="123:abc"), MessageBus())
+    channel._app = _FakeApp(lambda: None)
+    reply = SimpleNamespace(text=None, caption="Photo caption", from_user=SimpleNamespace(id=2, username=None, first_name="Test"))
     message = SimpleNamespace(reply_to_message=reply)
-    assert TelegramChannel._extract_reply_context(message) == "[Reply to: Photo caption]"
+    assert await channel._extract_reply_context(message) == "[Reply to Test: Photo caption]"
 
 
-def test_extract_reply_context_truncation() -> None:
+@pytest.mark.asyncio
+async def test_extract_reply_context_truncation() -> None:
     """Reply text is truncated at TELEGRAM_REPLY_CONTEXT_MAX_LEN."""
+    channel = TelegramChannel(TelegramConfig(enabled=True, token="123:abc"), MessageBus())
+    channel._app = _FakeApp(lambda: None)
     long_text = "x" * (TELEGRAM_REPLY_CONTEXT_MAX_LEN + 100)
-    reply = SimpleNamespace(text=long_text, caption=None)
+    reply = SimpleNamespace(text=long_text, caption=None, from_user=SimpleNamespace(id=2, username=None, first_name=None))
     message = SimpleNamespace(reply_to_message=reply)
-    result = TelegramChannel._extract_reply_context(message)
+    result = await channel._extract_reply_context(message)
     assert result is not None
     assert result.startswith("[Reply to: ")
     assert result.endswith("...]")
     assert len(result) == len("[Reply to: ]") + TELEGRAM_REPLY_CONTEXT_MAX_LEN + len("...")
 
 
-def test_extract_reply_context_no_text_returns_none() -> None:
+@pytest.mark.asyncio
+async def test_extract_reply_context_no_text_returns_none() -> None:
     """When reply has no text/caption, _extract_reply_context returns None (media handled separately)."""
+    channel = TelegramChannel(TelegramConfig(enabled=True, token="123:abc"), MessageBus())
     reply = SimpleNamespace(text=None, caption=None)
     message = SimpleNamespace(reply_to_message=reply)
-    assert TelegramChannel._extract_reply_context(message) is None
+    assert await channel._extract_reply_context(message) is None
 
 
 @pytest.mark.asyncio
@@ -949,6 +988,48 @@ async def test_forward_command_does_not_inject_reply_context() -> None:
     assert handled[0]["content"] == "/new"
 
 
+@pytest.mark.asyncio
+async def test_forward_command_preserves_dream_log_args_and_strips_bot_suffix() -> None:
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"], group_policy="open"),
+        MessageBus(),
+    )
+    channel._app = _FakeApp(lambda: None)
+    handled = []
+
+    async def capture_handle(**kwargs) -> None:
+        handled.append(kwargs)
+
+    channel._handle_message = capture_handle
+    update = _make_telegram_update(text="/dream-log@nanobot_test deadbeef", reply_to_message=None)
+
+    await channel._forward_command(update, None)
+
+    assert len(handled) == 1
+    assert handled[0]["content"] == "/dream-log deadbeef"
+
+
+@pytest.mark.asyncio
+async def test_forward_command_normalizes_telegram_safe_dream_aliases() -> None:
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"], group_policy="open"),
+        MessageBus(),
+    )
+    channel._app = _FakeApp(lambda: None)
+    handled = []
+
+    async def capture_handle(**kwargs) -> None:
+        handled.append(kwargs)
+
+    channel._handle_message = capture_handle
+    update = _make_telegram_update(text="/dream_restore@nanobot_test deadbeef", reply_to_message=None)
+
+    await channel._forward_command(update, None)
+
+    assert len(handled) == 1
+    assert handled[0]["content"] == "/dream-restore deadbeef"
+
+
 @pytest.mark.asyncio
 async def test_on_help_includes_restart_command() -> None:
     channel = TelegramChannel(
@@ -964,3 +1045,6 @@ async def test_on_help_includes_restart_command() -> None:
     help_text = update.message.reply_text.await_args.args[0]
     assert "/restart" in help_text
     assert "/status" in help_text
+    assert "/dream" in help_text
+    assert "/dream-log" in help_text
+    assert "/dream-restore" in help_text

tests/channels/test_weixin_channel.py

@@ -572,6 +572,85 @@ async def test_process_message_skips_bot_messages() -> None:
     assert bus.inbound_size == 0
 
 
+@pytest.mark.asyncio
+async def test_process_message_starts_typing_on_inbound() -> None:
+    """Typing indicator fires immediately when user message arrives."""
+    channel, _bus = _make_channel()
+    channel._running = True
+    channel._client = object()
+    channel._token = "token"
+    channel._start_typing = AsyncMock()
+
+    await channel._process_message(
+        {
+            "message_type": 1,
+            "message_id": "m-typing",
+            "from_user_id": "wx-user",
+            "context_token": "ctx-typing",
+            "item_list": [
+                {"type": ITEM_TEXT, "text_item": {"text": "hello"}},
+            ],
+        }
+    )
+
+    channel._start_typing.assert_awaited_once_with("wx-user", "ctx-typing")
+
+
+@pytest.mark.asyncio
+async def test_send_final_message_clears_typing_indicator() -> None:
+    """Non-progress send should cancel typing status."""
+    channel, _bus = _make_channel()
+    channel._client = object()
+    channel._token = "token"
+    channel._context_tokens["wx-user"] = "ctx-2"
+    channel._typing_tickets["wx-user"] = {"ticket": "ticket-2", "next_fetch_at": 9999999999}
+    channel._send_text = AsyncMock()
+    channel._api_post = AsyncMock(return_value={"ret": 0})
+
+    await channel.send(
+        type("Msg", (), {"chat_id": "wx-user", "content": "pong", "media": [], "metadata": {}})()
+    )
+
+    channel._send_text.assert_awaited_once_with("wx-user", "pong", "ctx-2")
+    typing_cancel_calls = [
+        c for c in channel._api_post.await_args_list
+        if c.args[0] == "ilink/bot/sendtyping" and c.args[1]["status"] == 2
+    ]
+    assert len(typing_cancel_calls) >= 1
+
+
+@pytest.mark.asyncio
+async def test_send_progress_message_keeps_typing_indicator() -> None:
+    """Progress messages must not cancel typing status."""
+    channel, _bus = _make_channel()
+    channel._client = object()
+    channel._token = "token"
+    channel._context_tokens["wx-user"] = "ctx-2"
+    channel._typing_tickets["wx-user"] = {"ticket": "ticket-2", "next_fetch_at": 9999999999}
+    channel._send_text = AsyncMock()
+    channel._api_post = AsyncMock(return_value={"ret": 0})
+
+    await channel.send(
+        type(
+            "Msg",
+            (),
+            {
+                "chat_id": "wx-user",
+                "content": "thinking",
+                "media": [],
+                "metadata": {"_progress": True},
+            },
+        )()
+    )
+
+    channel._send_text.assert_awaited_once_with("wx-user", "thinking", "ctx-2")
+    typing_cancel_calls = [
+        c for c in channel._api_post.await_args_list
+        if c.args and c.args[0] == "ilink/bot/sendtyping" and c.args[1].get("status") == 2
+    ]
+    assert len(typing_cancel_calls) == 0
+
+
 class _DummyHttpResponse:
     def __init__(self, *, headers: dict[str, str] | None = None, status_code: int = 200) -> None:
         self.headers = headers or {}

tests/cli/test_commands.py

@@ -317,6 +317,75 @@ def test_openai_compat_provider_passes_model_through():
     assert provider.get_default_model() == "github-copilot/gpt-5.3-codex"
 
 
+def test_make_provider_uses_github_copilot_backend():
+    from nanobot.cli.commands import _make_provider
+    from nanobot.config.schema import Config
+
+    config = Config.model_validate(
+        {
+            "agents": {
+                "defaults": {
+                    "provider": "github-copilot",
+                    "model": "github-copilot/gpt-4.1",
+                }
+            }
+        }
+    )
+
+    with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI"):
+        provider = _make_provider(config)
+
+    assert provider.__class__.__name__ == "GitHubCopilotProvider"
+
+
+def test_github_copilot_provider_strips_prefixed_model_name():
+    from nanobot.providers.github_copilot_provider import GitHubCopilotProvider
+
+    with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI"):
+        provider = GitHubCopilotProvider(default_model="github-copilot/gpt-5.1")
+
+    kwargs = provider._build_kwargs(
+        messages=[{"role": "user", "content": "hi"}],
+        tools=None,
+        model="github-copilot/gpt-5.1",
+        max_tokens=16,
+        temperature=0.1,
+        reasoning_effort=None,
+        tool_choice=None,
+    )
+
+    assert kwargs["model"] == "gpt-5.1"
+
+
+@pytest.mark.asyncio
+async def test_github_copilot_provider_refreshes_client_api_key_before_chat():
+    from nanobot.providers.github_copilot_provider import GitHubCopilotProvider
+
+    mock_client = MagicMock()
+    mock_client.api_key = "no-key"
+    mock_client.chat.completions.create = AsyncMock(return_value={
+        "choices": [{"message": {"content": "ok"}, "finish_reason": "stop"}],
+        "usage": {"prompt_tokens": 1, "completion_tokens": 1, "total_tokens": 2},
+    })
+
+    with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI", return_value=mock_client):
+        provider = GitHubCopilotProvider(default_model="github-copilot/gpt-5.1")
+
+    provider._get_copilot_access_token = AsyncMock(return_value="copilot-access-token")
+
+    response = await provider.chat(
+        messages=[{"role": "user", "content": "hi"}],
+        model="github-copilot/gpt-5.1",
+        max_tokens=16,
+        temperature=0.1,
+    )
+
+    assert response.content == "ok"
+    assert provider._client.api_key == "copilot-access-token"
+    provider._get_copilot_access_token.assert_awaited_once()
+    mock_client.chat.completions.create.assert_awaited_once()
+
+
 def test_openai_codex_strip_prefix_supports_hyphen_and_underscore():
     assert _strip_model_prefix("openai-codex/gpt-5.1-codex") == "gpt-5.1-codex"
     assert _strip_model_prefix("openai_codex/gpt-5.1-codex") == "gpt-5.1-codex"

tests/cli/test_restart_command.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import asyncio
+import os
 import time
 from unittest.mock import AsyncMock, MagicMock, patch
 
@@ -36,14 +37,23 @@ class TestRestartCommand:
     async def test_restart_sends_message_and_calls_execv(self):
         from nanobot.command.builtin import cmd_restart
         from nanobot.command.router import CommandContext
+        from nanobot.utils.restart import (
+            RESTART_NOTIFY_CHANNEL_ENV,
+            RESTART_NOTIFY_CHAT_ID_ENV,
+            RESTART_STARTED_AT_ENV,
+        )
 
         loop, bus = _make_loop()
         msg = InboundMessage(channel="cli", sender_id="user", chat_id="direct", content="/restart")
         ctx = CommandContext(msg=msg, session=None, key=msg.session_key, raw="/restart", loop=loop)
 
-        with patch("nanobot.command.builtin.os.execv") as mock_execv:
+        with patch.dict(os.environ, {}, clear=False), \
+             patch("nanobot.command.builtin.os.execv") as mock_execv:
             out = await cmd_restart(ctx)
             assert "Restarting" in out.content
+            assert os.environ.get(RESTART_NOTIFY_CHANNEL_ENV) == "cli"
+            assert os.environ.get(RESTART_NOTIFY_CHAT_ID_ENV) == "direct"
+            assert os.environ.get(RESTART_STARTED_AT_ENV)
 
             await asyncio.sleep(1.5)
             mock_execv.assert_called_once()
@@ -127,7 +137,7 @@ class TestRestartCommand:
         loop.sessions.get_or_create.return_value = session
         loop._start_time = time.time() - 125
         loop._last_usage = {"prompt_tokens": 0, "completion_tokens": 0}
-        loop.memory_consolidator.estimate_session_prompt_tokens = MagicMock(
+        loop.consolidator.estimate_session_prompt_tokens = MagicMock(
             return_value=(20500, "tiktoken")
         )
 
@@ -152,10 +162,12 @@ class TestRestartCommand:
         ])
 
         await loop._run_agent_loop([])
-        assert loop._last_usage == {"prompt_tokens": 9, "completion_tokens": 4}
+        assert loop._last_usage["prompt_tokens"] == 9
+        assert loop._last_usage["completion_tokens"] == 4
 
         await loop._run_agent_loop([])
-        assert loop._last_usage == {"prompt_tokens": 0, "completion_tokens": 0}
+        assert loop._last_usage["prompt_tokens"] == 0
+        assert loop._last_usage["completion_tokens"] == 0
 
