Merge remote-tracking branch 'origin/main' into pr-1488

.gitignore

@@ -19,4 +19,4 @@ __pycache__/
 poetry.lock
 .pytest_cache/
 botpy.log
-tests/
+

README.md

@@ -293,12 +293,18 @@ If you prefer to configure manually, add the following to `~/.nanobot/config.jso
     "discord": {
       "enabled": true,
       "token": "YOUR_BOT_TOKEN",
-      "allowFrom": ["YOUR_USER_ID"]
+      "allowFrom": ["YOUR_USER_ID"],
+      "groupPolicy": "mention"
     }
   }
 }
 ```
 
+> `groupPolicy` controls how the bot responds in group channels:
+> - `"mention"` (default) — Only respond when @mentioned
+> - `"open"` — Respond to all messages
+> DMs always respond when the sender is in `allowFrom`.
+
 **5. Invite the bot**
 - OAuth2 → URL Generator
 - Scopes: `bot`

nanobot/agent/tools/base.py

@@ -54,6 +54,8 @@ class Tool(ABC):
 
     def validate_params(self, params: dict[str, Any]) -> list[str]:
         """Validate tool parameters against JSON schema. Returns error list (empty if valid)."""
+        if not isinstance(params, dict):
+            return [f"parameters must be an object, got {type(params).__name__}"]
         schema = self.parameters or {}
         if schema.get("type", "object") != "object":
             raise ValueError(f"Schema must be object type, got {schema.get('type')!r}")

nanobot/agent/tools/cron.py

@@ -122,7 +122,10 @@ class CronTool(Tool):
         elif at:
             from datetime import datetime
 
-            dt = datetime.fromisoformat(at)
+            try:
+                dt = datetime.fromisoformat(at)
+            except ValueError:
+                return f"Error: invalid ISO datetime format '{at}'. Expected format: YYYY-MM-DDTHH:MM:SS"
             at_ms = int(dt.timestamp() * 1000)
             schedule = CronSchedule(kind="at", at_ms=at_ms)
             delete_after = True

nanobot/agent/tools/filesystem.py

@@ -26,6 +26,8 @@ def _resolve_path(
 class ReadFileTool(Tool):
     """Tool to read file contents."""
 
+    _MAX_CHARS = 128_000  # ~128 KB — prevents OOM from reading huge files into LLM context
+
     def __init__(self, workspace: Path | None = None, allowed_dir: Path | None = None):
         self._workspace = workspace
         self._allowed_dir = allowed_dir
@@ -54,7 +56,16 @@ class ReadFileTool(Tool):
             if not file_path.is_file():
                 return f"Error: Not a file: {path}"
 
+            size = file_path.stat().st_size
+            if size > self._MAX_CHARS * 4:  # rough upper bound (UTF-8 chars ≤ 4 bytes)
+                return (
+                    f"Error: File too large ({size:,} bytes). "
+                    f"Use exec tool with head/tail/grep to read portions."
+                )
+
             content = file_path.read_text(encoding="utf-8")
+            if len(content) > self._MAX_CHARS:
+                return content[: self._MAX_CHARS] + f"\n\n... (truncated — file is {len(content):,} chars, limit {self._MAX_CHARS:,})"
             return content
         except PermissionError as e:
             return f"Error: {e}"

nanobot/channels/discord.py

@@ -54,6 +54,7 @@ class DiscordChannel(BaseChannel):
         self._heartbeat_task: asyncio.Task | None = None
         self._typing_tasks: dict[str, asyncio.Task] = {}
         self._http: httpx.AsyncClient | None = None
+        self._bot_user_id: str | None = None
 
     async def start(self) -> None:
         """Start the Discord gateway connection."""
