Merge remote-tracking branch 'origin/main' into pr-1522

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/agent/tools/mcp.py

@@ -58,17 +58,48 @@ async def connect_mcp_servers(
 ) -> None:
     """Connect to configured MCP servers and register their tools."""
     from mcp import ClientSession, StdioServerParameters
+    from mcp.client.sse import sse_client
     from mcp.client.stdio import stdio_client
+    from mcp.client.streamable_http import streamable_http_client
 
     for name, cfg in mcp_servers.items():
         try:
-            if cfg.command:
+            transport_type = cfg.type
+            if not transport_type:
+                if cfg.command:
+                    transport_type = "stdio"
+                elif cfg.url:
+                    # Convention: URLs ending with /sse use SSE transport; others use streamableHttp
+                    transport_type = (
+                        "sse" if cfg.url.rstrip("/").endswith("/sse") else "streamableHttp"
+                    )
+                else:
+                    logger.warning("MCP server '{}': no command or url configured, skipping", name)
+                    continue
+
+            if transport_type == "stdio":
                 params = StdioServerParameters(
                     command=cfg.command, args=cfg.args, env=cfg.env or None
                 )
                 read, write = await stack.enter_async_context(stdio_client(params))
-            elif cfg.url:
-                from mcp.client.streamable_http import streamable_http_client
+            elif transport_type == "sse":
+                def httpx_client_factory(
+                    headers: dict[str, str] | None = None,
+                    timeout: httpx.Timeout | None = None,
+                    auth: httpx.Auth | None = None,
+                ) -> httpx.AsyncClient:
+                    merged_headers = {**(cfg.headers or {}), **(headers or {})}
+                    return httpx.AsyncClient(
+                        headers=merged_headers or None,
+                        follow_redirects=True,
+                        timeout=timeout,
+                        auth=auth,
+                    )
+
+                read, write = await stack.enter_async_context(
+                    sse_client(cfg.url, httpx_client_factory=httpx_client_factory)
+                )
+            elif transport_type == "streamableHttp":
                 # Always provide an explicit httpx client so MCP HTTP transport does not
                 # inherit httpx's default 5s timeout and preempt the higher-level tool timeout.
                 http_client = await stack.enter_async_context(
@@ -82,7 +113,7 @@ async def connect_mcp_servers(
                     streamable_http_client(cfg.url, http_client=http_client)
                 )
             else:
-                logger.warning("MCP server '{}': no command or url configured, skipping", name)
+                logger.warning("MCP server '{}': unknown transport type '{}'", name, transport_type)
                 continue
 
             session = await stack.enter_async_context(ClientSession(read, write))

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 lark_oapi as lark
-    from lark_oapi.api.im.v1 import (
-        CreateFileRequest,
-        CreateFileRequestBody,
-        CreateImageRequest,
-        CreateImageRequestBody,
-        CreateMessageReactionRequest,
-        CreateMessageReactionRequestBody,
-        CreateMessageRequest,
-        CreateMessageRequestBody,
-        Emoji,
-        GetMessageResourceRequest,
-        P2ImMessageReceiveV1,
-    )
-    FEISHU_AVAILABLE = True
-except ImportError:
-    FEISHU_AVAILABLE = False
-    lark = None
-    Emoji = None
+import importlib.util
+
+FEISHU_AVAILABLE = importlib.util.find_spec("lark_oapi") is not 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:
-                try:
-                    self._ws_client.start()
-                except Exception as e:
-                    logger.warning("Feishu WebSocket error: {}", e)
-                if self._running:
-                    import time
-                    time.sleep(5)
+            import time
+            import lark_oapi.ws.client as _lark_ws_client
+            ws_loop = asyncio.new_event_loop()
+            asyncio.set_event_loop(ws_loop)
+            # Patch the module-level loop used by lark's ws Client.start()
+            _lark_ws_client.loop = ws_loop
+            try:
+                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/cli/commands.py