     @pytest.mark.asyncio
     async def test_status_falls_back_to_last_usage_when_context_estimate_missing(self):
@@ -164,7 +176,7 @@ class TestRestartCommand:
         session.get_history.return_value = [{"role": "user"}]
         loop.sessions.get_or_create.return_value = session
         loop._last_usage = {"prompt_tokens": 1200, "completion_tokens": 34}
-        loop.memory_consolidator.estimate_session_prompt_tokens = MagicMock(
+        loop.consolidator.estimate_session_prompt_tokens = MagicMock(
             return_value=(0, "none")
         )
 

tests/command/test_builtin_dream.py

@@ -0,0 +1,143 @@
+from __future__ import annotations
+
+from types import SimpleNamespace
+
+import pytest
+
+from nanobot.bus.events import InboundMessage
+from nanobot.command.builtin import cmd_dream_log, cmd_dream_restore
+from nanobot.command.router import CommandContext
+from nanobot.utils.gitstore import CommitInfo
+
+
+class _FakeStore:
+    def __init__(self, git, last_dream_cursor: int = 1):
+        self.git = git
+        self._last_dream_cursor = last_dream_cursor
+
+    def get_last_dream_cursor(self) -> int:
+        return self._last_dream_cursor
+
+
+class _FakeGit:
+    def __init__(
+        self,
+        *,
+        initialized: bool = True,
+        commits: list[CommitInfo] | None = None,
+        diff_map: dict[str, tuple[CommitInfo, str] | None] | None = None,
+        revert_result: str | None = None,
+    ):
+        self._initialized = initialized
+        self._commits = commits or []
+        self._diff_map = diff_map or {}
+        self._revert_result = revert_result
+
+    def is_initialized(self) -> bool:
+        return self._initialized
+
+    def log(self, max_entries: int = 20) -> list[CommitInfo]:
+        return self._commits[:max_entries]
+
+    def show_commit_diff(self, sha: str, max_entries: int = 20):
+        return self._diff_map.get(sha)
+
+    def revert(self, sha: str) -> str | None:
+        return self._revert_result
+
+
+def _make_ctx(raw: str, git: _FakeGit, *, args: str = "", last_dream_cursor: int = 1) -> CommandContext:
+    msg = InboundMessage(channel="cli", sender_id="u1", chat_id="direct", content=raw)
+    store = _FakeStore(git, last_dream_cursor=last_dream_cursor)
+    loop = SimpleNamespace(consolidator=SimpleNamespace(store=store))
+    return CommandContext(msg=msg, session=None, key=msg.session_key, raw=raw, args=args, loop=loop)
+
+
+@pytest.mark.asyncio
+async def test_dream_log_latest_is_more_user_friendly() -> None:
+    commit = CommitInfo(sha="abcd1234", message="dream: 2026-04-04, 2 change(s)", timestamp="2026-04-04 12:00")
+    diff = (
+        "diff --git a/SOUL.md b/SOUL.md\n"
+        "--- a/SOUL.md\n"
+        "+++ b/SOUL.md\n"
+        "@@ -1 +1 @@\n"
+        "-old\n"
+        "+new\n"
+    )
+    git = _FakeGit(commits=[commit], diff_map={commit.sha: (commit, diff)})
+
+    out = await cmd_dream_log(_make_ctx("/dream-log", git))
+
+    assert "## Dream Update" in out.content
+    assert "Here is the latest Dream memory change." in out.content
+    assert "- Commit: `abcd1234`" in out.content
+    assert "- Changed files: `SOUL.md`" in out.content
+    assert "Use `/dream-restore abcd1234` to undo this change." in out.content
+    assert "```diff" in out.content
+
+
+@pytest.mark.asyncio
+async def test_dream_log_missing_commit_guides_user() -> None:
+    git = _FakeGit(diff_map={})
+
+    out = await cmd_dream_log(_make_ctx("/dream-log deadbeef", git, args="deadbeef"))
+
+    assert "Couldn't find Dream change `deadbeef`." in out.content
+    assert "Use `/dream-restore` to list recent versions" in out.content
+
+
+@pytest.mark.asyncio
+async def test_dream_log_before_first_run_is_clear() -> None:
+    git = _FakeGit(initialized=False)
+
+    out = await cmd_dream_log(_make_ctx("/dream-log", git, last_dream_cursor=0))
+
+    assert "Dream has not run yet." in out.content
+    assert "Run `/dream`" in out.content
+
+
+@pytest.mark.asyncio
+async def test_dream_restore_lists_versions_with_next_steps() -> None:
+    commits = [
+        CommitInfo(sha="abcd1234", message="dream: latest", timestamp="2026-04-04 12:00"),
+        CommitInfo(sha="bbbb2222", message="dream: older", timestamp="2026-04-04 08:00"),
+    ]
+    git = _FakeGit(commits=commits)
+
+    out = await cmd_dream_restore(_make_ctx("/dream-restore", git))
+
+    assert "## Dream Restore" in out.content
+    assert "Choose a Dream memory version to restore." in out.content
+    assert "`abcd1234` 2026-04-04 12:00 - dream: latest" in out.content
+    assert "Preview a version with `/dream-log <sha>`" in out.content
+    assert "Restore a version with `/dream-restore <sha>`." in out.content
+
+
+@pytest.mark.asyncio
+async def test_dream_restore_success_mentions_files_and_followup() -> None:
+    commit = CommitInfo(sha="abcd1234", message="dream: latest", timestamp="2026-04-04 12:00")
+    diff = (
+        "diff --git a/SOUL.md b/SOUL.md\n"
+        "--- a/SOUL.md\n"
+        "+++ b/SOUL.md\n"
+        "@@ -1 +1 @@\n"
+        "-old\n"
+        "+new\n"
+        "diff --git a/memory/MEMORY.md b/memory/MEMORY.md\n"
+        "--- a/memory/MEMORY.md\n"
+        "+++ b/memory/MEMORY.md\n"
+        "@@ -1 +1 @@\n"
+        "-old\n"
+        "+new\n"
+    )
+    git = _FakeGit(
+        diff_map={commit.sha: (commit, diff)},
+        revert_result="eeee9999",
+    )
+
+    out = await cmd_dream_restore(_make_ctx("/dream-restore abcd1234", git, args="abcd1234"))
+
+    assert "Restored Dream memory to the state before `abcd1234`." in out.content
+    assert "- New safety commit: `eeee9999`" in out.content
+    assert "- Restored files: `SOUL.md`, `memory/MEMORY.md`" in out.content
+    assert "Use `/dream-log eeee9999` to inspect the restore diff." in out.content

tests/config/test_config_migration.py

@@ -1,6 +1,18 @@
 import json
+import socket
+from unittest.mock import patch
 
 from nanobot.config.loader import load_config, save_config
+from nanobot.security.network import validate_url_target
+
+
+def _fake_resolve(host: str, results: list[str]):
+    """Return a getaddrinfo mock that maps the given host to fake IP results."""
+    def _resolver(hostname, port, family=0, type_=0):
+        if hostname == host:
+            return [(socket.AF_INET, socket.SOCK_STREAM, 0, "", (ip, 0)) for ip in results]
+        raise socket.gaierror(f"cannot resolve {hostname}")
+    return _resolver
 
 
 def test_load_config_keeps_max_tokens_and_ignores_legacy_memory_window(tmp_path) -> None:
@@ -126,3 +138,23 @@ def test_onboard_refresh_backfills_missing_channel_fields(tmp_path, monkeypatch)
     assert result.exit_code == 0
     saved = json.loads(config_path.read_text(encoding="utf-8"))
     assert saved["channels"]["qq"]["msgFormat"] == "plain"
+
+
+def test_load_config_resets_ssrf_whitelist_when_next_config_is_empty(tmp_path) -> None:
+    whitelisted = tmp_path / "whitelisted.json"
+    whitelisted.write_text(
+        json.dumps({"tools": {"ssrfWhitelist": ["100.64.0.0/10"]}}),
+        encoding="utf-8",
+    )
+    defaulted = tmp_path / "defaulted.json"
+    defaulted.write_text(json.dumps({}), encoding="utf-8")
+
+    load_config(whitelisted)
+    with patch("nanobot.security.network.socket.getaddrinfo", _fake_resolve("ts.local", ["100.100.1.1"])):
+        ok, err = validate_url_target("http://ts.local/api")
+        assert ok, err
+
+    load_config(defaulted)
+    with patch("nanobot.security.network.socket.getaddrinfo", _fake_resolve("ts.local", ["100.100.1.1"])):
+        ok, _ = validate_url_target("http://ts.local/api")
+        assert not ok

tests/config/test_dream_config.py

@@ -0,0 +1,48 @@
+from nanobot.config.schema import DreamConfig
+
+
+def test_dream_config_defaults_to_interval_hours() -> None:
+    cfg = DreamConfig()
+
+    assert cfg.interval_h == 2
+    assert cfg.cron is None
+
+
+def test_dream_config_builds_every_schedule_from_interval() -> None:
+    cfg = DreamConfig(interval_h=3)
+
+    schedule = cfg.build_schedule("UTC")
+
+    assert schedule.kind == "every"
+    assert schedule.every_ms == 3 * 3_600_000
+    assert schedule.expr is None
+
+
+def test_dream_config_honors_legacy_cron_override() -> None:
+    cfg = DreamConfig.model_validate({"cron": "0 */4 * * *"})
+
+    schedule = cfg.build_schedule("UTC")
+
+    assert schedule.kind == "cron"
+    assert schedule.expr == "0 */4 * * *"
+    assert schedule.tz == "UTC"
+    assert cfg.describe_schedule() == "cron 0 */4 * * * (legacy)"
+
+
+def test_dream_config_dump_uses_interval_h_and_hides_legacy_cron() -> None:
+    cfg = DreamConfig.model_validate({"intervalH": 5, "cron": "0 */4 * * *"})
+
+    dumped = cfg.model_dump(by_alias=True)
+
+    assert dumped["intervalH"] == 5
+    assert "cron" not in dumped
+
+
+def test_dream_config_uses_model_override_name_and_accepts_legacy_model() -> None:
+    cfg = DreamConfig.model_validate({"model": "openrouter/sonnet"})
+
+    dumped = cfg.model_dump(by_alias=True)
+
+    assert cfg.model_override == "openrouter/sonnet"
+    assert dumped["modelOverride"] == "openrouter/sonnet"
+    assert "model" not in dumped

tests/cron/test_cron_service.py

@@ -4,7 +4,7 @@ import json
 import pytest
 
 from nanobot.cron.service import CronService
-from nanobot.cron.types import CronSchedule
+from nanobot.cron.types import CronJob, CronPayload, CronSchedule
 
 
 def test_add_job_rejects_unknown_timezone(tmp_path) -> None:
@@ -141,3 +141,18 @@ async def test_running_service_honors_external_disable(tmp_path) -> None:
         assert called == []
     finally:
         service.stop()
+
+
+def test_remove_job_refuses_system_jobs(tmp_path) -> None:
+    service = CronService(tmp_path / "cron" / "jobs.json")
+    service.register_system_job(CronJob(
+        id="dream",
+        name="dream",
+        schedule=CronSchedule(kind="cron", expr="0 */2 * * *", tz="UTC"),
+        payload=CronPayload(kind="system_event"),
+    ))
+
+    result = service.remove_job("dream")
+
+    assert result == "protected"
+    assert service.get_job("dream") is not None

tests/cron/test_cron_tool_list.py

@@ -4,7 +4,7 @@ from datetime import datetime, timezone
 
 from nanobot.agent.tools.cron import CronTool
 from nanobot.cron.service import CronService
-from nanobot.cron.types import CronJobState, CronSchedule
+from nanobot.cron.types import CronJob, CronJobState, CronPayload, CronSchedule
 
 
 def _make_tool(tmp_path) -> CronTool:
@@ -262,6 +262,39 @@ def test_list_shows_next_run(tmp_path) -> None:
     assert "(UTC)" in result
 
 
+def test_list_includes_protected_dream_system_job_with_memory_purpose(tmp_path) -> None:
+    tool = _make_tool(tmp_path)
+    tool._cron.register_system_job(CronJob(
+        id="dream",
+        name="dream",
+        schedule=CronSchedule(kind="cron", expr="0 */2 * * *", tz="UTC"),
+        payload=CronPayload(kind="system_event"),
+    ))
+
+    result = tool._list_jobs()
+
+    assert "- dream (id: dream, cron: 0 */2 * * * (UTC))" in result
+    assert "Dream memory consolidation for long-term memory." in result
+    assert "cannot be removed" in result
+
+
+def test_remove_protected_dream_job_returns_clear_feedback(tmp_path) -> None:
+    tool = _make_tool(tmp_path)
+    tool._cron.register_system_job(CronJob(
+        id="dream",
+        name="dream",
+        schedule=CronSchedule(kind="cron", expr="0 */2 * * *", tz="UTC"),
+        payload=CronPayload(kind="system_event"),
+    ))
+
+    result = tool._remove_job("dream")
+
+    assert "Cannot remove job `dream`." in result
+    assert "Dream memory consolidation job for long-term memory" in result
+    assert "cannot be removed" in result
+    assert tool._cron.get_job("dream") is not None
+
+
 def test_add_cron_job_defaults_to_tool_timezone(tmp_path) -> None:
     tool = _make_tool_with_tz(tmp_path, "Asia/Shanghai")
     tool.set_context("telegram", "chat-1")
@@ -285,6 +318,28 @@ def test_add_at_job_uses_default_timezone_for_naive_datetime(tmp_path) -> None:
     assert job.schedule.at_ms == expected
 
 
+def test_add_job_delivers_by_default(tmp_path) -> None:
+    tool = _make_tool(tmp_path)
+    tool.set_context("telegram", "chat-1")
+
+    result = tool._add_job("Morning standup", 60, None, None, None)
+
+    assert result.startswith("Created job")
+    job = tool._cron.list_jobs()[0]
+    assert job.payload.deliver is True
+
+
+def test_add_job_can_disable_delivery(tmp_path) -> None:
+    tool = _make_tool(tmp_path)
+    tool.set_context("telegram", "chat-1")
+
+    result = tool._add_job("Background refresh", 60, None, None, None, deliver=False)
+
+    assert result.startswith("Created job")
+    job = tool._cron.list_jobs()[0]
+    assert job.payload.deliver is False
+
+
 def test_list_excludes_disabled_jobs(tmp_path) -> None:
     tool = _make_tool(tmp_path)
     job = tool._cron.add_job(

tests/providers/test_azure_openai_provider.py

@@ -1,6 +1,6 @@
-"""Test Azure OpenAI provider implementation (updated for model-based deployment names)."""
+"""Test Azure OpenAI provider (Responses API via OpenAI SDK)."""
 