@@ -170,6 +171,10 @@ class DiscordChannel(BaseChannel):
                 await self._identify()
             elif op == 0 and event_type == "READY":
                 logger.info("Discord gateway READY")
+                # Capture bot user ID for mention detection
+                user_data = payload.get("user") or {}
+                self._bot_user_id = user_data.get("id")
+                logger.info("Discord bot connected as user {}", self._bot_user_id)
             elif op == 0 and event_type == "MESSAGE_CREATE":
                 await self._handle_message_create(payload)
             elif op == 7:
@@ -226,6 +231,7 @@ class DiscordChannel(BaseChannel):
         sender_id = str(author.get("id", ""))
         channel_id = str(payload.get("channel_id", ""))
         content = payload.get("content") or ""
+        guild_id = payload.get("guild_id")
 
         if not sender_id or not channel_id:
             return
@@ -233,6 +239,11 @@ class DiscordChannel(BaseChannel):
         if not self.is_allowed(sender_id):
             return
 
+        # Check group channel policy (DMs always respond if is_allowed passes)
+        if guild_id is not None:
+            if not self._should_respond_in_group(payload, content):
+                return
+
         content_parts = [content] if content else []
         media_paths: list[str] = []
         media_dir = Path.home() / ".nanobot" / "media"
@@ -269,11 +280,32 @@ class DiscordChannel(BaseChannel):
             media=media_paths,
             metadata={
                 "message_id": str(payload.get("id", "")),
-                "guild_id": payload.get("guild_id"),
+                "guild_id": guild_id,
                 "reply_to": reply_to,
             },
         )
 
+    def _should_respond_in_group(self, payload: dict[str, Any], content: str) -> bool:
+        """Check if bot should respond in a group channel based on policy."""
+        if self.config.group_policy == "open":
+            return True
+
+        if self.config.group_policy == "mention":
+            # Check if bot was mentioned in the message
+            if self._bot_user_id:
+                # Check mentions array
+                mentions = payload.get("mentions") or []
+                for mention in mentions:
+                    if str(mention.get("id")) == self._bot_user_id:
+                        return True
+                # Also check content for mention format <@USER_ID>
+                if f"<@{self._bot_user_id}>" in content or f"<@!{self._bot_user_id}>" in content:
+                    return True
+            logger.debug("Discord message in {} ignored (bot not mentioned)", payload.get("channel_id"))
+            return False
+
+        return True
+
     async def _start_typing(self, channel_id: str) -> None:
         """Start periodic typing indicator for a channel."""
         await self._stop_typing(channel_id)

nanobot/channels/feishu.py

@@ -16,26 +16,9 @@ from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.config.schema import FeishuConfig
 
-try:
+import importlib.util
-    import lark_oapi as lark
+
-    from lark_oapi.api.im.v1 import (
+FEISHU_AVAILABLE = importlib.util.find_spec("lark_oapi") is not None
-        CreateFileRequest,
-        CreateFileRequestBody,
-        CreateImageRequest,
-        CreateImageRequestBody,
-        CreateMessageReactionRequest,
-        CreateMessageReactionRequestBody,
-        CreateMessageRequest,
-        CreateMessageRequestBody,
-        Emoji,
-        GetMessageResourceRequest,
-        P2ImMessageReceiveV1,
-    )
-    FEISHU_AVAILABLE = True
-except ImportError:
-    FEISHU_AVAILABLE = False
-    lark = None
-    Emoji = None
 
 # Message type display mapping
 MSG_TYPE_MAP = {
@@ -280,6 +263,7 @@ class FeishuChannel(BaseChannel):
             logger.error("Feishu app_id and app_secret not configured")
             return
 
+        import lark_oapi as lark
         self._running = True
         self._loop = asyncio.get_running_loop()
 
@@ -306,16 +290,28 @@ class FeishuChannel(BaseChannel):
             log_level=lark.LogLevel.INFO
         )
 
-        # Start WebSocket client in a separate thread with reconnect loop
+        # Start WebSocket client in a separate thread with reconnect loop.