@@ -244,13 +244,15 @@ def _make_provider(config: Config):
 @app.command()
 def gateway(
     port: int = typer.Option(18790, "--port", "-p", help="Gateway port"),
+    workspace: str | None = typer.Option(None, "--workspace", "-w", help="Workspace directory"),
+    config: str | None = typer.Option(None, "--config", "-c", help="Config file path"),
     verbose: bool = typer.Option(False, "--verbose", "-v", help="Verbose output"),
 ):
     """Start the nanobot gateway."""
     from nanobot.agent.loop import AgentLoop
     from nanobot.bus.queue import MessageBus
     from nanobot.channels.manager import ChannelManager
-    from nanobot.config.loader import get_data_dir, load_config
+    from nanobot.config.loader import load_config
     from nanobot.cron.service import CronService
     from nanobot.cron.types import CronJob
     from nanobot.heartbeat.service import HeartbeatService
@@ -260,16 +262,20 @@ def gateway(
         import logging
         logging.basicConfig(level=logging.DEBUG)
 
-    console.print(f"{__logo__} Starting nanobot gateway on port {port}...")
+    config_path = Path(config) if config else None
+    config = load_config(config_path)
+    if workspace:
+        config.agents.defaults.workspace = workspace
 
-    config = load_config()
+    console.print(f"{__logo__} Starting nanobot gateway on port {port}...")
     sync_workspace_templates(config.workspace_path)
     bus = MessageBus()
     provider = _make_provider(config)
     session_manager = SessionManager(config.workspace_path)
 
     # Create cron service first (callback set after agent creation)
-    cron_store_path = get_data_dir() / "cron" / "jobs.json"
+    # Use workspace path for per-instance cron store
+    cron_store_path = config.workspace_path / "cron" / "jobs.json"
     cron = CronService(cron_store_path)
 
     # Create agent with cron service
@@ -511,12 +517,17 @@ def agent(
         else:
             cli_channel, cli_chat_id = "cli", session_id
 
-        def _exit_on_sigint(signum, frame):
+        def _handle_signal(signum, frame):
+            sig_name = signal.Signals(signum).name
             _restore_terminal()
-            console.print("\nGoodbye!")
-            os._exit(0)
+            console.print(f"\nReceived {sig_name}, goodbye!")
+            sys.exit(0)
 
-        signal.signal(signal.SIGINT, _exit_on_sigint)
+        signal.signal(signal.SIGINT, _handle_signal)
+        signal.signal(signal.SIGTERM, _handle_signal)
+        signal.signal(signal.SIGHUP, _handle_signal)
+        # Ignore SIGPIPE to prevent silent process termination when writing to closed pipes
+        signal.signal(signal.SIGPIPE, signal.SIG_IGN)
 
         async def run_interactive():
             bus_task = asyncio.create_task(agent_loop.run())

nanobot/config/schema.py

@@ -29,7 +29,9 @@ class TelegramConfig(Base):
     enabled: bool = False
     token: str = ""  # Bot token from @BotFather
     allow_from: list[str] = Field(default_factory=list)  # Allowed user IDs or usernames
-    proxy: str | None = None  # HTTP/SOCKS5 proxy URL, e.g. "http://127.0.0.1:7890" or "socks5://127.0.0.1:1080"
+    proxy: str | None = (
+        None  # HTTP/SOCKS5 proxy URL, e.g. "http://127.0.0.1:7890" or "socks5://127.0.0.1:1080"
+    )
     reply_to_message: bool = False  # If true, bot replies quote the original message
 
 
@@ -42,7 +44,9 @@ class FeishuConfig(Base):
     encrypt_key: str = ""  # Encrypt Key for event subscription (optional)
     verification_token: str = ""  # Verification Token for event subscription (optional)
     allow_from: list[str] = Field(default_factory=list)  # Allowed user open_ids
-    react_emoji: str = "THUMBSUP"  # Emoji type for message reactions (e.g. THUMBSUP, OK, DONE, SMILE)
+    react_emoji: str = (
+        "THUMBSUP"  # Emoji type for message reactions (e.g. THUMBSUP, OK, DONE, SMILE)
+    )
 
 
 class DingTalkConfig(Base):
@@ -62,6 +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):
@@ -72,9 +77,13 @@ class MatrixConfig(Base):
     access_token: str = ""
     user_id: str = ""  # @bot:matrix.org
     device_id: str = ""
-    e2ee_enabled: bool = True # Enable Matrix E2EE support (encryption + encrypted room handling).
-    sync_stop_grace_seconds: int = 2 # Max seconds to wait for sync_forever to stop gracefully before cancellation fallback.
-    max_media_bytes: int = 20 * 1024 * 1024 # Max attachment size accepted for Matrix media handling (inbound + outbound).
+    e2ee_enabled: bool = True  # Enable Matrix E2EE support (encryption + encrypted room handling).
+    sync_stop_grace_seconds: int = (
+        2  # Max seconds to wait for sync_forever to stop gracefully before cancellation fallback.
+    )
+    max_media_bytes: int = (
+        20 * 1024 * 1024
+    )  # Max attachment size accepted for Matrix media handling (inbound + outbound).
     allow_from: list[str] = Field(default_factory=list)
     group_policy: Literal["open", "mention", "allowlist"] = "open"
     group_allow_from: list[str] = Field(default_factory=list)
@@ -105,7 +114,9 @@ class EmailConfig(Base):
     from_address: str = ""
 
     # Behavior
-    auto_reply_enabled: bool = True  # If false, inbound email is read but no automatic reply is sent
+    auto_reply_enabled: bool = (
+        True  # If false, inbound email is read but no automatic reply is sent
+    )
     poll_interval_seconds: int = 30
     mark_seen: bool = True
     max_body_chars: int = 12000
@@ -183,27 +194,32 @@ class QQConfig(Base):
     enabled: bool = False
     app_id: str = ""  # 机器人 ID (AppID) from q.qq.com
     secret: str = ""  # 机器人密钥 (AppSecret) from q.qq.com
-    allow_from: list[str] = Field(default_factory=list)  # Allowed user openids (empty = public access)
+    allow_from: list[str] = Field(
+        default_factory=list
+    )  # Allowed user openids (empty = public access)
+
 
 class MatrixConfig(Base):
     """Matrix (Element) channel configuration."""
+
     enabled: bool = False
     homeserver: str = "https://matrix.org"
     access_token: str = ""
-    user_id: str = ""                       # e.g. @bot:matrix.org
+    user_id: str = ""  # e.g. @bot:matrix.org
     device_id: str = ""
-    e2ee_enabled: bool = True               # end-to-end encryption support
-    sync_stop_grace_seconds: int = 2        # graceful sync_forever shutdown timeout
-    max_media_bytes: int = 20 * 1024 * 1024 # inbound + outbound attachment limit
+    e2ee_enabled: bool = True  # end-to-end encryption support
+    sync_stop_grace_seconds: int = 2  # graceful sync_forever shutdown timeout
+    max_media_bytes: int = 20 * 1024 * 1024  # inbound + outbound attachment limit
     allow_from: list[str] = Field(default_factory=list)
     group_policy: Literal["open", "mention", "allowlist"] = "open"
     group_allow_from: list[str] = Field(default_factory=list)
     allow_room_mentions: bool = False
 
+
 class ChannelsConfig(Base):
     """Configuration for chat channels."""
 