-from unittest.mock import AsyncMock, Mock, patch
+from unittest.mock import AsyncMock, MagicMock
 
 import pytest
 
@@ -8,392 +8,401 @@ from nanobot.providers.azure_openai_provider import AzureOpenAIProvider
 from nanobot.providers.base import LLMResponse
 
 
-def test_azure_openai_provider_init():
-    """Test AzureOpenAIProvider initialization without deployment_name."""
+# ---------------------------------------------------------------------------
+# Init & validation
+# ---------------------------------------------------------------------------
+
+
+def test_init_creates_sdk_client():
+    """Provider creates an AsyncOpenAI client with correct base_url."""
     provider = AzureOpenAIProvider(
         api_key="test-key",
         api_base="https://test-resource.openai.azure.com",
         default_model="gpt-4o-deployment",
     )
-    
     assert provider.api_key == "test-key"
     assert provider.api_base == "https://test-resource.openai.azure.com/"
     assert provider.default_model == "gpt-4o-deployment"
-    assert provider.api_version == "2024-10-21"
+    # SDK client base_url ends with /openai/v1/
+    assert str(provider._client.base_url).rstrip("/").endswith("/openai/v1")
 
 
-def test_azure_openai_provider_init_validation():
-    """Test AzureOpenAIProvider initialization validation."""
-    # Missing api_key
+def test_init_base_url_no_trailing_slash():
+    """Trailing slashes are normalised before building base_url."""
+    provider = AzureOpenAIProvider(
+        api_key="k", api_base="https://res.openai.azure.com",
+    )
+    assert str(provider._client.base_url).rstrip("/").endswith("/openai/v1")
+
+
+def test_init_base_url_with_trailing_slash():
+    provider = AzureOpenAIProvider(
+        api_key="k", api_base="https://res.openai.azure.com/",
+    )
+    assert str(provider._client.base_url).rstrip("/").endswith("/openai/v1")
+
+
+def test_init_validation_missing_key():
     with pytest.raises(ValueError, match="Azure OpenAI api_key is required"):
         AzureOpenAIProvider(api_key="", api_base="https://test.com")
-    
-    # Missing api_base
+
+
+def test_init_validation_missing_base():
     with pytest.raises(ValueError, match="Azure OpenAI api_base is required"):
         AzureOpenAIProvider(api_key="test", api_base="")
 
 
-def test_build_chat_url():
-    """Test Azure OpenAI URL building with different deployment names."""
+def test_no_api_version_in_base_url():
+    """The /openai/v1/ path should NOT contain an api-version query param."""
+    provider = AzureOpenAIProvider(api_key="k", api_base="https://res.openai.azure.com")
+    base = str(provider._client.base_url)
+    assert "api-version" not in base
+
+
+# ---------------------------------------------------------------------------
+# _supports_temperature
+# ---------------------------------------------------------------------------
+
+
+def test_supports_temperature_standard_model():
+    assert AzureOpenAIProvider._supports_temperature("gpt-4o") is True
+
+
+def test_supports_temperature_reasoning_model():
+    assert AzureOpenAIProvider._supports_temperature("o3-mini") is False
+    assert AzureOpenAIProvider._supports_temperature("gpt-5-chat") is False
+    assert AzureOpenAIProvider._supports_temperature("o4-mini") is False
+
+
+def test_supports_temperature_with_reasoning_effort():
+    assert AzureOpenAIProvider._supports_temperature("gpt-4o", reasoning_effort="medium") is False
+
+
+# ---------------------------------------------------------------------------
+# _build_body — Responses API body construction
+# ---------------------------------------------------------------------------
+
+
+def test_build_body_basic():
     provider = AzureOpenAIProvider(
-        api_key="test-key",
-        api_base="https://test-resource.openai.azure.com",
-        default_model="gpt-4o",
+        api_key="k", api_base="https://res.openai.azure.com", default_model="gpt-4o",
     )
-    
-    # Test various deployment names
-    test_cases = [
-        ("gpt-4o-deployment", "https://test-resource.openai.azure.com/openai/deployments/gpt-4o-deployment/chat/completions?api-version=2024-10-21"),
-        ("gpt-35-turbo", "https://test-resource.openai.azure.com/openai/deployments/gpt-35-turbo/chat/completions?api-version=2024-10-21"),
-        ("custom-model", "https://test-resource.openai.azure.com/openai/deployments/custom-model/chat/completions?api-version=2024-10-21"),
-    ]
-    
-    for deployment_name, expected_url in test_cases:
-        url = provider._build_chat_url(deployment_name)
-        assert url == expected_url
+    messages = [{"role": "system", "content": "You are helpful."}, {"role": "user", "content": "Hi"}]
+    body = provider._build_body(messages, None, None, 4096, 0.7, None, None)
 
-
-def test_build_chat_url_api_base_without_slash():
-    """Test URL building when api_base doesn't end with slash."""
-    provider = AzureOpenAIProvider(
-        api_key="test-key",
-        api_base="https://test-resource.openai.azure.com",  # No trailing slash
-        default_model="gpt-4o",
+    assert body["model"] == "gpt-4o"
+    assert body["instructions"] == "You are helpful."
+    assert body["temperature"] == 0.7
+    assert body["max_output_tokens"] == 4096
+    assert body["store"] is False
+    assert "reasoning" not in body
+    # input should contain the converted user message only (system extracted)
+    assert any(
+        item.get("role") == "user"
+        for item in body["input"]
     )
-    
-    url = provider._build_chat_url("test-deployment")
-    expected = "https://test-resource.openai.azure.com/openai/deployments/test-deployment/chat/completions?api-version=2024-10-21"
-    assert url == expected
 
 
-def test_build_headers():
-    """Test Azure OpenAI header building with api-key authentication."""
-    provider = AzureOpenAIProvider(
-        api_key="test-api-key-123",
-        api_base="https://test-resource.openai.azure.com",
-        default_model="gpt-4o",
-    )
-    
-    headers = provider._build_headers()
-    assert headers["Content-Type"] == "application/json"
-    assert headers["api-key"] == "test-api-key-123"  # Azure OpenAI specific header
-    assert "x-session-affinity" in headers
+def test_build_body_max_tokens_minimum():
+    """max_output_tokens should never be less than 1."""
+    provider = AzureOpenAIProvider(api_key="k", api_base="https://r.com", default_model="gpt-4o")
+    body = provider._build_body([{"role": "user", "content": "x"}], None, None, 0, 0.7, None, None)
+    assert body["max_output_tokens"] == 1
 
 
-def test_prepare_request_payload():
-    """Test request payload preparation with Azure OpenAI 2024-10-21 compliance."""
-    provider = AzureOpenAIProvider(
-        api_key="test-key",
-        api_base="https://test-resource.openai.azure.com",
-        default_model="gpt-4o",
-    )
-    
-    messages = [{"role": "user", "content": "Hello"}]
-    payload = provider._prepare_request_payload("gpt-4o", messages, max_tokens=1500, temperature=0.8)
-    
-    assert payload["messages"] == messages
-    assert payload["max_completion_tokens"] == 1500  # Azure API 2024-10-21 uses max_completion_tokens
-    assert payload["temperature"] == 0.8
-    assert "tools" not in payload
-    
-    # Test with tools
+def test_build_body_with_tools():
+    provider = AzureOpenAIProvider(api_key="k", api_base="https://r.com", default_model="gpt-4o")
     tools = [{"type": "function", "function": {"name": "get_weather", "parameters": {}}}]
-    payload_with_tools = provider._prepare_request_payload("gpt-4o", messages, tools=tools)
-    assert payload_with_tools["tools"] == tools
-    assert payload_with_tools["tool_choice"] == "auto"
-    
-    # Test with reasoning_effort
-    payload_with_reasoning = provider._prepare_request_payload(
-        "gpt-5-chat", messages, reasoning_effort="medium"
+    body = provider._build_body(
+        [{"role": "user", "content": "weather?"}], tools, None, 4096, 0.7, None, None,
     )
-    assert payload_with_reasoning["reasoning_effort"] == "medium"
-    assert "temperature" not in payload_with_reasoning
+    assert body["tools"] == [{"type": "function", "name": "get_weather", "description": "", "parameters": {}}]
+    assert body["tool_choice"] == "auto"
 
 
-def test_prepare_request_payload_sanitizes_messages():
-    """Test Azure payload strips non-standard message keys before sending."""
-    provider = AzureOpenAIProvider(
-        api_key="test-key",
-        api_base="https://test-resource.openai.azure.com",
-        default_model="gpt-4o",
+def test_build_body_with_reasoning():
+    provider = AzureOpenAIProvider(api_key="k", api_base="https://r.com", default_model="gpt-5-chat")
+    body = provider._build_body(
+        [{"role": "user", "content": "think"}], None, "gpt-5-chat", 4096, 0.7, "medium", None,
     )
+    assert body["reasoning"] == {"effort": "medium"}
+    assert "reasoning.encrypted_content" in body.get("include", [])
+    # temperature omitted for reasoning models
+    assert "temperature" not in body
 
-    messages = [
-        {
-            "role": "assistant",
-            "tool_calls": [{"id": "call_123", "type": "function", "function": {"name": "x"}}],
-            "reasoning_content": "hidden chain-of-thought",
-        },
-        {
-            "role": "tool",
-            "tool_call_id": "call_123",
-            "name": "x",
-            "content": "ok",
-            "extra_field": "should be removed",
-        },
-    ]
 
-    payload = provider._prepare_request_payload("gpt-4o", messages)
+def test_build_body_image_conversion():
+    """image_url content blocks should be converted to input_image."""
+    provider = AzureOpenAIProvider(api_key="k", api_base="https://r.com", default_model="gpt-4o")
+    messages = [{
+        "role": "user",
+        "content": [
+            {"type": "text", "text": "What's in this image?"},
+            {"type": "image_url", "image_url": {"url": "https://example.com/img.png"}},
+        ],
+    }]
+    body = provider._build_body(messages, None, None, 4096, 0.7, None, None)
+    user_item = body["input"][0]
+    content_types = [b["type"] for b in user_item["content"]]
+    assert "input_text" in content_types
+    assert "input_image" in content_types
+    image_block = next(b for b in user_item["content"] if b["type"] == "input_image")
+    assert image_block["image_url"] == "https://example.com/img.png"
 
-    assert payload["messages"] == [
-        {
-            "role": "assistant",
-            "content": None,
-            "tool_calls": [{"id": "call_123", "type": "function", "function": {"name": "x"}}],
+
+def test_build_body_sanitizes_single_dict_content_block():
+    """Single content dicts should be preserved via shared message sanitization."""
+    provider = AzureOpenAIProvider(api_key="k", api_base="https://r.com", default_model="gpt-4o")
+    messages = [{
+        "role": "user",
+        "content": {"type": "text", "text": "Hi from dict content"},
+    }]
+
+    body = provider._build_body(messages, None, None, 4096, 0.7, None, None)
+
+    assert body["input"][0]["content"] == [{"type": "input_text", "text": "Hi from dict content"}]
+
+
+# ---------------------------------------------------------------------------
+# chat() — non-streaming
+# ---------------------------------------------------------------------------
+
+
+def _make_sdk_response(
+    content="Hello!", tool_calls=None, status="completed",
+    usage=None,
+):
+    """Build a mock that quacks like an openai Response object."""
+    resp = MagicMock()
+    resp.model_dump = MagicMock(return_value={
+        "output": [
+            {"type": "message", "role": "assistant", "content": [{"type": "output_text", "text": content}]},
+            *([{
+                "type": "function_call",
+                "call_id": tc["call_id"], "id": tc["id"],
+                "name": tc["name"], "arguments": tc["arguments"],
+            } for tc in (tool_calls or [])]),
+        ],
+        "status": status,
+        "usage": {
+            "input_tokens": (usage or {}).get("input_tokens", 10),
+            "output_tokens": (usage or {}).get("output_tokens", 5),
+            "total_tokens": (usage or {}).get("total_tokens", 15),
         },
-        {
-            "role": "tool",
-            "tool_call_id": "call_123",
-            "name": "x",
-            "content": "ok",
-        },
-    ]
+    })
+    return resp
 
 
 @pytest.mark.asyncio
 async def test_chat_success():
-    """Test successful chat request using model as deployment name."""
     provider = AzureOpenAIProvider(
-        api_key="test-key",
-        api_base="https://test-resource.openai.azure.com",
-        default_model="gpt-4o-deployment",
+        api_key="test-key", api_base="https://test.openai.azure.com", default_model="gpt-4o",
     )
-    
-    # Mock response data
-    mock_response_data = {
-        "choices": [{
-            "message": {
-                "content": "Hello! How can I help you today?",
-                "role": "assistant"
-            },
-            "finish_reason": "stop"
-        }],
-        "usage": {
-            "prompt_tokens": 12,
-            "completion_tokens": 18,
-            "total_tokens": 30
-        }
-    }
-    
-    with patch("httpx.AsyncClient") as mock_client:
-        mock_response = AsyncMock()
-        mock_response.status_code = 200
-        mock_response.json = Mock(return_value=mock_response_data)
-        
-        mock_context = AsyncMock()
-        mock_context.post = AsyncMock(return_value=mock_response)
-        mock_client.return_value.__aenter__.return_value = mock_context
-        
-        # Test with specific model (deployment name)
-        messages = [{"role": "user", "content": "Hello"}]
-        result = await provider.chat(messages, model="custom-deployment")
-        
-        assert isinstance(result, LLMResponse)
-        assert result.content == "Hello! How can I help you today?"
-        assert result.finish_reason == "stop"
-        assert result.usage["prompt_tokens"] == 12
-        assert result.usage["completion_tokens"] == 18
-        assert result.usage["total_tokens"] == 30
-        
-        # Verify URL was built with the provided model as deployment name
-        call_args = mock_context.post.call_args
-        expected_url = "https://test-resource.openai.azure.com/openai/deployments/custom-deployment/chat/completions?api-version=2024-10-21"
-        assert call_args[0][0] == expected_url
+    mock_resp = _make_sdk_response(content="Hello!")
+    provider._client.responses = MagicMock()
+    provider._client.responses.create = AsyncMock(return_value=mock_resp)
+
+    result = await provider.chat([{"role": "user", "content": "Hi"}])
+
+    assert isinstance(result, LLMResponse)
+    assert result.content == "Hello!"
+    assert result.finish_reason == "stop"
+    assert result.usage["prompt_tokens"] == 10
 
 
 @pytest.mark.asyncio
-async def test_chat_uses_default_model_when_no_model_provided():
-    """Test that chat uses default_model when no model is specified."""
+async def test_chat_uses_default_model():
     provider = AzureOpenAIProvider(
-        api_key="test-key",
-        api_base="https://test-resource.openai.azure.com",
-        default_model="default-deployment",
+        api_key="k", api_base="https://test.openai.azure.com", default_model="my-deployment",
     )
-    
-    mock_response_data = {
-        "choices": [{
-            "message": {"content": "Response", "role": "assistant"},
-            "finish_reason": "stop"
-        }],
-        "usage": {"prompt_tokens": 5, "completion_tokens": 5, "total_tokens": 10}
-    }
-    
-    with patch("httpx.AsyncClient") as mock_client:
-        mock_response = AsyncMock()
-        mock_response.status_code = 200
-        mock_response.json = Mock(return_value=mock_response_data)
-        
-        mock_context = AsyncMock()
-        mock_context.post = AsyncMock(return_value=mock_response)
-        mock_client.return_value.__aenter__.return_value = mock_context
-        
-        messages = [{"role": "user", "content": "Test"}]
-        await provider.chat(messages)  # No model specified
-        
-        # Verify URL was built with default model as deployment name
-        call_args = mock_context.post.call_args
-        expected_url = "https://test-resource.openai.azure.com/openai/deployments/default-deployment/chat/completions?api-version=2024-10-21"
-        assert call_args[0][0] == expected_url
+    mock_resp = _make_sdk_response(content="ok")
+    provider._client.responses = MagicMock()
+    provider._client.responses.create = AsyncMock(return_value=mock_resp)
+
+    await provider.chat([{"role": "user", "content": "test"}])
+
+    call_kwargs = provider._client.responses.create.call_args[1]
+    assert call_kwargs["model"] == "my-deployment"
+
+
+@pytest.mark.asyncio
+async def test_chat_custom_model():
+    provider = AzureOpenAIProvider(
+        api_key="k", api_base="https://test.openai.azure.com", default_model="gpt-4o",
+    )
+    mock_resp = _make_sdk_response(content="ok")
+    provider._client.responses = MagicMock()
+    provider._client.responses.create = AsyncMock(return_value=mock_resp)
+
+    await provider.chat([{"role": "user", "content": "test"}], model="custom-deploy")
+
+    call_kwargs = provider._client.responses.create.call_args[1]
+    assert call_kwargs["model"] == "custom-deploy"
 