+        # A dedicated event loop is created for this thread so that lark_oapi's
+        # module-level `loop = asyncio.get_event_loop()` picks up an idle loop
+        # instead of the already-running main asyncio loop, which would cause
+        # "This event loop is already running" errors.
         def run_ws():
-            while self._running:
+            import time
-                try:
+            import lark_oapi.ws.client as _lark_ws_client
-                    self._ws_client.start()
+            ws_loop = asyncio.new_event_loop()
-                except Exception as e:
+            asyncio.set_event_loop(ws_loop)
-                    logger.warning("Feishu WebSocket error: {}", e)
+            # Patch the module-level loop used by lark's ws Client.start()
-                if self._running:
+            _lark_ws_client.loop = ws_loop
-                    import time
+            try:
-                    time.sleep(5)
+                while self._running:
+                    try:
+                        self._ws_client.start()
+                    except Exception as e:
+                        logger.warning("Feishu WebSocket error: {}", e)
+                    if self._running:
+                        time.sleep(5)
+            finally:
+                ws_loop.close()
 
         self._ws_thread = threading.Thread(target=run_ws, daemon=True)
         self._ws_thread.start()
@@ -340,6 +336,7 @@ class FeishuChannel(BaseChannel):
 
     def _add_reaction_sync(self, message_id: str, emoji_type: str) -> None:
         """Sync helper for adding reaction (runs in thread pool)."""
+        from lark_oapi.api.im.v1 import CreateMessageReactionRequest, CreateMessageReactionRequestBody, Emoji
         try:
             request = CreateMessageReactionRequest.builder() \
                 .message_id(message_id) \
@@ -364,7 +361,7 @@ class FeishuChannel(BaseChannel):
 
         Common emoji types: THUMBSUP, OK, EYES, DONE, OnIt, HEART
         """
-        if not self._client or not Emoji:
+        if not self._client:
             return
 
         loop = asyncio.get_running_loop()
@@ -456,6 +453,7 @@ class FeishuChannel(BaseChannel):
 
     def _upload_image_sync(self, file_path: str) -> str | None:
         """Upload an image to Feishu and return the image_key."""
+        from lark_oapi.api.im.v1 import CreateImageRequest, CreateImageRequestBody
         try:
             with open(file_path, "rb") as f:
                 request = CreateImageRequest.builder() \
@@ -479,6 +477,7 @@ class FeishuChannel(BaseChannel):
 
     def _upload_file_sync(self, file_path: str) -> str | None:
         """Upload a file to Feishu and return the file_key."""
+        from lark_oapi.api.im.v1 import CreateFileRequest, CreateFileRequestBody
         ext = os.path.splitext(file_path)[1].lower()
         file_type = self._FILE_TYPE_MAP.get(ext, "stream")
         file_name = os.path.basename(file_path)
@@ -506,6 +505,7 @@ class FeishuChannel(BaseChannel):
 
     def _download_image_sync(self, message_id: str, image_key: str) -> tuple[bytes | None, str | None]:
         """Download an image from Feishu message by message_id and image_key."""
+        from lark_oapi.api.im.v1 import GetMessageResourceRequest
         try:
             request = GetMessageResourceRequest.builder() \
                 .message_id(message_id) \
@@ -530,6 +530,13 @@ class FeishuChannel(BaseChannel):
         self, message_id: str, file_key: str, resource_type: str = "file"
     ) -> tuple[bytes | None, str | None]:
         """Download a file/audio/media from a Feishu message by message_id and file_key."""
+        from lark_oapi.api.im.v1 import GetMessageResourceRequest
+
+        # Feishu API only accepts 'image' or 'file' as type parameter
+        # Convert 'audio' to 'file' for API compatibility
+        if resource_type == "audio":
+            resource_type = "file"
+
         try:
             request = (
                 GetMessageResourceRequest.builder()
@@ -598,6 +605,7 @@ class FeishuChannel(BaseChannel):
 
     def _send_message_sync(self, receive_id_type: str, receive_id: str, msg_type: str, content: str) -> bool:
         """Send a single message (text/image/file/interactive) synchronously."""
+        from lark_oapi.api.im.v1 import CreateMessageRequest, CreateMessageRequestBody
         try:
             request = CreateMessageRequest.builder() \
                 .receive_id_type(receive_id_type) \

nanobot/channels/qq.py

@@ -56,6 +56,7 @@ class QQChannel(BaseChannel):
         self.config: QQConfig = config
         self._client: "botpy.Client | None" = None
         self._processed_ids: deque = deque(maxlen=1000)
+        self._msg_seq: int = 1  # 消息序列号，避免被 QQ API 去重
 
     async def start(self) -> None:
         """Start the QQ bot."""