-    send_progress: bool = True    # stream agent's text progress to the channel
+    send_progress: bool = True  # stream agent's text progress to the channel
     send_tool_hints: bool = False  # stream tool-call hints (e.g. read_file("…"))
     whatsapp: WhatsAppConfig = Field(default_factory=WhatsAppConfig)
     telegram: TelegramConfig = Field(default_factory=TelegramConfig)
@@ -222,7 +238,9 @@ class AgentDefaults(Base):
 
     workspace: str = "~/.nanobot/workspace"
     model: str = "anthropic/claude-opus-4-5"
-    provider: str = "auto"  # Provider name (e.g. "anthropic", "openrouter") or "auto" for auto-detection
+    provider: str = (
+        "auto"  # Provider name (e.g. "anthropic", "openrouter") or "auto" for auto-detection
+    )
     max_tokens: int = 8192
     temperature: float = 0.1
     max_tool_iterations: int = 40
@@ -260,8 +278,12 @@ class ProvidersConfig(Base):
     moonshot: ProviderConfig = Field(default_factory=ProviderConfig)
     minimax: ProviderConfig = Field(default_factory=ProviderConfig)
     aihubmix: ProviderConfig = Field(default_factory=ProviderConfig)  # AiHubMix API gateway
-    siliconflow: ProviderConfig = Field(default_factory=ProviderConfig)  # SiliconFlow (硅基流动) API gateway
-    volcengine: ProviderConfig = Field(default_factory=ProviderConfig)  # VolcEngine (火山引擎) API gateway
+    siliconflow: ProviderConfig = Field(
+        default_factory=ProviderConfig
+    )  # SiliconFlow (硅基流动) API gateway
+    volcengine: ProviderConfig = Field(
+        default_factory=ProviderConfig
+    )  # VolcEngine (火山引擎) API gateway
     openai_codex: ProviderConfig = Field(default_factory=ProviderConfig)  # OpenAI Codex (OAuth)
     github_copilot: ProviderConfig = Field(default_factory=ProviderConfig)  # Github Copilot (OAuth)
 
@@ -291,7 +313,9 @@ class WebSearchConfig(Base):
 class WebToolsConfig(Base):
     """Web tools configuration."""
 
-    proxy: str | None = None  # HTTP/SOCKS5 proxy URL, e.g. "http://127.0.0.1:7890" or "socks5://127.0.0.1:1080"
+    proxy: str | None = (
+        None  # HTTP/SOCKS5 proxy URL, e.g. "http://127.0.0.1:7890" or "socks5://127.0.0.1:1080"
+    )
     search: WebSearchConfig = Field(default_factory=WebSearchConfig)
 
 
@@ -305,12 +329,13 @@ class ExecToolConfig(Base):
 class MCPServerConfig(Base):
     """MCP server connection configuration (stdio or HTTP)."""
 
+    type: Literal["stdio", "sse", "streamableHttp"] | None = None  # auto-detected if omitted
     command: str = ""  # Stdio: command to run (e.g. "npx")
     args: list[str] = Field(default_factory=list)  # Stdio: command arguments
     env: dict[str, str] = Field(default_factory=dict)  # Stdio: extra env vars
-    url: str = ""  # HTTP: streamable HTTP endpoint URL
-    headers: dict[str, str] = Field(default_factory=dict)  # HTTP: Custom HTTP Headers
-    tool_timeout: int = 30  # Seconds before a tool call is cancelled
+    url: str = ""  # HTTP/SSE: endpoint URL
+    headers: dict[str, str] = Field(default_factory=dict)  # HTTP/SSE: custom headers
+    tool_timeout: int = 30  # seconds before a tool call is cancelled
 
 
 class ToolsConfig(Base):
@@ -336,7 +361,9 @@ class Config(BaseSettings):
         """Get expanded workspace path."""
         return Path(self.agents.defaults.workspace).expanduser()
 
-    def _match_provider(self, model: str | None = None) -> tuple["ProviderConfig | None", str | None]:
+    def _match_provider(
+        self, model: str | None = None
+    ) -> tuple["ProviderConfig | None", str | None]:
         """Match provider config and its registry name. Returns (config, spec_name)."""
         from nanobot.providers.registry import PROVIDERS
 

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)