 
 @pytest.mark.asyncio
 async def test_chat_with_tool_calls():
-    """Test chat request with tool calls in response."""
     provider = AzureOpenAIProvider(
-        api_key="test-key",
-        api_base="https://test-resource.openai.azure.com",
-        default_model="gpt-4o",
+        api_key="k", api_base="https://test.openai.azure.com", default_model="gpt-4o",
     )
-    
-    # Mock response with tool calls
-    mock_response_data = {
-        "choices": [{
-            "message": {
-                "content": None,
-                "role": "assistant",
-                "tool_calls": [{
-                    "id": "call_12345",
-                    "function": {
-                        "name": "get_weather",
-                        "arguments": '{"location": "San Francisco"}'
-                    }
-                }]
-            },
-            "finish_reason": "tool_calls"
+    mock_resp = _make_sdk_response(
+        content=None,
+        tool_calls=[{
+            "call_id": "call_123", "id": "fc_1",
+            "name": "get_weather", "arguments": '{"location": "SF"}',
         }],
-        "usage": {
-            "prompt_tokens": 20,
-            "completion_tokens": 15,
-            "total_tokens": 35
-        }
-    }
-    
-    with patch("httpx.AsyncClient") as mock_client:
-        mock_response = AsyncMock()
-        mock_response.status_code = 200
-        mock_response.json = Mock(return_value=mock_response_data)
-        
-        mock_context = AsyncMock()
-        mock_context.post = AsyncMock(return_value=mock_response)
-        mock_client.return_value.__aenter__.return_value = mock_context
-        
-        messages = [{"role": "user", "content": "What's the weather?"}]
-        tools = [{"type": "function", "function": {"name": "get_weather", "parameters": {}}}]
-        result = await provider.chat(messages, tools=tools, model="weather-model")
-        
-        assert isinstance(result, LLMResponse)
-        assert result.content is None
-        assert result.finish_reason == "tool_calls"
-        assert len(result.tool_calls) == 1
-        assert result.tool_calls[0].name == "get_weather"
-        assert result.tool_calls[0].arguments == {"location": "San Francisco"}
+    )
+    provider._client.responses = MagicMock()
+    provider._client.responses.create = AsyncMock(return_value=mock_resp)
+
+    result = await provider.chat(
+        [{"role": "user", "content": "Weather?"}],
+        tools=[{"type": "function", "function": {"name": "get_weather", "parameters": {}}}],
+    )
+
+    assert len(result.tool_calls) == 1
+    assert result.tool_calls[0].name == "get_weather"
+    assert result.tool_calls[0].arguments == {"location": "SF"}
 
 
 @pytest.mark.asyncio
-async def test_chat_api_error():
-    """Test chat request API error handling."""
+async def test_chat_error_handling():
     provider = AzureOpenAIProvider(
-        api_key="test-key",
-        api_base="https://test-resource.openai.azure.com",
-        default_model="gpt-4o",
+        api_key="k", api_base="https://test.openai.azure.com", default_model="gpt-4o",
     )
-    
-    with patch("httpx.AsyncClient") as mock_client:
-        mock_response = AsyncMock()
-        mock_response.status_code = 401
-        mock_response.text = "Invalid authentication credentials"
-        
-        mock_context = AsyncMock()
-        mock_context.post = AsyncMock(return_value=mock_response)
-        mock_client.return_value.__aenter__.return_value = mock_context
-        
-        messages = [{"role": "user", "content": "Hello"}]
-        result = await provider.chat(messages)
-        
-        assert isinstance(result, LLMResponse)
-        assert "Azure OpenAI API Error 401" in result.content
-        assert "Invalid authentication credentials" in result.content
-        assert result.finish_reason == "error"
+    provider._client.responses = MagicMock()
+    provider._client.responses.create = AsyncMock(side_effect=Exception("Connection failed"))
 
+    result = await provider.chat([{"role": "user", "content": "Hi"}])
 
-@pytest.mark.asyncio
-async def test_chat_connection_error():
-    """Test chat request connection error handling."""
-    provider = AzureOpenAIProvider(
-        api_key="test-key",
-        api_base="https://test-resource.openai.azure.com",
-        default_model="gpt-4o",
-    )
-    
-    with patch("httpx.AsyncClient") as mock_client:
-        mock_context = AsyncMock()
-        mock_context.post = AsyncMock(side_effect=Exception("Connection failed"))
-        mock_client.return_value.__aenter__.return_value = mock_context
-        
-        messages = [{"role": "user", "content": "Hello"}]
-        result = await provider.chat(messages)
-        
-        assert isinstance(result, LLMResponse)
-        assert "Error calling Azure OpenAI: Exception('Connection failed')" in result.content
-        assert result.finish_reason == "error"
-
-
-def test_parse_response_malformed():
-    """Test response parsing with malformed data."""
-    provider = AzureOpenAIProvider(
-        api_key="test-key",
-        api_base="https://test-resource.openai.azure.com",
-        default_model="gpt-4o",
-    )
-    
-    # Test with missing choices
-    malformed_response = {"usage": {"prompt_tokens": 10}}
-    result = provider._parse_response(malformed_response)
-    
     assert isinstance(result, LLMResponse)
-    assert "Error parsing Azure OpenAI response" in result.content
+    assert "Connection failed" in result.content
     assert result.finish_reason == "error"
 
 
+@pytest.mark.asyncio
+async def test_chat_reasoning_param_format():
+    """reasoning_effort should be sent as reasoning={effort: ...} not a flat string."""
+    provider = AzureOpenAIProvider(
+        api_key="k", api_base="https://test.openai.azure.com", default_model="gpt-5-chat",
+    )
+    mock_resp = _make_sdk_response(content="thought")
+    provider._client.responses = MagicMock()
+    provider._client.responses.create = AsyncMock(return_value=mock_resp)
+
+    await provider.chat(
+        [{"role": "user", "content": "think"}], reasoning_effort="medium",
+    )
+
+    call_kwargs = provider._client.responses.create.call_args[1]
+    assert call_kwargs["reasoning"] == {"effort": "medium"}
+    assert "reasoning_effort" not in call_kwargs
+
+
+# ---------------------------------------------------------------------------
+# chat_stream()
+# ---------------------------------------------------------------------------
+
+
+@pytest.mark.asyncio
+async def test_chat_stream_success():
+    """Streaming should call on_content_delta and return combined response."""
+    provider = AzureOpenAIProvider(
+        api_key="test-key", api_base="https://test.openai.azure.com", default_model="gpt-4o",
+    )
+
+    # Build mock SDK stream events
+    events = []
+    ev1 = MagicMock(type="response.output_text.delta", delta="Hello")
+    ev2 = MagicMock(type="response.output_text.delta", delta=" world")
+    resp_obj = MagicMock(status="completed")
+    ev3 = MagicMock(type="response.completed", response=resp_obj)
+    events = [ev1, ev2, ev3]
+
+    async def mock_stream():
+        for e in events:
+            yield e
+
+    provider._client.responses = MagicMock()
+    provider._client.responses.create = AsyncMock(return_value=mock_stream())
+
+    deltas: list[str] = []
+
+    async def on_delta(text: str) -> None:
+        deltas.append(text)
+
+    result = await provider.chat_stream(
+        [{"role": "user", "content": "Hi"}], on_content_delta=on_delta,
+    )
+
+    assert result.content == "Hello world"
+    assert result.finish_reason == "stop"
+    assert deltas == ["Hello", " world"]
+
+
+@pytest.mark.asyncio
+async def test_chat_stream_with_tool_calls():
+    """Streaming tool calls should be accumulated correctly."""
+    provider = AzureOpenAIProvider(
+        api_key="k", api_base="https://test.openai.azure.com", default_model="gpt-4o",
+    )
+
+    item_added = MagicMock(type="function_call", call_id="call_1", id="fc_1", arguments="")
+    item_added.name = "get_weather"
+    ev_added = MagicMock(type="response.output_item.added", item=item_added)
+    ev_args_delta = MagicMock(type="response.function_call_arguments.delta", call_id="call_1", delta='{"loc')
+    ev_args_done = MagicMock(
+        type="response.function_call_arguments.done",
+        call_id="call_1", arguments='{"location":"SF"}',
+    )
+    item_done = MagicMock(
+        type="function_call", call_id="call_1", id="fc_1",
+        arguments='{"location":"SF"}',
+    )
+    item_done.name = "get_weather"
+    ev_item_done = MagicMock(type="response.output_item.done", item=item_done)
+    resp_obj = MagicMock(status="completed")
+    ev_completed = MagicMock(type="response.completed", response=resp_obj)
+
+    async def mock_stream():
+        for e in [ev_added, ev_args_delta, ev_args_done, ev_item_done, ev_completed]:
+            yield e
+
+    provider._client.responses = MagicMock()
+    provider._client.responses.create = AsyncMock(return_value=mock_stream())
+
+    result = await provider.chat_stream(
+        [{"role": "user", "content": "weather?"}],
+        tools=[{"type": "function", "function": {"name": "get_weather", "parameters": {}}}],
+    )
+
+    assert len(result.tool_calls) == 1
+    assert result.tool_calls[0].name == "get_weather"
+    assert result.tool_calls[0].arguments == {"location": "SF"}
+
+
+@pytest.mark.asyncio
+async def test_chat_stream_error():
+    """Streaming should return error when SDK raises."""
+    provider = AzureOpenAIProvider(
+        api_key="k", api_base="https://test.openai.azure.com", default_model="gpt-4o",
+    )
+    provider._client.responses = MagicMock()
+    provider._client.responses.create = AsyncMock(side_effect=Exception("Connection failed"))
+
+    result = await provider.chat_stream([{"role": "user", "content": "Hi"}])
+
+    assert "Connection failed" in result.content
+    assert result.finish_reason == "error"
+
+
+# ---------------------------------------------------------------------------
+# get_default_model
+# ---------------------------------------------------------------------------
+
+
 def test_get_default_model():
-    """Test get_default_model method."""
     provider = AzureOpenAIProvider(
-        api_key="test-key",
-        api_base="https://test-resource.openai.azure.com",
-        default_model="my-custom-deployment",
+        api_key="k", api_base="https://r.com", default_model="my-deploy",
     )
-    
-    assert provider.get_default_model() == "my-custom-deployment"
-
-
-if __name__ == "__main__":
-    # Run basic tests
-    print("Running basic Azure OpenAI provider tests...")
-    
-    # Test initialization
-    provider = AzureOpenAIProvider(
-        api_key="test-key",
-        api_base="https://test-resource.openai.azure.com",
-        default_model="gpt-4o-deployment",
-    )
-    print("✅ Provider initialization successful")
-    
-    # Test URL building
-    url = provider._build_chat_url("my-deployment")
-    expected = "https://test-resource.openai.azure.com/openai/deployments/my-deployment/chat/completions?api-version=2024-10-21"
-    assert url == expected
-    print("✅ URL building works correctly")
-    
-    # Test headers
-    headers = provider._build_headers()
-    assert headers["api-key"] == "test-key"
-    assert headers["Content-Type"] == "application/json"
-    print("✅ Header building works correctly")
-    
-    # Test payload preparation
-    messages = [{"role": "user", "content": "Test"}]
-    payload = provider._prepare_request_payload("gpt-4o-deployment", messages, max_tokens=1000)
-    assert payload["max_completion_tokens"] == 1000  # Azure 2024-10-21 format
-    print("✅ Payload preparation works correctly")
-    
-    print("✅ All basic tests passed! Updated test file is working correctly.")
+    assert provider.get_default_model() == "my-deploy"

tests/providers/test_cached_tokens.py

@@ -0,0 +1,233 @@
+"""Tests for cached token extraction from OpenAI-compatible providers."""
+
+from __future__ import annotations
+
+from nanobot.providers.openai_compat_provider import OpenAICompatProvider
+
+
+class FakeUsage:
+    """Mimics an OpenAI SDK usage object (has attributes, not dict keys)."""
+    def __init__(self, **kwargs):
+        for k, v in kwargs.items():
+            setattr(self, k, v)
+
+
+class FakePromptDetails:
+    """Mimics prompt_tokens_details sub-object."""
+    def __init__(self, cached_tokens=0):
+        self.cached_tokens = cached_tokens
+
+
+class _FakeSpec:
+    supports_prompt_caching = False
+    model_id_prefix = None
+    strip_model_prefix = False
+    max_completion_tokens = False
+    reasoning_effort = None
+
+
+def _provider():
+    from unittest.mock import MagicMock
+    p = OpenAICompatProvider.__new__(OpenAICompatProvider)
+    p.client = MagicMock()
+    p.spec = _FakeSpec()
+    return p
+
+
+# Minimal valid choice so _parse reaches _extract_usage.
+_DICT_CHOICE = {"message": {"content": "Hello"}}
+
+class _FakeMessage:
+    content = "Hello"
+    tool_calls = None
+
+
+class _FakeChoice:
+    message = _FakeMessage()
+    finish_reason = "stop"
+
+
+# --- dict-based response (raw JSON / mapping) ---
+
+def test_extract_usage_openai_cached_tokens_dict():
+    """prompt_tokens_details.cached_tokens from a dict response."""
+    p = _provider()
+    response = {
+        "choices": [_DICT_CHOICE],
+        "usage": {
+            "prompt_tokens": 2000,
+            "completion_tokens": 300,
+            "total_tokens": 2300,
+            "prompt_tokens_details": {"cached_tokens": 1200},
+        }
+    }
+    result = p._parse(response)
+    assert result.usage["cached_tokens"] == 1200
+    assert result.usage["prompt_tokens"] == 2000
+
+
+def test_extract_usage_deepseek_cached_tokens_dict():
+    """prompt_cache_hit_tokens from a DeepSeek dict response."""
+    p = _provider()
+    response = {
+        "choices": [_DICT_CHOICE],
+        "usage": {
+            "prompt_tokens": 1500,
+            "completion_tokens": 200,
+            "total_tokens": 1700,
+            "prompt_cache_hit_tokens": 1200,
+            "prompt_cache_miss_tokens": 300,
+        }
+    }
+    result = p._parse(response)
+    assert result.usage["cached_tokens"] == 1200
+
+
+def test_extract_usage_no_cached_tokens_dict():
+    """Response without any cache fields -> no cached_tokens key."""
+    p = _provider()
+    response = {
+        "choices": [_DICT_CHOICE],
+        "usage": {
+            "prompt_tokens": 1000,
+            "completion_tokens": 200,
+            "total_tokens": 1200,
+        }
+    }
+    result = p._parse(response)
+    assert "cached_tokens" not in result.usage
+
+
+def test_extract_usage_openai_cached_zero_dict():
+    """cached_tokens=0 should NOT be included (same as existing fields)."""
+    p = _provider()
+    response = {
+        "choices": [_DICT_CHOICE],
+        "usage": {
+            "prompt_tokens": 2000,
+            "completion_tokens": 300,
+            "total_tokens": 2300,
+            "prompt_tokens_details": {"cached_tokens": 0},
+        }
+    }
+    result = p._parse(response)
+    assert "cached_tokens" not in result.usage
+
+
+# --- object-based response (OpenAI SDK Pydantic model) ---
+
+def test_extract_usage_openai_cached_tokens_obj():
+    """prompt_tokens_details.cached_tokens from an SDK object response."""
+    p = _provider()
+    usage_obj = FakeUsage(
+        prompt_tokens=2000,
+        completion_tokens=300,
+        total_tokens=2300,
+        prompt_tokens_details=FakePromptDetails(cached_tokens=1200),
+    )
+    response = FakeUsage(choices=[_FakeChoice()], usage=usage_obj)
+    result = p._parse(response)
+    assert result.usage["cached_tokens"] == 1200
+
+
+def test_extract_usage_deepseek_cached_tokens_obj():
+    """prompt_cache_hit_tokens from a DeepSeek SDK object response."""
+    p = _provider()
+    usage_obj = FakeUsage(
+        prompt_tokens=1500,
+        completion_tokens=200,
+        total_tokens=1700,
+        prompt_cache_hit_tokens=1200,
+    )
+    response = FakeUsage(choices=[_FakeChoice()], usage=usage_obj)
+    result = p._parse(response)
+    assert result.usage["cached_tokens"] == 1200
+
+
+def test_extract_usage_stepfun_top_level_cached_tokens_dict():
+    """StepFun/Moonshot: usage.cached_tokens at top level (not nested)."""
+    p = _provider()
+    response = {
+        "choices": [_DICT_CHOICE],
+        "usage": {
+            "prompt_tokens": 591,
+            "completion_tokens": 120,
+            "total_tokens": 711,
+            "cached_tokens": 512,
+        }
+    }
+    result = p._parse(response)
+    assert result.usage["cached_tokens"] == 512
+
+
+def test_extract_usage_stepfun_top_level_cached_tokens_obj():
+    """StepFun/Moonshot: usage.cached_tokens as SDK object attribute."""
+    p = _provider()
+    usage_obj = FakeUsage(
+        prompt_tokens=591,
+        completion_tokens=120,
+        total_tokens=711,
+        cached_tokens=512,
+    )
+    response = FakeUsage(choices=[_FakeChoice()], usage=usage_obj)
+    result = p._parse(response)
+    assert result.usage["cached_tokens"] == 512
+
+
+def test_extract_usage_priority_nested_over_top_level_dict():
+    """When both nested and top-level cached_tokens exist, nested wins."""
+    p = _provider()
+    response = {
+        "choices": [_DICT_CHOICE],
+        "usage": {
+            "prompt_tokens": 2000,
+            "completion_tokens": 300,
+            "total_tokens": 2300,
+            "prompt_tokens_details": {"cached_tokens": 100},
+            "cached_tokens": 500,
+        }
+    }
+    result = p._parse(response)
+    assert result.usage["cached_tokens"] == 100
+
+
+def test_anthropic_maps_cache_fields_to_cached_tokens():
+    """Anthropic's cache_read_input_tokens should map to cached_tokens."""
+    from nanobot.providers.anthropic_provider import AnthropicProvider
+
+    usage_obj = FakeUsage(
+        input_tokens=800,
+        output_tokens=200,
+        cache_creation_input_tokens=300,
+        cache_read_input_tokens=1200,
+    )
+    content_block = FakeUsage(type="text", text="hello")
+    response = FakeUsage(
+        id="msg_1",
+        type="message",
+        stop_reason="end_turn",
+        content=[content_block],
+        usage=usage_obj,
+    )
+    result = AnthropicProvider._parse_response(response)
+    assert result.usage["cached_tokens"] == 1200
+    assert result.usage["prompt_tokens"] == 2300
+    assert result.usage["total_tokens"] == 2500
+    assert result.usage["cache_creation_input_tokens"] == 300
+
+
+def test_anthropic_no_cache_fields():
+    """Anthropic response without cache fields should not have cached_tokens."""
+    from nanobot.providers.anthropic_provider import AnthropicProvider
+
+    usage_obj = FakeUsage(input_tokens=800, output_tokens=200)
+    content_block = FakeUsage(type="text", text="hello")
+    response = FakeUsage(
+        id="msg_1",
+        type="message",
+        stop_reason="end_turn",
+        content=[content_block],
+        usage=usage_obj,
+    )
+    result = AnthropicProvider._parse_response(response)
+    assert "cached_tokens" not in result.usage

tests/providers/test_litellm_kwargs.py

@@ -8,6 +8,7 @@ Validates that:
 
 from __future__ import annotations
 
+import asyncio
 from types import SimpleNamespace
 from unittest.mock import AsyncMock, patch
 
@@ -53,6 +54,15 @@ def _fake_tool_call_response() -> SimpleNamespace:
     return SimpleNamespace(choices=[choice], usage=usage)
 
 
+class _StalledStream:
+    def __aiter__(self):
+        return self
+
+    async def __anext__(self):
+        await asyncio.sleep(3600)
+        raise StopAsyncIteration
+
+
 def test_openrouter_spec_is_gateway() -> None:
     spec = find_by_name("openrouter")
     assert spec is not None
@@ -214,3 +224,86 @@ def test_openai_model_passthrough() -> None:
             spec=spec,
         )
     assert provider.get_default_model() == "gpt-4o"
+
+
+def test_openai_compat_supports_temperature_matches_reasoning_model_rules() -> None:
+    assert OpenAICompatProvider._supports_temperature("gpt-4o") is True
+    assert OpenAICompatProvider._supports_temperature("gpt-5-chat") is False
+    assert OpenAICompatProvider._supports_temperature("o3-mini") is False
+    assert OpenAICompatProvider._supports_temperature("gpt-4o", reasoning_effort="medium") is False
+
+
+def test_openai_compat_build_kwargs_uses_gpt5_safe_parameters() -> None:
+    spec = find_by_name("openai")
+    with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI"):
+        provider = OpenAICompatProvider(
+            api_key="sk-test-key",
+            default_model="gpt-5-chat",
+            spec=spec,
+        )
+
+    kwargs = provider._build_kwargs(
+        messages=[{"role": "user", "content": "hello"}],
+        tools=None,
+        model="gpt-5-chat",
+        max_tokens=4096,
+        temperature=0.7,
+        reasoning_effort=None,
+        tool_choice=None,
+    )
+
+    assert kwargs["model"] == "gpt-5-chat"
+    assert kwargs["max_completion_tokens"] == 4096
+    assert "max_tokens" not in kwargs
+    assert "temperature" not in kwargs
+
+
+def test_openai_compat_preserves_message_level_reasoning_fields() -> None:
+    with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI"):
+        provider = OpenAICompatProvider()
+
+    sanitized = provider._sanitize_messages([
+        {
+            "role": "assistant",
+            "content": "done",
+            "reasoning_content": "hidden",
+            "extra_content": {"debug": True},
+            "tool_calls": [
+                {
+                    "id": "call_1",
+                    "type": "function",
+                    "function": {"name": "fn", "arguments": "{}"},
+                    "extra_content": {"google": {"thought_signature": "sig"}},
+                }
+            ],
+        }
+    ])
+
+    assert sanitized[0]["reasoning_content"] == "hidden"
+    assert sanitized[0]["extra_content"] == {"debug": True}
+    assert sanitized[0]["tool_calls"][0]["extra_content"] == {"google": {"thought_signature": "sig"}}
+
+
+@pytest.mark.asyncio
+async def test_openai_compat_stream_watchdog_returns_error_on_stall(monkeypatch) -> None:
+    monkeypatch.setenv("NANOBOT_STREAM_IDLE_TIMEOUT_S", "0")
+    mock_create = AsyncMock(return_value=_StalledStream())
+    spec = find_by_name("openai")
+
+    with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI") as MockClient:
+        client_instance = MockClient.return_value
+        client_instance.chat.completions.create = mock_create
+
+        provider = OpenAICompatProvider(
+            api_key="sk-test-key",
+            default_model="gpt-4o",
+            spec=spec,
+        )
+        result = await provider.chat_stream(
+            messages=[{"role": "user", "content": "hello"}],
+            model="gpt-4o",
+        )
+
+    assert result.finish_reason == "error"
+    assert result.content is not None
+    assert "stream stalled" in result.content

tests/providers/test_openai_responses.py

@@ -0,0 +1,522 @@
+"""Tests for the shared openai_responses converters and parsers."""
+
+from unittest.mock import MagicMock, patch
+
+import pytest
+
+from nanobot.providers.base import LLMResponse, ToolCallRequest
+from nanobot.providers.openai_responses.converters import (
+    convert_messages,
+    convert_tools,
+    convert_user_message,
+    split_tool_call_id,
+)
+from nanobot.providers.openai_responses.parsing import (
+    consume_sdk_stream,
+    map_finish_reason,
+    parse_response_output,
+)
+
+
+# ======================================================================
+# converters - split_tool_call_id
+# ======================================================================
+
+
+class TestSplitToolCallId:
+    def test_plain_id(self):
+        assert split_tool_call_id("call_abc") == ("call_abc", None)
+
+    def test_compound_id(self):
+        assert split_tool_call_id("call_abc|fc_1") == ("call_abc", "fc_1")
+
+    def test_compound_empty_item_id(self):
+        assert split_tool_call_id("call_abc|") == ("call_abc", None)
+
+    def test_none(self):
+        assert split_tool_call_id(None) == ("call_0", None)
+
+    def test_empty_string(self):
+        assert split_tool_call_id("") == ("call_0", None)
+
+    def test_non_string(self):
+        assert split_tool_call_id(42) == ("call_0", None)
+
+
+# ======================================================================
+# converters - convert_user_message
+# ======================================================================
+
+
+class TestConvertUserMessage:
+    def test_string_content(self):
+        result = convert_user_message("hello")
+        assert result == {"role": "user", "content": [{"type": "input_text", "text": "hello"}]}
+
+    def test_text_block(self):
+        result = convert_user_message([{"type": "text", "text": "hi"}])
+        assert result["content"] == [{"type": "input_text", "text": "hi"}]
+
+    def test_image_url_block(self):
+        result = convert_user_message([
+            {"type": "image_url", "image_url": {"url": "https://img.example/a.png"}},
+        ])
+        assert result["content"] == [
+            {"type": "input_image", "image_url": "https://img.example/a.png", "detail": "auto"},
+        ]
+
+    def test_mixed_text_and_image(self):
+        result = convert_user_message([
+            {"type": "text", "text": "what's this?"},
+            {"type": "image_url", "image_url": {"url": "https://img.example/b.png"}},
+        ])
+        assert len(result["content"]) == 2
+        assert result["content"][0]["type"] == "input_text"
+        assert result["content"][1]["type"] == "input_image"
+
+    def test_empty_list_falls_back(self):
+        result = convert_user_message([])
+        assert result["content"] == [{"type": "input_text", "text": ""}]
+
+    def test_none_falls_back(self):
+        result = convert_user_message(None)
+        assert result["content"] == [{"type": "input_text", "text": ""}]
+
+    def test_image_without_url_skipped(self):
+        result = convert_user_message([{"type": "image_url", "image_url": {}}])
+        assert result["content"] == [{"type": "input_text", "text": ""}]
+
+    def test_meta_fields_not_leaked(self):
+        """_meta on content blocks must never appear in converted output."""
+        result = convert_user_message([
+            {"type": "text", "text": "hi", "_meta": {"path": "/tmp/x"}},
+        ])
+        assert "_meta" not in result["content"][0]
+
+    def test_non_dict_items_skipped(self):
+        result = convert_user_message(["just a string", 42])
+        assert result["content"] == [{"type": "input_text", "text": ""}]
+
+
+# ======================================================================
+# converters - convert_messages
+# ======================================================================
+
+
+class TestConvertMessages:
+    def test_system_extracted_as_instructions(self):
+        msgs = [
+            {"role": "system", "content": "You are helpful."},
+            {"role": "user", "content": "Hi"},
+        ]
+        instructions, items = convert_messages(msgs)
+        assert instructions == "You are helpful."
+        assert len(items) == 1
+        assert items[0]["role"] == "user"
+
+    def test_multiple_system_messages_last_wins(self):
+        msgs = [
+            {"role": "system", "content": "first"},
+            {"role": "system", "content": "second"},
+            {"role": "user", "content": "x"},
+        ]
+        instructions, _ = convert_messages(msgs)
+        assert instructions == "second"
+
+    def test_user_message_converted(self):
+        _, items = convert_messages([{"role": "user", "content": "hello"}])
+        assert items[0]["role"] == "user"
+        assert items[0]["content"][0]["type"] == "input_text"
+
+    def test_assistant_text_message(self):
+        _, items = convert_messages([
+            {"role": "assistant", "content": "I'll help"},
+        ])
+        assert items[0]["type"] == "message"
+        assert items[0]["role"] == "assistant"
+        assert items[0]["content"][0]["type"] == "output_text"
+        assert items[0]["content"][0]["text"] == "I'll help"
+
+    def test_assistant_empty_content_skipped(self):
+        _, items = convert_messages([{"role": "assistant", "content": ""}])
+        assert len(items) == 0
+
+    def test_assistant_with_tool_calls(self):
+        _, items = convert_messages([{
+            "role": "assistant",
+            "content": None,
+            "tool_calls": [{
+                "id": "call_abc|fc_1",
+                "function": {"name": "get_weather", "arguments": '{"city":"SF"}'},
+            }],
+        }])
+        assert items[0]["type"] == "function_call"
+        assert items[0]["call_id"] == "call_abc"
+        assert items[0]["id"] == "fc_1"
+        assert items[0]["name"] == "get_weather"
+
+    def test_assistant_with_tool_calls_no_id(self):
+        """Fallback IDs when tool_call.id is missing."""
+        _, items = convert_messages([{
+            "role": "assistant",
+            "content": None,
+            "tool_calls": [{"function": {"name": "f1", "arguments": "{}"}}],
+        }])
+        assert items[0]["call_id"] == "call_0"
+        assert items[0]["id"].startswith("fc_")
+
+    def test_tool_message(self):
+        _, items = convert_messages([{
+            "role": "tool",
+            "tool_call_id": "call_abc",
+            "content": "result text",
+        }])
+        assert items[0]["type"] == "function_call_output"
+        assert items[0]["call_id"] == "call_abc"
+        assert items[0]["output"] == "result text"
+
+    def test_tool_message_dict_content(self):
+        _, items = convert_messages([{
+            "role": "tool",
+            "tool_call_id": "call_1",
+            "content": {"key": "value"},
+        }])
+        assert items[0]["output"] == '{"key": "value"}'
+
+    def test_non_standard_keys_not_leaked(self):
+        """Extra keys on messages must not appear in converted items."""
+        _, items = convert_messages([{
+            "role": "user",
+            "content": "hi",
+            "extra_field": "should vanish",
+            "_meta": {"path": "/tmp"},
+        }])
+        item = items[0]
+        assert "extra_field" not in str(item)
+        assert "_meta" not in str(item)
+
+    def test_full_conversation_roundtrip(self):
+        """System + user + assistant(tool_call) + tool -> correct structure."""
+        msgs = [
+            {"role": "system", "content": "Be concise."},
+            {"role": "user", "content": "Weather in SF?"},
+            {
+                "role": "assistant", "content": None,
+                "tool_calls": [{
+                    "id": "c1|fc1",
+                    "function": {"name": "get_weather", "arguments": '{"city":"SF"}'},
+                }],
+            },
+            {"role": "tool", "tool_call_id": "c1", "content": '{"temp":72}'},
+        ]
+        instructions, items = convert_messages(msgs)
+        assert instructions == "Be concise."
+        assert len(items) == 3  # user, function_call, function_call_output
+        assert items[0]["role"] == "user"
+        assert items[1]["type"] == "function_call"
+        assert items[2]["type"] == "function_call_output"
+
+
+# ======================================================================
+# converters - convert_tools
+# ======================================================================
+
+
+class TestConvertTools:
+    def test_standard_function_tool(self):
+        tools = [{"type": "function", "function": {
+            "name": "get_weather",
+            "description": "Get weather",
+            "parameters": {"type": "object", "properties": {"city": {"type": "string"}}},
+        }}]
+        result = convert_tools(tools)
+        assert len(result) == 1
+        assert result[0]["type"] == "function"
+        assert result[0]["name"] == "get_weather"
+        assert result[0]["description"] == "Get weather"
+        assert "properties" in result[0]["parameters"]
+
+    def test_tool_without_name_skipped(self):
+        tools = [{"type": "function", "function": {"parameters": {}}}]
+        assert convert_tools(tools) == []
+
+    def test_tool_without_function_wrapper(self):
+        """Direct dict without type=function wrapper."""
+        tools = [{"name": "f1", "description": "d", "parameters": {}}]
+        result = convert_tools(tools)
+        assert result[0]["name"] == "f1"
+
+    def test_missing_optional_fields_default(self):
+        tools = [{"type": "function", "function": {"name": "f"}}]
+        result = convert_tools(tools)
+        assert result[0]["description"] == ""
+        assert result[0]["parameters"] == {}
+
+    def test_multiple_tools(self):
+        tools = [
+            {"type": "function", "function": {"name": "a", "parameters": {}}},
+            {"type": "function", "function": {"name": "b", "parameters": {}}},
+        ]
+        assert len(convert_tools(tools)) == 2
+
+
+# ======================================================================
+# parsing - map_finish_reason
+# ======================================================================
+
+
+class TestMapFinishReason:
+    def test_completed(self):
+        assert map_finish_reason("completed") == "stop"
+
+    def test_incomplete(self):
+        assert map_finish_reason("incomplete") == "length"
+
+    def test_failed(self):
+        assert map_finish_reason("failed") == "error"
+
+    def test_cancelled(self):
+        assert map_finish_reason("cancelled") == "error"
+
+    def test_none_defaults_to_stop(self):
+        assert map_finish_reason(None) == "stop"
+
+    def test_unknown_defaults_to_stop(self):
+        assert map_finish_reason("some_new_status") == "stop"
+
+
+# ======================================================================
+# parsing - parse_response_output
+# ======================================================================
+
+
+class TestParseResponseOutput:
+    def test_text_response(self):
+        resp = {
+            "output": [{"type": "message", "role": "assistant",
+                         "content": [{"type": "output_text", "text": "Hello!"}]}],
+            "status": "completed",
+            "usage": {"input_tokens": 10, "output_tokens": 5, "total_tokens": 15},
+        }
+        result = parse_response_output(resp)
+        assert result.content == "Hello!"
+        assert result.finish_reason == "stop"
+        assert result.usage == {"prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15}
+        assert result.tool_calls == []
+
+    def test_tool_call_response(self):
+        resp = {
+            "output": [{
+                "type": "function_call",
+                "call_id": "call_1", "id": "fc_1",
+                "name": "get_weather",
+                "arguments": '{"city": "SF"}',
+            }],
+            "status": "completed",
+            "usage": {},
+        }
+        result = parse_response_output(resp)
+        assert result.content is None
+        assert len(result.tool_calls) == 1
+        assert result.tool_calls[0].name == "get_weather"
+        assert result.tool_calls[0].arguments == {"city": "SF"}
+        assert result.tool_calls[0].id == "call_1|fc_1"
+
+    def test_malformed_tool_arguments_logged(self):
+        """Malformed JSON arguments should log a warning and fallback."""
+        resp = {
+            "output": [{
+                "type": "function_call",
+                "call_id": "c1", "id": "fc1",
+                "name": "f", "arguments": "{bad json",
+            }],
+            "status": "completed", "usage": {},
+        }
+        with patch("nanobot.providers.openai_responses.parsing.logger") as mock_logger:
+            result = parse_response_output(resp)
+        assert result.tool_calls[0].arguments == {"raw": "{bad json"}
+        mock_logger.warning.assert_called_once()
+        assert "Failed to parse tool call arguments" in str(mock_logger.warning.call_args)
+
+    def test_reasoning_content_extracted(self):
+        resp = {
+            "output": [
+                {"type": "reasoning", "summary": [
+                    {"type": "summary_text", "text": "I think "},
+                    {"type": "summary_text", "text": "therefore I am."},
+                ]},
+                {"type": "message", "role": "assistant",
+                 "content": [{"type": "output_text", "text": "42"}]},
+            ],
+            "status": "completed", "usage": {},
+        }
+        result = parse_response_output(resp)
+        assert result.content == "42"
+        assert result.reasoning_content == "I think therefore I am."
+
+    def test_empty_output(self):
+        resp = {"output": [], "status": "completed", "usage": {}}
+        result = parse_response_output(resp)
+        assert result.content is None
+        assert result.tool_calls == []
+
+    def test_incomplete_status(self):
+        resp = {"output": [], "status": "incomplete", "usage": {}}
+        result = parse_response_output(resp)
+        assert result.finish_reason == "length"
+
+    def test_sdk_model_object(self):
+        """parse_response_output should handle SDK objects with model_dump()."""
+        mock = MagicMock()
+        mock.model_dump.return_value = {
+            "output": [{"type": "message", "role": "assistant",
+                         "content": [{"type": "output_text", "text": "sdk"}]}],
+            "status": "completed",
+            "usage": {"input_tokens": 1, "output_tokens": 2, "total_tokens": 3},
+        }
+        result = parse_response_output(mock)
+        assert result.content == "sdk"
+        assert result.usage["prompt_tokens"] == 1
+
+    def test_usage_maps_responses_api_keys(self):
+        """Responses API uses input_tokens/output_tokens, not prompt_tokens/completion_tokens."""
+        resp = {
+            "output": [],
+            "status": "completed",
+            "usage": {"input_tokens": 100, "output_tokens": 50, "total_tokens": 150},
+        }
+        result = parse_response_output(resp)
+        assert result.usage["prompt_tokens"] == 100
+        assert result.usage["completion_tokens"] == 50
+        assert result.usage["total_tokens"] == 150
+
+
+# ======================================================================
+# parsing - consume_sdk_stream
+# ======================================================================
+
+
+class TestConsumeSdkStream:
+    @pytest.mark.asyncio
+    async def test_text_stream(self):
+        ev1 = MagicMock(type="response.output_text.delta", delta="Hello")
+        ev2 = MagicMock(type="response.output_text.delta", delta=" world")
+        resp_obj = MagicMock(status="completed", usage=None, output=[])
+        ev3 = MagicMock(type="response.completed", response=resp_obj)
+
+        async def stream():
+            for e in [ev1, ev2, ev3]:
+                yield e
+
+        content, tool_calls, finish_reason, usage, reasoning = await consume_sdk_stream(stream())
+        assert content == "Hello world"
+        assert tool_calls == []
+        assert finish_reason == "stop"
+
+    @pytest.mark.asyncio
+    async def test_on_content_delta_called(self):
+        ev1 = MagicMock(type="response.output_text.delta", delta="hi")
+        resp_obj = MagicMock(status="completed", usage=None, output=[])
+        ev2 = MagicMock(type="response.completed", response=resp_obj)
+        deltas = []
+
+        async def cb(text):
+            deltas.append(text)
+
+        async def stream():
+            for e in [ev1, ev2]:
+                yield e
+
+        await consume_sdk_stream(stream(), on_content_delta=cb)
+        assert deltas == ["hi"]
+
+    @pytest.mark.asyncio
+    async def test_tool_call_stream(self):
+        item_added = MagicMock(type="function_call", call_id="c1", id="fc1", arguments="")
+        item_added.name = "get_weather"
+        ev1 = MagicMock(type="response.output_item.added", item=item_added)
+        ev2 = MagicMock(type="response.function_call_arguments.delta", call_id="c1", delta='{"ci')
+        ev3 = MagicMock(type="response.function_call_arguments.done", call_id="c1", arguments='{"city":"SF"}')
+        item_done = MagicMock(type="function_call", call_id="c1", id="fc1", arguments='{"city":"SF"}')
+        item_done.name = "get_weather"
+        ev4 = MagicMock(type="response.output_item.done", item=item_done)
+        resp_obj = MagicMock(status="completed", usage=None, output=[])
+        ev5 = MagicMock(type="response.completed", response=resp_obj)
+
+        async def stream():
+            for e in [ev1, ev2, ev3, ev4, ev5]:
+                yield e
+
+        content, tool_calls, finish_reason, usage, reasoning = await consume_sdk_stream(stream())
+        assert content == ""
+        assert len(tool_calls) == 1
+        assert tool_calls[0].name == "get_weather"
+        assert tool_calls[0].arguments == {"city": "SF"}
+
+    @pytest.mark.asyncio
+    async def test_usage_extracted(self):
+        usage_obj = MagicMock(input_tokens=10, output_tokens=5, total_tokens=15)
+        resp_obj = MagicMock(status="completed", usage=usage_obj, output=[])
+        ev = MagicMock(type="response.completed", response=resp_obj)
+
+        async def stream():
+            yield ev
+
+        _, _, _, usage, _ = await consume_sdk_stream(stream())
+        assert usage == {"prompt_tokens": 10, "completion_tokens": 5, "total_tokens": 15}
+
+    @pytest.mark.asyncio
+    async def test_reasoning_extracted(self):
+        summary_item = MagicMock(type="summary_text", text="thinking...")
+        reasoning_item = MagicMock(type="reasoning", summary=[summary_item])
+        resp_obj = MagicMock(status="completed", usage=None, output=[reasoning_item])
+        ev = MagicMock(type="response.completed", response=resp_obj)
+
+        async def stream():
+            yield ev
+
+        _, _, _, _, reasoning = await consume_sdk_stream(stream())
+        assert reasoning == "thinking..."
+
+    @pytest.mark.asyncio
+    async def test_error_event_raises(self):
+        ev = MagicMock(type="error", error="rate_limit_exceeded")
+
+        async def stream():
+            yield ev
+
+        with pytest.raises(RuntimeError, match="Response failed.*rate_limit_exceeded"):
+            await consume_sdk_stream(stream())
+
+    @pytest.mark.asyncio
+    async def test_failed_event_raises(self):
+        ev = MagicMock(type="response.failed", error="server_error")
+
+        async def stream():
+            yield ev
+
+        with pytest.raises(RuntimeError, match="Response failed.*server_error"):
+            await consume_sdk_stream(stream())
+
+    @pytest.mark.asyncio
+    async def test_malformed_tool_args_logged(self):
+        """Malformed JSON in streaming tool args should log a warning."""
+        item_added = MagicMock(type="function_call", call_id="c1", id="fc1", arguments="")
+        item_added.name = "f"
+        ev1 = MagicMock(type="response.output_item.added", item=item_added)
+        ev2 = MagicMock(type="response.function_call_arguments.done", call_id="c1", arguments="{bad")
+        item_done = MagicMock(type="function_call", call_id="c1", id="fc1", arguments="{bad")
+        item_done.name = "f"
+        ev3 = MagicMock(type="response.output_item.done", item=item_done)
+        resp_obj = MagicMock(status="completed", usage=None, output=[])
+        ev4 = MagicMock(type="response.completed", response=resp_obj)
+
+        async def stream():
+            for e in [ev1, ev2, ev3, ev4]:
+                yield e
+
+        with patch("nanobot.providers.openai_responses.parsing.logger") as mock_logger:
+            _, tool_calls, _, _, _ = await consume_sdk_stream(stream())
+        assert tool_calls[0].arguments == {"raw": "{bad"}
+        mock_logger.warning.assert_called_once()
+        assert "Failed to parse tool call arguments" in str(mock_logger.warning.call_args)

tests/providers/test_provider_retry.py

@@ -211,3 +211,88 @@ async def test_image_fallback_without_meta_uses_default_placeholder() -> None:
         content = msg.get("content")
         if isinstance(content, list):
             assert any("[image omitted]" in (b.get("text") or "") for b in content)
+
+
+@pytest.mark.asyncio
+async def test_chat_with_retry_uses_retry_after_and_emits_wait_progress(monkeypatch) -> None:
+    provider = ScriptedProvider([
+        LLMResponse(content="429 rate limit, retry after 7s", finish_reason="error"),
+        LLMResponse(content="ok"),
+    ])
+    delays: list[float] = []
+    progress: list[str] = []
+
+    async def _fake_sleep(delay: float) -> None:
+        delays.append(delay)
+
+    async def _progress(msg: str) -> None:
+        progress.append(msg)
+
+    monkeypatch.setattr("nanobot.providers.base.asyncio.sleep", _fake_sleep)
+
+    response = await provider.chat_with_retry(
+        messages=[{"role": "user", "content": "hello"}],
+        on_retry_wait=_progress,
+    )
+
+    assert response.content == "ok"
+    assert delays == [7.0]
+    assert progress and "7s" in progress[0]
+
+
+def test_extract_retry_after_supports_common_provider_formats() -> None:
+    assert LLMProvider._extract_retry_after('{"error":{"retry_after":20}}') == 20.0
+    assert LLMProvider._extract_retry_after("Rate limit reached, please try again in 20s") == 20.0
+    assert LLMProvider._extract_retry_after("retry-after: 20") == 20.0
+
+
+def test_extract_retry_after_from_headers_supports_numeric_and_http_date() -> None:
+    assert LLMProvider._extract_retry_after_from_headers({"Retry-After": "20"}) == 20.0
+    assert LLMProvider._extract_retry_after_from_headers({"retry-after": "20"}) == 20.0
+    assert LLMProvider._extract_retry_after_from_headers(
+        {"Retry-After": "Wed, 21 Oct 2015 07:28:00 GMT"},
+    ) == 0.1
+
+
+@pytest.mark.asyncio
+async def test_chat_with_retry_prefers_structured_retry_after_when_present(monkeypatch) -> None:
+    provider = ScriptedProvider([
+        LLMResponse(content="429 rate limit", finish_reason="error", retry_after=9.0),
+        LLMResponse(content="ok"),
+    ])
+    delays: list[float] = []
+
+    async def _fake_sleep(delay: float) -> None:
+        delays.append(delay)
+
+    monkeypatch.setattr("nanobot.providers.base.asyncio.sleep", _fake_sleep)
+
+    response = await provider.chat_with_retry(messages=[{"role": "user", "content": "hello"}])
+
+    assert response.content == "ok"
+    assert delays == [9.0]
+
+
+@pytest.mark.asyncio
+async def test_persistent_retry_aborts_after_ten_identical_transient_errors(monkeypatch) -> None:
+    provider = ScriptedProvider([
+        *[LLMResponse(content="429 rate limit", finish_reason="error") for _ in range(10)],
+        LLMResponse(content="ok"),
+    ])
+    delays: list[float] = []
+
+    async def _fake_sleep(delay: float) -> None:
+        delays.append(delay)
+
+    monkeypatch.setattr("nanobot.providers.base.asyncio.sleep", _fake_sleep)
+
+    response = await provider.chat_with_retry(
+        messages=[{"role": "user", "content": "hello"}],
+        retry_mode="persistent",
+    )
+
+    assert response.finish_reason == "error"
+    assert response.content == "429 rate limit"
+    assert provider.calls == 10
+    assert delays == [1, 2, 4, 4, 4, 4, 4, 4, 4]
+

tests/providers/test_provider_retry_after_hints.py

@@ -0,0 +1,42 @@
+from types import SimpleNamespace
+
+from nanobot.providers.anthropic_provider import AnthropicProvider
+from nanobot.providers.azure_openai_provider import AzureOpenAIProvider
+from nanobot.providers.openai_compat_provider import OpenAICompatProvider
+
+
+def test_openai_compat_error_captures_retry_after_from_headers() -> None:
+    err = Exception("boom")
+    err.doc = None
+    err.response = SimpleNamespace(
+        text='{"error":{"message":"Rate limit exceeded"}}',
+        headers={"Retry-After": "20"},
+    )
+
+    response = OpenAICompatProvider._handle_error(err)
+
+    assert response.retry_after == 20.0
+
+
+def test_azure_openai_error_captures_retry_after_from_headers() -> None:
+    err = Exception("boom")
+    err.body = {"message": "Rate limit exceeded"}
+    err.response = SimpleNamespace(
+        text='{"error":{"message":"Rate limit exceeded"}}',
+        headers={"Retry-After": "20"},
+    )
+
+    response = AzureOpenAIProvider._handle_error(err)
+
+    assert response.retry_after == 20.0
+
+
+def test_anthropic_error_captures_retry_after_from_headers() -> None:
+    err = Exception("boom")
+    err.response = SimpleNamespace(
+        headers={"Retry-After": "20"},
+    )
+
+    response = AnthropicProvider._handle_error(err)
+
+    assert response.retry_after == 20.0

tests/providers/test_provider_sdk_retry_defaults.py

@@ -0,0 +1,33 @@
+from unittest.mock import patch
+
+from nanobot.providers.anthropic_provider import AnthropicProvider
+from nanobot.providers.azure_openai_provider import AzureOpenAIProvider
+from nanobot.providers.openai_compat_provider import OpenAICompatProvider
+
+
+def test_openai_compat_disables_sdk_retries_by_default() -> None:
+    with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI") as mock_client:
+        OpenAICompatProvider(api_key="sk-test", default_model="gpt-4o")
+
+    kwargs = mock_client.call_args.kwargs
+    assert kwargs["max_retries"] == 0
+
+
+def test_anthropic_disables_sdk_retries_by_default() -> None:
+    with patch("anthropic.AsyncAnthropic") as mock_client:
+        AnthropicProvider(api_key="sk-test", default_model="claude-sonnet-4-5")
+
+    kwargs = mock_client.call_args.kwargs
+    assert kwargs["max_retries"] == 0
+
+
+def test_azure_openai_disables_sdk_retries_by_default() -> None:
+    with patch("nanobot.providers.azure_openai_provider.AsyncOpenAI") as mock_client:
+        AzureOpenAIProvider(
+            api_key="sk-test",
+            api_base="https://example.openai.azure.com",
+            default_model="gpt-4.1",
+        )
+
+    kwargs = mock_client.call_args.kwargs
+    assert kwargs["max_retries"] == 0

tests/providers/test_providers_init.py

@@ -11,6 +11,7 @@ def test_importing_providers_package_is_lazy(monkeypatch) -> None:
     monkeypatch.delitem(sys.modules, "nanobot.providers.anthropic_provider", raising=False)
     monkeypatch.delitem(sys.modules, "nanobot.providers.openai_compat_provider", raising=False)
     monkeypatch.delitem(sys.modules, "nanobot.providers.openai_codex_provider", raising=False)
+    monkeypatch.delitem(sys.modules, "nanobot.providers.github_copilot_provider", raising=False)
     monkeypatch.delitem(sys.modules, "nanobot.providers.azure_openai_provider", raising=False)
 
     providers = importlib.import_module("nanobot.providers")
@@ -18,6 +19,7 @@ def test_importing_providers_package_is_lazy(monkeypatch) -> None:
     assert "nanobot.providers.anthropic_provider" not in sys.modules
     assert "nanobot.providers.openai_compat_provider" not in sys.modules
     assert "nanobot.providers.openai_codex_provider" not in sys.modules
+    assert "nanobot.providers.github_copilot_provider" not in sys.modules
     assert "nanobot.providers.azure_openai_provider" not in sys.modules
     assert providers.__all__ == [
         "LLMProvider",
@@ -25,6 +27,7 @@ def test_importing_providers_package_is_lazy(monkeypatch) -> None:
         "AnthropicProvider",
         "OpenAICompatProvider",
         "OpenAICodexProvider",
+        "GitHubCopilotProvider",
         "AzureOpenAIProvider",
     ]
 

tests/providers/test_reasoning_content.py

@@ -0,0 +1,128 @@
+"""Tests for reasoning_content extraction in OpenAICompatProvider.
+
+Covers non-streaming (_parse) and streaming (_parse_chunks) paths for
+providers that return a reasoning_content field (e.g. MiMo, DeepSeek-R1).
+"""
+
+from types import SimpleNamespace
+from unittest.mock import patch
+
+from nanobot.providers.openai_compat_provider import OpenAICompatProvider
+
+
+# ── _parse: non-streaming ─────────────────────────────────────────────────
+
+
+def test_parse_dict_extracts_reasoning_content() -> None:
+    """reasoning_content at message level is surfaced in LLMResponse."""
+    with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI"):
+        provider = OpenAICompatProvider()
+
+    response = {
+        "choices": [{
+            "message": {
+                "content": "42",
+                "reasoning_content": "Let me think step by step…",
+            },
+            "finish_reason": "stop",
+        }],
+        "usage": {"prompt_tokens": 5, "completion_tokens": 10, "total_tokens": 15},
+    }
+
+    result = provider._parse(response)
+
+    assert result.content == "42"
+    assert result.reasoning_content == "Let me think step by step…"
+
+
+def test_parse_dict_reasoning_content_none_when_absent() -> None:
+    """reasoning_content is None when the response doesn't include it."""
+    with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI"):
+        provider = OpenAICompatProvider()
+
+    response = {
+        "choices": [{
+            "message": {"content": "hello"},
+            "finish_reason": "stop",
+        }],
+    }
+
+    result = provider._parse(response)
+
+    assert result.reasoning_content is None
+
+
+# ── _parse_chunks: streaming dict branch ─────────────────────────────────
+
+
+def test_parse_chunks_dict_accumulates_reasoning_content() -> None:
+    """reasoning_content deltas in dict chunks are joined into one string."""
+    chunks = [
+        {
+            "choices": [{
+                "finish_reason": None,
+                "delta": {"content": None, "reasoning_content": "Step 1. "},
+            }],
+        },
+        {
+            "choices": [{
+                "finish_reason": None,
+                "delta": {"content": None, "reasoning_content": "Step 2."},
+            }],
+        },
+        {
+            "choices": [{
+                "finish_reason": "stop",
+                "delta": {"content": "answer"},
+            }],
+        },
+    ]
+
+    result = OpenAICompatProvider._parse_chunks(chunks)
+
+    assert result.content == "answer"
+    assert result.reasoning_content == "Step 1. Step 2."
+
+
+def test_parse_chunks_dict_reasoning_content_none_when_absent() -> None:
+    """reasoning_content is None when no chunk contains it."""
+    chunks = [
+        {"choices": [{"finish_reason": "stop", "delta": {"content": "hi"}}]},
+    ]
+
+    result = OpenAICompatProvider._parse_chunks(chunks)
+
+    assert result.content == "hi"
+    assert result.reasoning_content is None
+
+
+# ── _parse_chunks: streaming SDK-object branch ────────────────────────────
+
+
+def _make_reasoning_chunk(reasoning: str | None, content: str | None, finish: str | None):
+    delta = SimpleNamespace(content=content, reasoning_content=reasoning, tool_calls=None)
+    choice = SimpleNamespace(finish_reason=finish, delta=delta)
+    return SimpleNamespace(choices=[choice], usage=None)
+
+
+def test_parse_chunks_sdk_accumulates_reasoning_content() -> None:
+    """reasoning_content on SDK delta objects is joined across chunks."""
+    chunks = [
+        _make_reasoning_chunk("Think… ", None, None),
+        _make_reasoning_chunk("Done.", None, None),
+        _make_reasoning_chunk(None, "result", "stop"),
+    ]
+
+    result = OpenAICompatProvider._parse_chunks(chunks)
+
+    assert result.content == "result"
+    assert result.reasoning_content == "Think… Done."
+
+
+def test_parse_chunks_sdk_reasoning_content_none_when_absent() -> None:
+    """reasoning_content is None when SDK deltas carry no reasoning_content."""
+    chunks = [_make_reasoning_chunk(None, "hello", "stop")]
+
+    result = OpenAICompatProvider._parse_chunks(chunks)
+
+    assert result.reasoning_content is None

tests/security/test_security_network.py

@@ -7,7 +7,7 @@ from unittest.mock import patch
 
 import pytest
 
-from nanobot.security.network import contains_internal_url, validate_url_target
+from nanobot.security.network import configure_ssrf_whitelist, contains_internal_url, validate_url_target
 
 
 def _fake_resolve(host: str, results: list[str]):
@@ -99,3 +99,47 @@ def test_allows_normal_curl():
 
 def test_no_urls_returns_false():
     assert not contains_internal_url("echo hello && ls -la")
+
+
+# ---------------------------------------------------------------------------
+# SSRF whitelist — allow specific CIDR ranges (#2669)
+# ---------------------------------------------------------------------------
+
+def test_blocks_cgnat_by_default():
+    """100.64.0.0/10 (CGNAT / Tailscale) is blocked by default."""
+    with patch("nanobot.security.network.socket.getaddrinfo", _fake_resolve("ts.local", ["100.100.1.1"])):
+        ok, _ = validate_url_target("http://ts.local/api")
+        assert not ok
+
+
+def test_whitelist_allows_cgnat():
+    """Whitelisting 100.64.0.0/10 lets Tailscale addresses through."""
+    configure_ssrf_whitelist(["100.64.0.0/10"])
+    try:
+        with patch("nanobot.security.network.socket.getaddrinfo", _fake_resolve("ts.local", ["100.100.1.1"])):
+            ok, err = validate_url_target("http://ts.local/api")
+            assert ok, f"Whitelisted CGNAT should be allowed, got: {err}"
+    finally:
+        configure_ssrf_whitelist([])
+
+
+def test_whitelist_does_not_affect_other_blocked():
+    """Whitelisting CGNAT must not unblock other private ranges."""
+    configure_ssrf_whitelist(["100.64.0.0/10"])
+    try:
+        with patch("nanobot.security.network.socket.getaddrinfo", _fake_resolve("evil.com", ["10.0.0.1"])):
+            ok, _ = validate_url_target("http://evil.com/secret")
+            assert not ok
+    finally:
+        configure_ssrf_whitelist([])
+
+
+def test_whitelist_invalid_cidr_ignored():
+    """Invalid CIDR entries are silently skipped."""
+    configure_ssrf_whitelist(["not-a-cidr", "100.64.0.0/10"])
+    try:
+        with patch("nanobot.security.network.socket.getaddrinfo", _fake_resolve("ts.local", ["100.100.1.1"])):
+            ok, _ = validate_url_target("http://ts.local/api")
+            assert ok
+    finally:
+        configure_ssrf_whitelist([])