@@ -102,11 +103,13 @@ class QQChannel(BaseChannel):
             return
         try:
             msg_id = msg.metadata.get("message_id")
+            self._msg_seq += 1  # 递增序列号
             await self._client.api.post_c2c_message(
                 openid=msg.chat_id,
                 msg_type=0,
                 content=msg.content,
                 msg_id=msg_id,
+                msg_seq=self._msg_seq,  # 添加序列号避免去重
             )
         except Exception as e:
             logger.error("Error sending QQ message: {}", e)
@@ -133,3 +136,4 @@ class QQChannel(BaseChannel):
             )
         except Exception:
             logger.exception("Error handling QQ message")
+

nanobot/config/schema.py

@@ -66,6 +66,7 @@ class DiscordConfig(Base):
     allow_from: list[str] = Field(default_factory=list)  # Allowed user IDs
     gateway_url: str = "wss://gateway.discord.gg/?v=10&encoding=json"
     intents: int = 37377  # GUILDS + GUILD_MESSAGES + DIRECT_MESSAGES + MESSAGE_CONTENT
+    group_policy: Literal["mention", "open"] = "mention"
 
 
 class MatrixConfig(Base):

nanobot/providers/custom_provider.py

@@ -2,6 +2,7 @@
 
 from __future__ import annotations
 
+import uuid
 from typing import Any
 
 import json_repair
@@ -15,7 +16,12 @@ class CustomProvider(LLMProvider):
     def __init__(self, api_key: str = "no-key", api_base: str = "http://localhost:8000/v1", default_model: str = "default"):
         super().__init__(api_key, api_base)
         self.default_model = default_model
-        self._client = AsyncOpenAI(api_key=api_key, base_url=api_base)
+        # Keep affinity stable for this provider instance to improve backend cache locality.
+        self._client = AsyncOpenAI(
+            api_key=api_key,
+            base_url=api_base,
+            default_headers={"x-session-affinity": uuid.uuid4().hex},
+        )
 
     async def chat(self, messages: list[dict[str, Any]], tools: list[dict[str, Any]] | None = None,
                    model: str | None = None, max_tokens: int = 4096, temperature: float = 0.7,

nanobot/providers/openai_codex_provider.py

@@ -52,6 +52,9 @@ class OpenAICodexProvider(LLMProvider):
             "parallel_tool_calls": True,
         }
 
+        if reasoning_effort:
+            body["reasoning"] = {"effort": reasoning_effort}
+
         if tools:
             body["tools"] = _convert_tools(tools)
 

pyproject.toml

@@ -42,6 +42,7 @@ dependencies = [
     "prompt-toolkit>=3.0.50,<4.0.0",
     "mcp>=1.26.0,<2.0.0",
     "json-repair>=0.57.0,<1.0.0",
+    "chardet>=3.0.2,<6.0.0",
     "openai>=2.8.0",
 ]
 
@@ -55,6 +56,9 @@ dev = [
     "pytest>=9.0.0,<10.0.0",
     "pytest-asyncio>=1.3.0,<2.0.0",
     "ruff>=0.1.0",
+    "matrix-nio[e2e]>=0.25.2",
+    "mistune>=3.0.0,<4.0.0",
+    "nh3>=0.2.17,<1.0.0",
 ]
 
 [project.scripts]

tests/test_context_prompt_cache.py

@@ -40,7 +40,7 @@ def test_system_prompt_stays_stable_when_clock_changes(tmp_path, monkeypatch) ->
 
 
 def test_runtime_context_is_separate_untrusted_user_message(tmp_path) -> None:
-    """Runtime metadata should be a separate user message before the actual user message."""
+    """Runtime metadata should be merged with the user message."""