tests/test_build_status.py

@@ -0,0 +1,59 @@
+"""Tests for build_status_content cache hit rate display."""
+
+from nanobot.utils.helpers import build_status_content
+
+
+def test_status_shows_cache_hit_rate():
+    content = build_status_content(
+        version="0.1.0",
+        model="glm-4-plus",
+        start_time=1000000.0,
+        last_usage={"prompt_tokens": 2000, "completion_tokens": 300, "cached_tokens": 1200},
+        context_window_tokens=128000,
+        session_msg_count=10,
+        context_tokens_estimate=5000,
+    )
+    assert "60% cached" in content
+    assert "2000 in / 300 out" in content
+
+
+def test_status_no_cache_info():
+    """Without cached_tokens, display should not show cache percentage."""
+    content = build_status_content(
+        version="0.1.0",
+        model="glm-4-plus",
+        start_time=1000000.0,
+        last_usage={"prompt_tokens": 2000, "completion_tokens": 300},
+        context_window_tokens=128000,
+        session_msg_count=10,
+        context_tokens_estimate=5000,
+    )
+    assert "cached" not in content.lower()
+    assert "2000 in / 300 out" in content
+
+
+def test_status_zero_cached_tokens():
+    """cached_tokens=0 should not show cache percentage."""
+    content = build_status_content(
+        version="0.1.0",
+        model="glm-4-plus",
+        start_time=1000000.0,
+        last_usage={"prompt_tokens": 2000, "completion_tokens": 300, "cached_tokens": 0},
+        context_window_tokens=128000,
+        session_msg_count=10,
+        context_tokens_estimate=5000,
+    )
+    assert "cached" not in content.lower()
+
+
+def test_status_100_percent_cached():
+    content = build_status_content(
+        version="0.1.0",
+        model="glm-4-plus",
+        start_time=1000000.0,
+        last_usage={"prompt_tokens": 1000, "completion_tokens": 100, "cached_tokens": 1000},
+        context_window_tokens=128000,
+        session_msg_count=5,
+        context_tokens_estimate=3000,
+    )
+    assert "100% cached" in content

tests/test_nanobot_facade.py

@@ -125,6 +125,27 @@ def test_workspace_override(tmp_path):
     assert bot._loop.workspace == custom_ws
 
 
+def test_sdk_make_provider_uses_github_copilot_backend():
+    from nanobot.config.schema import Config
+    from nanobot.nanobot import _make_provider
+
+    config = Config.model_validate(
+        {
+            "agents": {
+                "defaults": {
+                    "provider": "github-copilot",
+                    "model": "github-copilot/gpt-4.1",
+                }
+            }
+        }
+    )
+
+    with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI"):
+        provider = _make_provider(config)
+
+    assert provider.__class__.__name__ == "GitHubCopilotProvider"
+
+
 @pytest.mark.asyncio
 async def test_run_custom_session_key(tmp_path):
     from nanobot.bus.events import OutboundMessage

tests/test_openai_api.py

@@ -347,6 +347,8 @@ async def test_empty_response_retry_then_success(aiohttp_client) -> None:
 @pytest.mark.skipif(not HAS_AIOHTTP, reason="aiohttp not installed")
 @pytest.mark.asyncio
 async def test_empty_response_falls_back(aiohttp_client) -> None:
+    from nanobot.utils.runtime import EMPTY_FINAL_RESPONSE_MESSAGE
+
     call_count = 0
 
     async def always_empty(content, session_key="", channel="", chat_id=""):
@@ -367,5 +369,5 @@ async def test_empty_response_falls_back(aiohttp_client) -> None:
     )
     assert resp.status == 200
     body = await resp.json()
-    assert body["choices"][0]["message"]["content"] == "I've completed processing but have no response to give."
+    assert body["choices"][0]["message"]["content"] == EMPTY_FINAL_RESPONSE_MESSAGE
     assert call_count == 2

tests/tools/test_filesystem_tools.py

@@ -321,6 +321,22 @@ class TestWorkspaceRestriction:
         assert "Test Skill" in result
         assert "Error" not in result
 
+    @pytest.mark.asyncio
+    async def test_read_allowed_in_media_dir(self, tmp_path, monkeypatch):
+        workspace = tmp_path / "ws"
+        workspace.mkdir()
+        media_dir = tmp_path / "media"
+        media_dir.mkdir()
+        media_file = media_dir / "photo.txt"
+        media_file.write_text("shared media", encoding="utf-8")
+
+        monkeypatch.setattr("nanobot.agent.tools.filesystem.get_media_dir", lambda: media_dir)
+
+        tool = ReadFileTool(workspace=workspace, allowed_dir=workspace)
+        result = await tool.execute(path=str(media_file))
+        assert "shared media" in result
+        assert "Error" not in result
+
     @pytest.mark.asyncio
     async def test_extra_dirs_does_not_widen_write(self, tmp_path):
         from nanobot.agent.tools.filesystem import WriteFileTool

tests/tools/test_mcp_tool.py

@@ -196,7 +196,7 @@ async def test_execute_re_raises_external_cancellation() -> None:
 
     wrapper = _make_wrapper(SimpleNamespace(call_tool=call_tool), timeout=10)
     task = asyncio.create_task(wrapper.execute())
-    await started.wait()
+    await asyncio.wait_for(started.wait(), timeout=1.0)
 
     task.cancel()
 

tests/tools/test_tool_validation.py

@@ -1,5 +1,14 @@
 from typing import Any
 
+from nanobot.agent.tools import (
+    ArraySchema,
+    IntegerSchema,
+    ObjectSchema,
+    Schema,
+    StringSchema,
+    tool_parameters,
+    tool_parameters_schema,
+)
 from nanobot.agent.tools.base import Tool
 from nanobot.agent.tools.registry import ToolRegistry
 from nanobot.agent.tools.shell import ExecTool
@@ -41,6 +50,103 @@ class SampleTool(Tool):
         return "ok"
 
 
+@tool_parameters(
+    tool_parameters_schema(
+        query=StringSchema(min_length=2),
+        count=IntegerSchema(2, minimum=1, maximum=10),
+        required=["query", "count"],
+    )
+)
+class DecoratedSampleTool(Tool):
+    @property
+    def name(self) -> str:
+        return "decorated_sample"
+
+    @property
+    def description(self) -> str:
+        return "decorated sample tool"
+
+    async def execute(self, **kwargs: Any) -> str:
+        return f"ok:{kwargs['count']}"
+
+
+def test_schema_validate_value_matches_tool_validate_params() -> None:
+    """ObjectSchema.validate_value 与 validate_json_schema_value、Tool.validate_params 一致。"""
+    root = tool_parameters_schema(
+        query=StringSchema(min_length=2),
+        count=IntegerSchema(2, minimum=1, maximum=10),
+        required=["query", "count"],
+    )
+    obj = ObjectSchema(
+        query=StringSchema(min_length=2),
+        count=IntegerSchema(2, minimum=1, maximum=10),
+        required=["query", "count"],
+    )
+    params = {"query": "h", "count": 2}
+
+    class _Mini(Tool):
+        @property
+        def name(self) -> str:
+            return "m"
+
+        @property
+        def description(self) -> str:
+            return ""
+
+        @property
+        def parameters(self) -> dict[str, Any]:
+            return root
+
+        async def execute(self, **kwargs: Any) -> str:
+            return ""
+
+    expected = _Mini().validate_params(params)
+    assert Schema.validate_json_schema_value(params, root, "") == expected
+    assert obj.validate_value(params, "") == expected
+    assert IntegerSchema(0, minimum=1).validate_value(0, "n") == ["n must be >= 1"]
+
+
+def test_schema_classes_equivalent_to_sample_tool_parameters() -> None:
+    """Schema 类生成的 JSON Schema 应与手写 dict 一致，便于校验行为一致。"""
+    built = tool_parameters_schema(
+        query=StringSchema(min_length=2),
+        count=IntegerSchema(2, minimum=1, maximum=10),
+        mode=StringSchema("", enum=["fast", "full"]),
+        meta=ObjectSchema(
+            tag=StringSchema(""),
+            flags=ArraySchema(StringSchema("")),
+            required=["tag"],
+        ),
+        required=["query", "count"],
+    )
+    assert built == SampleTool().parameters
+
+
+def test_tool_parameters_returns_fresh_copy_per_access() -> None:
+    tool = DecoratedSampleTool()
+
+    first = tool.parameters
+    second = tool.parameters
+
+    assert first == second
+    assert first is not second
+    assert first["properties"] is not second["properties"]
+
+    first["properties"]["query"]["minLength"] = 99
+    assert tool.parameters["properties"]["query"]["minLength"] == 2
+
+
+async def test_registry_executes_decorated_tool_end_to_end() -> None:
+    reg = ToolRegistry()
+    reg.register(DecoratedSampleTool())
+
+    ok = await reg.execute("decorated_sample", {"query": "hello", "count": "3"})
+    assert ok == "ok:3"
+
+    err = await reg.execute("decorated_sample", {"query": "h", "count": 3})
+    assert "Invalid parameters" in err
+
+
 def test_validate_params_missing_required() -> None:
     tool = SampleTool()
     errors = tool.validate_params({"query": "hi"})
@@ -95,6 +201,14 @@ def test_exec_extract_absolute_paths_keeps_full_windows_path() -> None:
     assert paths == [r"C:\user\workspace\txt"]
 
 
+def test_exec_extract_absolute_paths_captures_windows_drive_root_path() -> None:
+    """Windows drive root paths like `E:\\` must be extracted for workspace guarding."""
+    # Note: raw strings cannot end with a single backslash.
+    cmd = "dir E:\\"
+    paths = ExecTool._extract_absolute_paths(cmd)
+    assert paths == ["E:\\"]
+
+
 def test_exec_extract_absolute_paths_ignores_relative_posix_segments() -> None:
     cmd = ".venv/bin/python script.py"
     paths = ExecTool._extract_absolute_paths(cmd)
@@ -134,6 +248,58 @@ def test_exec_guard_blocks_quoted_home_path_outside_workspace(tmp_path) -> None:
     assert error == "Error: Command blocked by safety guard (path outside working dir)"
 
 
+def test_exec_guard_allows_media_path_outside_workspace(tmp_path, monkeypatch) -> None:
+    media_dir = tmp_path / "media"
+    media_dir.mkdir()
+    media_file = media_dir / "photo.jpg"
+    media_file.write_text("ok", encoding="utf-8")
+
+    monkeypatch.setattr("nanobot.agent.tools.shell.get_media_dir", lambda: media_dir)
+
+    tool = ExecTool(restrict_to_workspace=True)
+    error = tool._guard_command(f'cat "{media_file}"', str(tmp_path / "workspace"))
+    assert error is None
+
+
+def test_exec_guard_blocks_windows_drive_root_outside_workspace(monkeypatch) -> None:
+    import nanobot.agent.tools.shell as shell_mod
+
+    class FakeWindowsPath:
+        def __init__(self, raw: str) -> None:
+            self.raw = raw.rstrip("\\") + ("\\" if raw.endswith("\\") else "")
+
+        def resolve(self) -> "FakeWindowsPath":
+            return self
+
+        def expanduser(self) -> "FakeWindowsPath":
+            return self
+
+        def is_absolute(self) -> bool:
+            return len(self.raw) >= 3 and self.raw[1:3] == ":\\"
+
+        @property
+        def parents(self) -> list["FakeWindowsPath"]:
+            if not self.is_absolute():
+                return []
+            trimmed = self.raw.rstrip("\\")
+            if len(trimmed) <= 2:
+                return []
+            idx = trimmed.rfind("\\")
+            if idx <= 2:
+                return [FakeWindowsPath(trimmed[:2] + "\\")]
+            parent = FakeWindowsPath(trimmed[:idx])
+            return [parent, *parent.parents]
+
+        def __eq__(self, other: object) -> bool:
+            return isinstance(other, FakeWindowsPath) and self.raw.lower() == other.raw.lower()
+
+    monkeypatch.setattr(shell_mod, "Path", FakeWindowsPath)
+
+    tool = ExecTool(restrict_to_workspace=True)
+    error = tool._guard_command("dir E:\\", "E:\\workspace")
+    assert error == "Error: Command blocked by safety guard (path outside working dir)"
+
+
 # --- cast_params tests ---
 
 

tests/utils/test_restart.py

@@ -0,0 +1,49 @@
+"""Tests for restart notice helpers."""
+
+from __future__ import annotations
+
+import os
+
+from nanobot.utils.restart import (
+    RestartNotice,
+    consume_restart_notice_from_env,
+    format_restart_completed_message,
+    set_restart_notice_to_env,
+    should_show_cli_restart_notice,
+)
+
+
+def test_set_and_consume_restart_notice_env_roundtrip(monkeypatch):
+    monkeypatch.delenv("NANOBOT_RESTART_NOTIFY_CHANNEL", raising=False)
+    monkeypatch.delenv("NANOBOT_RESTART_NOTIFY_CHAT_ID", raising=False)
+    monkeypatch.delenv("NANOBOT_RESTART_STARTED_AT", raising=False)
+
+    set_restart_notice_to_env(channel="feishu", chat_id="oc_123")
+
+    notice = consume_restart_notice_from_env()
+    assert notice is not None
+    assert notice.channel == "feishu"
+    assert notice.chat_id == "oc_123"
+    assert notice.started_at_raw
+
+    # Consumed values should be cleared from env.
+    assert consume_restart_notice_from_env() is None
+    assert "NANOBOT_RESTART_NOTIFY_CHANNEL" not in os.environ
+    assert "NANOBOT_RESTART_NOTIFY_CHAT_ID" not in os.environ
+    assert "NANOBOT_RESTART_STARTED_AT" not in os.environ
+
+
+def test_format_restart_completed_message_with_elapsed(monkeypatch):
+    monkeypatch.setattr("nanobot.utils.restart.time.time", lambda: 102.0)
+    assert format_restart_completed_message("100.0") == "Restart completed in 2.0s."
+
+
+def test_should_show_cli_restart_notice():
+    notice = RestartNotice(channel="cli", chat_id="direct", started_at_raw="100")
+    assert should_show_cli_restart_notice(notice, "cli:direct") is True
+    assert should_show_cli_restart_notice(notice, "cli:other") is False
+    assert should_show_cli_restart_notice(notice, "direct") is True
+
+    non_cli = RestartNotice(channel="feishu", chat_id="oc_1", started_at_raw="100")
+    assert should_show_cli_restart_notice(non_cli, "cli:direct") is False
+