     workspace = _make_workspace(tmp_path)
     builder = ContextBuilder(workspace)
 
@@ -54,13 +54,12 @@ def test_runtime_context_is_separate_untrusted_user_message(tmp_path) -> None:
     assert messages[0]["role"] == "system"
     assert "## Current Session" not in messages[0]["content"]
 
-    assert messages[-2]["role"] == "user"
+    # Runtime context is now merged with user message into a single message
-    runtime_content = messages[-2]["content"]
-    assert isinstance(runtime_content, str)
-    assert ContextBuilder._RUNTIME_CONTEXT_TAG in runtime_content
-    assert "Current Time:" in runtime_content
-    assert "Channel: cli" in runtime_content
-    assert "Chat ID: direct" in runtime_content
-
     assert messages[-1]["role"] == "user"
-    assert messages[-1]["content"] == "Return exactly: OK"
+    user_content = messages[-1]["content"]
+    assert isinstance(user_content, str)
+    assert ContextBuilder._RUNTIME_CONTEXT_TAG in user_content
+    assert "Current Time:" in user_content
+    assert "Channel: cli" in user_content
+    assert "Chat ID: direct" in user_content
+    assert "Return exactly: OK" in user_content

tests/test_cron_commands.py

@@ -1,29 +0,0 @@
-from typer.testing import CliRunner
-
-from nanobot.cli.commands import app
-
-runner = CliRunner()
-
-
-def test_cron_add_rejects_invalid_timezone(monkeypatch, tmp_path) -> None:
-    monkeypatch.setattr("nanobot.config.loader.get_data_dir", lambda: tmp_path)
-
-    result = runner.invoke(
-        app,
-        [
-            "cron",
-            "add",
-            "--name",
-            "demo",
-            "--message",
-            "hello",
-            "--cron",
-            "0 9 * * *",
-            "--tz",
-            "America/Vancovuer",
-        ],
-    )
-
-    assert result.exit_code == 1
-    assert "Error: unknown timezone 'America/Vancovuer'" in result.stdout
-    assert not (tmp_path / "cron" / "jobs.json").exists()

tests/test_cron_service.py

@@ -48,6 +48,8 @@ async def test_running_service_honors_external_disable(tmp_path) -> None:
     )
     await service.start()
     try:
+        # Wait slightly to ensure file mtime is definitively different
+        await asyncio.sleep(0.05)
         external = CronService(store_path)
         updated = external.enable_job(job.id, enabled=False)
         assert updated is not None

tests/test_matrix_channel.py

@@ -159,6 +159,7 @@ class _FakeAsyncClient:
 
 
 def _make_config(**kwargs) -> MatrixConfig:
+    kwargs.setdefault("allow_from", ["*"])
     return MatrixConfig(
         enabled=True,
         homeserver="https://matrix.org",
@@ -274,7 +275,7 @@ async def test_stop_stops_sync_forever_before_close(monkeypatch) -> None:
 
 
 @pytest.mark.asyncio
-async def test_room_invite_joins_when_allow_list_is_empty() -> None:
+async def test_room_invite_ignores_when_allow_list_is_empty() -> None:
     channel = MatrixChannel(_make_config(allow_from=[]), MessageBus())
     client = _FakeAsyncClient("", "", "", None)
     channel.client = client
@@ -284,9 +285,22 @@ async def test_room_invite_joins_when_allow_list_is_empty() -> None:
 
     await channel._on_room_invite(room, event)
 
-    assert client.join_calls == ["!room:matrix.org"]
+    assert client.join_calls == []
 
 
+@pytest.mark.asyncio
+async def test_room_invite_joins_when_sender_allowed() -> None:
+    channel = MatrixChannel(_make_config(allow_from=["@alice:matrix.org"]), MessageBus())
+    client = _FakeAsyncClient("", "", "", None)
+    channel.client = client
+
+    room = SimpleNamespace(room_id="!room:matrix.org")
+    event = SimpleNamespace(sender="@alice:matrix.org")
+
+    await channel._on_room_invite(room, event)
+
+    assert client.join_calls == ["!room:matrix.org"]
+
 @pytest.mark.asyncio
 async def test_room_invite_respects_allow_list_when_configured() -> None:
     channel = MatrixChannel(_make_config(allow_from=["@bob:matrix.org"]), MessageBus())
@@ -1163,6 +1177,8 @@ async def test_send_progress_keeps_typing_keepalive_running() -> None:
     assert "!room:matrix.org" in channel._typing_tasks
     assert client.typing_calls[-1] == ("!room:matrix.org", True, TYPING_NOTICE_TIMEOUT_MS)
 
+    await channel.stop()
+
 
 @pytest.mark.asyncio
 async def test_send_clears_typing_when_send_fails() -> None: