diff --git a/.gitignore b/.gitignore index 742d593..374875a 100644 --- a/.gitignore +++ b/.gitignore @@ -1,3 +1,4 @@ +.worktrees/ .assets .env *.pyc diff --git a/README.md b/README.md index 33cdeee..0c49608 100644 --- a/README.md +++ b/README.md @@ -12,11 +12,11 @@

-🐈 **nanobot** is an **ultra-lightweight** personal AI assistant inspired by [OpenClaw](https://github.com/openclaw/openclaw) +🐈 **nanobot** is an **ultra-lightweight** personal AI assistant inspired by [OpenClaw](https://github.com/openclaw/openclaw). -⚑️ Delivers core agent functionality in just **~4,000** lines of code β€” **99% smaller** than Clawdbot's 430k+ lines. +⚑️ Delivers core agent functionality with **99% fewer lines of code** than OpenClaw. -πŸ“ Real-time line count: **3,935 lines** (run `bash core_agent_lines.sh` to verify anytime) +πŸ“ Real-time line count: run `bash core_agent_lines.sh` to verify anytime. ## πŸ“’ News @@ -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) β€” Only respond when @mentioned +> - `"open"` β€” Respond to all messages +> DMs always respond when the sender is in `allowFrom`. + **5. Invite the bot** - OAuth2 β†’ URL Generator - Scopes: `bot` @@ -658,6 +664,7 @@ Config file: `~/.nanobot/config.json` > - **Zhipu Coding Plan**: If you're on Zhipu's coding plan, set `"apiBase": "https://open.bigmodel.cn/api/coding/paas/v4"` in your zhipu provider config. > - **MiniMax (Mainland China)**: If your API key is from MiniMax's mainland China platform (minimaxi.com), set `"apiBase": "https://api.minimaxi.com/v1"` in your minimax provider config. > - **VolcEngine Coding Plan**: If you're on VolcEngine's coding plan, set `"apiBase": "https://ark.cn-beijing.volces.com/api/coding/v3"` in your volcengine provider config. +> - **Alibaba Cloud Coding Plan**: If you're on the Alibaba Cloud Coding Plan (BaiLian), set `"apiBase": "https://coding.dashscope.aliyuncs.com/v1"` in your dashscope provider config. | Provider | Purpose | Get API Key | |----------|---------|-------------| @@ -884,6 +891,33 @@ MCP tools are automatically discovered and registered on startup. The LLM can us | `channels.*.allowFrom` | `[]` (allow all) | Whitelist of user IDs. Empty = allow everyone; non-empty = only listed users can interact. | +## Multiple Instances + +Run multiple nanobot instances simultaneously, each with its own workspace and configuration. + +```bash +# Instance A - Telegram bot +nanobot gateway -w ~/.nanobot/botA -p 18791 + +# Instance B - Discord bot +nanobot gateway -w ~/.nanobot/botB -p 18792 + +# Instance C - Using custom config file +nanobot gateway -w ~/.nanobot/botC -c ~/.nanobot/botC/config.json -p 18793 +``` + +| Option | Short | Description | +|--------|-------|-------------| +| `--workspace` | `-w` | Workspace directory (default: `~/.nanobot/workspace`) | +| `--config` | `-c` | Config file path (default: `~/.nanobot/config.json`) | +| `--port` | `-p` | Gateway port (default: `18790`) | + +Each instance has its own: +- Workspace directory (MEMORY.md, HEARTBEAT.md, session files) +- Cron jobs storage (`workspace/cron/jobs.json`) +- Configuration (if using `--config`) + + ## CLI Reference | Command | Description | diff --git a/nanobot/agent/context.py b/nanobot/agent/context.py index df4825f..27511fa 100644 --- a/nanobot/agent/context.py +++ b/nanobot/agent/context.py @@ -10,6 +10,7 @@ from typing import Any from nanobot.agent.memory import MemoryStore from nanobot.agent.skills import SkillsLoader +from nanobot.utils.helpers import detect_image_mime class ContextBuilder: @@ -136,10 +137,14 @@ Reply directly with text for conversations. Only use the 'message' tool to send images = [] for path in media: p = Path(path) - mime, _ = mimetypes.guess_type(path) - if not p.is_file() or not mime or not mime.startswith("image/"): + if not p.is_file(): continue - b64 = base64.b64encode(p.read_bytes()).decode() + raw = p.read_bytes() + # Detect real MIME type from magic bytes; fallback to filename guess + mime = detect_image_mime(raw) or mimetypes.guess_type(path)[0] + if not mime or not mime.startswith("image/"): + continue + b64 = base64.b64encode(raw).decode() images.append({"type": "image_url", "image_url": {"url": f"data:{mime};base64,{b64}"}}) if not images: diff --git a/nanobot/agent/loop.py b/nanobot/agent/loop.py index 65a62e5..7f129a2 100644 --- a/nanobot/agent/loop.py +++ b/nanobot/agent/loop.py @@ -202,9 +202,18 @@ class AgentLoop: if response.has_tool_calls: if on_progress: - clean = self._strip_think(response.content) - if clean: - await on_progress(clean) + thoughts = [ + self._strip_think(response.content), + response.reasoning_content, + *( + f"Thinking [{b.get('signature', '...')}]:\n{b.get('thought', '...')}" + for b in (response.thinking_blocks or []) + if isinstance(b, dict) and "signature" in b + ), + ] + combined_thoughts = "\n\n".join(filter(None, thoughts)) + if combined_thoughts: + await on_progress(combined_thoughts) await on_progress(self._tool_hint(response.tool_calls), tool_hint=True) tool_call_dicts = [ diff --git a/nanobot/agent/memory.py b/nanobot/agent/memory.py index 93c1825..21fe77d 100644 --- a/nanobot/agent/memory.py +++ b/nanobot/agent/memory.py @@ -128,6 +128,13 @@ class MemoryStore: # Some providers return arguments as a JSON string instead of dict if isinstance(args, str): args = json.loads(args) + # Some providers return arguments as a list (handle edge case) + if isinstance(args, list): + if args and isinstance(args[0], dict): + args = args[0] + else: + logger.warning("Memory consolidation: unexpected arguments as empty or non-dict list") + return False if not isinstance(args, dict): logger.warning("Memory consolidation: unexpected arguments type {}", type(args).__name__) return False diff --git a/nanobot/agent/tools/mcp.py b/nanobot/agent/tools/mcp.py index 37464e1..2cbffd0 100644 --- a/nanobot/agent/tools/mcp.py +++ b/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)) diff --git a/nanobot/channels/discord.py b/nanobot/channels/discord.py index 57e5922..c868bbf 100644 --- a/nanobot/channels/discord.py +++ b/nanobot/channels/discord.py @@ -13,34 +13,13 @@ from nanobot.bus.events import OutboundMessage from nanobot.bus.queue import MessageBus from nanobot.channels.base import BaseChannel from nanobot.config.schema import DiscordConfig +from nanobot.utils.helpers import split_message DISCORD_API_BASE = "https://discord.com/api/v10" MAX_ATTACHMENT_BYTES = 20 * 1024 * 1024 # 20MB MAX_MESSAGE_LEN = 2000 # Discord message character limit -def _split_message(content: str, max_len: int = MAX_MESSAGE_LEN) -> list[str]: - """Split content into chunks within max_len, preferring line breaks.""" - if not content: - return [] - if len(content) <= max_len: - return [content] - chunks: list[str] = [] - while content: - if len(content) <= max_len: - chunks.append(content) - break - cut = content[:max_len] - pos = cut.rfind('\n') - if pos <= 0: - pos = cut.rfind(' ') - if pos <= 0: - pos = max_len - chunks.append(content[:pos]) - content = content[pos:].lstrip() - return chunks - - class DiscordChannel(BaseChannel): """Discord channel using Gateway websocket.""" @@ -54,6 +33,7 @@ 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.""" @@ -104,7 +84,7 @@ class DiscordChannel(BaseChannel): headers = {"Authorization": f"Bot {self.config.token}"} try: - chunks = _split_message(msg.content or "") + chunks = split_message(msg.content or "", MAX_MESSAGE_LEN) if not chunks: return @@ -170,6 +150,10 @@ 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 +210,7 @@ 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 +218,11 @@ 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 +259,32 @@ 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) diff --git a/nanobot/channels/feishu.py b/nanobot/channels/feishu.py index 0cd84c3..8f69c09 100644 --- a/nanobot/channels/feishu.py +++ b/nanobot/channels/feishu.py @@ -290,16 +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() @@ -398,6 +410,34 @@ class FeishuChannel(BaseChannel): elements.extend(self._split_headings(remaining)) return elements or [{"tag": "markdown", "content": content}] + @staticmethod + def _split_elements_by_table_limit(elements: list[dict], max_tables: int = 1) -> list[list[dict]]: + """Split card elements into groups with at most *max_tables* table elements each. + + Feishu cards have a hard limit of one table per card (API error 11310). + When the rendered content contains multiple markdown tables each table is + placed in a separate card message so every table reaches the user. + """ + if not elements: + return [[]] + groups: list[list[dict]] = [] + current: list[dict] = [] + table_count = 0 + for el in elements: + if el.get("tag") == "table": + if table_count >= max_tables: + if current: + groups.append(current) + current = [] + table_count = 0 + current.append(el) + table_count += 1 + else: + current.append(el) + if current: + groups.append(current) + return groups or [[]] + def _split_headings(self, content: str) -> list[dict]: """Split content by headings, converting headings to div elements.""" protected = content @@ -432,8 +472,124 @@ class FeishuChannel(BaseChannel): return elements or [{"tag": "markdown", "content": content}] + # ── Smart format detection ────────────────────────────────────────── + # Patterns that indicate "complex" markdown needing card rendering + _COMPLEX_MD_RE = re.compile( + r"```" # fenced code block + r"|^\|.+\|.*\n\s*\|[-:\s|]+\|" # markdown table (header + separator) + r"|^#{1,6}\s+" # headings + , re.MULTILINE, + ) + + # Simple markdown patterns (bold, italic, strikethrough) + _SIMPLE_MD_RE = re.compile( + r"\*\*.+?\*\*" # **bold** + r"|__.+?__" # __bold__ + r"|(? str: + """Determine the optimal Feishu message format for *content*. + + Returns one of: + - ``"text"`` – plain text, short and no markdown + - ``"post"`` – rich text (links only, moderate length) + - ``"interactive"`` – card with full markdown rendering + """ + stripped = content.strip() + + # Complex markdown (code blocks, tables, headings) β†’ always card + if cls._COMPLEX_MD_RE.search(stripped): + return "interactive" + + # Long content β†’ card (better readability with card layout) + if len(stripped) > cls._POST_MAX_LEN: + return "interactive" + + # Has bold/italic/strikethrough β†’ card (post format can't render these) + if cls._SIMPLE_MD_RE.search(stripped): + return "interactive" + + # Has list items β†’ card (post format can't render list bullets well) + if cls._LIST_RE.search(stripped) or cls._OLIST_RE.search(stripped): + return "interactive" + + # Has links β†’ post format (supports tags) + if cls._MD_LINK_RE.search(stripped): + return "post" + + # Short plain text β†’ text format + if len(stripped) <= cls._TEXT_MAX_LEN: + return "text" + + # Medium plain text without any formatting β†’ post format + return "post" + + @classmethod + def _markdown_to_post(cls, content: str) -> str: + """Convert markdown content to Feishu post message JSON. + + Handles links ``[text](url)`` as ``a`` tags; everything else as ``text`` tags. + Each line becomes a paragraph (row) in the post body. + """ + lines = content.strip().split("\n") + paragraphs: list[list[dict]] = [] + + for line in lines: + elements: list[dict] = [] + last_end = 0 + + for m in cls._MD_LINK_RE.finditer(line): + # Text before this link + before = line[last_end:m.start()] + if before: + elements.append({"tag": "text", "text": before}) + elements.append({ + "tag": "a", + "text": m.group(1), + "href": m.group(2), + }) + last_end = m.end() + + # Remaining text after last link + remaining = line[last_end:] + if remaining: + elements.append({"tag": "text", "text": remaining}) + + # Empty line β†’ empty paragraph for spacing + if not elements: + elements.append({"tag": "text", "text": ""}) + + paragraphs.append(elements) + + post_body = { + "zh_cn": { + "content": paragraphs, + } + } + return json.dumps(post_body, ensure_ascii=False) + _IMAGE_EXTS = {".png", ".jpg", ".jpeg", ".gif", ".bmp", ".webp", ".ico", ".tiff", ".tif"} _AUDIO_EXTS = {".opus"} + _VIDEO_EXTS = {".mp4", ".mov", ".avi"} _FILE_TYPE_MAP = { ".opus": "opus", ".mp4": "mp4", ".pdf": "pdf", ".doc": "doc", ".docx": "doc", ".xls": "xls", ".xlsx": "xls", ".ppt": "ppt", ".pptx": "ppt", @@ -642,18 +798,45 @@ class FeishuChannel(BaseChannel): else: key = await loop.run_in_executor(None, self._upload_file_sync, file_path) if key: - media_type = "audio" if ext in self._AUDIO_EXTS else "file" + # Use msg_type "media" for audio/video so users can play inline; + # "file" for everything else (documents, archives, etc.) + if ext in self._AUDIO_EXTS or ext in self._VIDEO_EXTS: + media_type = "media" + else: + media_type = "file" await loop.run_in_executor( None, self._send_message_sync, receive_id_type, msg.chat_id, media_type, json.dumps({"file_key": key}, ensure_ascii=False), ) if msg.content and msg.content.strip(): - card = {"config": {"wide_screen_mode": True}, "elements": self._build_card_elements(msg.content)} - await loop.run_in_executor( - None, self._send_message_sync, - receive_id_type, msg.chat_id, "interactive", json.dumps(card, ensure_ascii=False), - ) + fmt = self._detect_msg_format(msg.content) + + if fmt == "text": + # Short plain text – send as simple text message + text_body = json.dumps({"text": msg.content.strip()}, ensure_ascii=False) + await loop.run_in_executor( + None, self._send_message_sync, + receive_id_type, msg.chat_id, "text", text_body, + ) + + elif fmt == "post": + # Medium content with links – send as rich-text post + post_body = self._markdown_to_post(msg.content) + await loop.run_in_executor( + None, self._send_message_sync, + receive_id_type, msg.chat_id, "post", post_body, + ) + + else: + # Complex / long content – send as interactive card + elements = self._build_card_elements(msg.content) + for chunk in self._split_elements_by_table_limit(elements): + card = {"config": {"wide_screen_mode": True}, "elements": chunk} + await loop.run_in_executor( + None, self._send_message_sync, + receive_id_type, msg.chat_id, "interactive", json.dumps(card, ensure_ascii=False), + ) except Exception as e: logger.error("Error sending Feishu message: {}", e) diff --git a/nanobot/channels/telegram.py b/nanobot/channels/telegram.py index c290535..9097496 100644 --- a/nanobot/channels/telegram.py +++ b/nanobot/channels/telegram.py @@ -14,6 +14,9 @@ from nanobot.bus.events import OutboundMessage from nanobot.bus.queue import MessageBus from nanobot.channels.base import BaseChannel from nanobot.config.schema import TelegramConfig +from nanobot.utils.helpers import split_message + +TELEGRAM_MAX_MESSAGE_LEN = 4000 # Telegram message character limit def _markdown_to_telegram_html(text: str) -> str: @@ -79,26 +82,6 @@ def _markdown_to_telegram_html(text: str) -> str: return text -def _split_message(content: str, max_len: int = 4000) -> list[str]: - """Split content into chunks within max_len, preferring line breaks.""" - if len(content) <= max_len: - return [content] - chunks: list[str] = [] - while content: - if len(content) <= max_len: - chunks.append(content) - break - cut = content[:max_len] - pos = cut.rfind('\n') - if pos == -1: - pos = cut.rfind(' ') - if pos == -1: - pos = max_len - chunks.append(content[:pos]) - content = content[pos:].lstrip() - return chunks - - class TelegramChannel(BaseChannel): """ Telegram channel using long polling. @@ -225,7 +208,9 @@ class TelegramChannel(BaseChannel): logger.warning("Telegram bot not running") return - self._stop_typing(msg.chat_id) + # Only stop typing indicator for final responses + if not msg.metadata.get("_progress", False): + self._stop_typing(msg.chat_id) try: chat_id = int(msg.chat_id) @@ -269,23 +254,41 @@ class TelegramChannel(BaseChannel): # Send text content if msg.content and msg.content != "[empty message]": - for chunk in _split_message(msg.content): + is_progress = msg.metadata.get("_progress", False) + draft_id = msg.metadata.get("message_id") + + for chunk in split_message(msg.content, TELEGRAM_MAX_MESSAGE_LEN): try: html = _markdown_to_telegram_html(chunk) - await self._app.bot.send_message( - chat_id=chat_id, - text=html, - parse_mode="HTML", - reply_parameters=reply_params - ) + if is_progress and draft_id: + await self._app.bot.send_message_draft( + chat_id=chat_id, + draft_id=draft_id, + text=html, + parse_mode="HTML" + ) + else: + await self._app.bot.send_message( + chat_id=chat_id, + text=html, + parse_mode="HTML", + reply_parameters=reply_params + ) except Exception as e: logger.warning("HTML parse failed, falling back to plain text: {}", e) try: - await self._app.bot.send_message( - chat_id=chat_id, - text=chunk, - reply_parameters=reply_params - ) + if is_progress and draft_id: + await self._app.bot.send_message_draft( + chat_id=chat_id, + draft_id=draft_id, + text=chunk + ) + else: + await self._app.bot.send_message( + chat_id=chat_id, + text=chunk, + reply_parameters=reply_params + ) except Exception as e2: logger.error("Error sending Telegram message: {}", e2) diff --git a/nanobot/cli/commands.py b/nanobot/cli/commands.py index b75a2bc..eb3d833 100644 --- a/nanobot/cli/commands.py +++ b/nanobot/cli/commands.py @@ -7,6 +7,18 @@ import signal import sys from pathlib import Path +# Force UTF-8 encoding for Windows console +if sys.platform == "win32": + import locale + if sys.stdout.encoding != "utf-8": + os.environ["PYTHONIOENCODING"] = "utf-8" + # Re-open stdout/stderr with UTF-8 encoding + try: + sys.stdout.reconfigure(encoding="utf-8", errors="replace") + sys.stderr.reconfigure(encoding="utf-8", errors="replace") + except Exception: + pass + import typer from prompt_toolkit import PromptSession from prompt_toolkit.formatted_text import HTML @@ -244,13 +256,15 @@ 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 +274,20 @@ 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 +529,21 @@ 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) + # SIGHUP is not available on Windows + if hasattr(signal, 'SIGHUP'): + signal.signal(signal.SIGHUP, _handle_signal) + # Ignore SIGPIPE to prevent silent process termination when writing to closed pipes + # SIGPIPE is not available on Windows + if hasattr(signal, 'SIGPIPE'): + signal.signal(signal.SIGPIPE, signal.SIG_IGN) async def run_interactive(): bus_task = asyncio.create_task(agent_loop.run()) diff --git a/nanobot/config/schema.py b/nanobot/config/schema.py index 61a7bd2..2073eeb 100644 --- a/nanobot/config/schema.py +++ b/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 +194,17 @@ class QQConfig(Base): enabled: bool = False app_id: str = "" # ζœΊε™¨δΊΊ ID (AppID) from q.qq.com secret: str = "" # ζœΊε™¨δΊΊε―†ι’₯ (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 - 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 - 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 +223,9 @@ 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 +263,8 @@ 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 (η‘…εŸΊζ΅εŠ¨) API gateway - volcengine: ProviderConfig = Field(default_factory=ProviderConfig) # VolcEngine (η«ε±±εΌ•ζ“Ž) API gateway + siliconflow: ProviderConfig = Field(default_factory=ProviderConfig) # SiliconFlow (η‘…εŸΊζ΅εŠ¨) + volcengine: ProviderConfig = Field(default_factory=ProviderConfig) # VolcEngine (η«ε±±εΌ•ζ“Ž) openai_codex: ProviderConfig = Field(default_factory=ProviderConfig) # OpenAI Codex (OAuth) github_copilot: ProviderConfig = Field(default_factory=ProviderConfig) # Github Copilot (OAuth) @@ -291,7 +294,9 @@ 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 +310,13 @@ 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 +342,9 @@ 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 diff --git a/nanobot/providers/custom_provider.py b/nanobot/providers/custom_provider.py index 56e6270..66df734 100644 --- a/nanobot/providers/custom_provider.py +++ b/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, diff --git a/nanobot/providers/registry.py b/nanobot/providers/registry.py index df915b7..59ba31a 100644 --- a/nanobot/providers/registry.py +++ b/nanobot/providers/registry.py @@ -26,33 +26,33 @@ class ProviderSpec: """ # identity - name: str # config field name, e.g. "dashscope" - keywords: tuple[str, ...] # model-name keywords for matching (lowercase) - env_key: str # LiteLLM env var, e.g. "DASHSCOPE_API_KEY" - display_name: str = "" # shown in `nanobot status` + name: str # config field name, e.g. "dashscope" + keywords: tuple[str, ...] # model-name keywords for matching (lowercase) + env_key: str # LiteLLM env var, e.g. "DASHSCOPE_API_KEY" + display_name: str = "" # shown in `nanobot status` # model prefixing - litellm_prefix: str = "" # "dashscope" β†’ model becomes "dashscope/{model}" - skip_prefixes: tuple[str, ...] = () # don't prefix if model already starts with these + litellm_prefix: str = "" # "dashscope" β†’ model becomes "dashscope/{model}" + skip_prefixes: tuple[str, ...] = () # don't prefix if model already starts with these # extra env vars, e.g. (("ZHIPUAI_API_KEY", "{api_key}"),) env_extras: tuple[tuple[str, str], ...] = () # gateway / local detection - is_gateway: bool = False # routes any model (OpenRouter, AiHubMix) - is_local: bool = False # local deployment (vLLM, Ollama) - detect_by_key_prefix: str = "" # match api_key prefix, e.g. "sk-or-" - detect_by_base_keyword: str = "" # match substring in api_base URL - default_api_base: str = "" # fallback base URL + is_gateway: bool = False # routes any model (OpenRouter, AiHubMix) + is_local: bool = False # local deployment (vLLM, Ollama) + detect_by_key_prefix: str = "" # match api_key prefix, e.g. "sk-or-" + detect_by_base_keyword: str = "" # match substring in api_base URL + default_api_base: str = "" # fallback base URL # gateway behavior - strip_model_prefix: bool = False # strip "provider/" before re-prefixing + strip_model_prefix: bool = False # strip "provider/" before re-prefixing # per-model param overrides, e.g. (("kimi-k2.5", {"temperature": 1.0}),) model_overrides: tuple[tuple[str, dict[str, Any]], ...] = () # OAuth-based providers (e.g., OpenAI Codex) don't use API keys - is_oauth: bool = False # if True, uses OAuth flow instead of API key + is_oauth: bool = False # if True, uses OAuth flow instead of API key # Direct providers bypass LiteLLM entirely (e.g., CustomProvider) is_direct: bool = False @@ -70,7 +70,6 @@ class ProviderSpec: # --------------------------------------------------------------------------- PROVIDERS: tuple[ProviderSpec, ...] = ( - # === Custom (direct OpenAI-compatible endpoint, bypasses LiteLLM) ====== ProviderSpec( name="custom", @@ -80,17 +79,15 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( litellm_prefix="", is_direct=True, ), - # === Gateways (detected by api_key / api_base, not model name) ========= # Gateways can route any model, so they win in fallback. - # OpenRouter: global gateway, keys start with "sk-or-" ProviderSpec( name="openrouter", keywords=("openrouter",), env_key="OPENROUTER_API_KEY", display_name="OpenRouter", - litellm_prefix="openrouter", # claude-3 β†’ openrouter/claude-3 + litellm_prefix="openrouter", # claude-3 β†’ openrouter/claude-3 skip_prefixes=(), env_extras=(), is_gateway=True, @@ -102,16 +99,15 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( model_overrides=(), supports_prompt_caching=True, ), - # AiHubMix: global gateway, OpenAI-compatible interface. # strip_model_prefix=True: it doesn't understand "anthropic/claude-3", # so we strip to bare "claude-3" then re-prefix as "openai/claude-3". ProviderSpec( name="aihubmix", keywords=("aihubmix",), - env_key="OPENAI_API_KEY", # OpenAI-compatible + env_key="OPENAI_API_KEY", # OpenAI-compatible display_name="AiHubMix", - litellm_prefix="openai", # β†’ openai/{model} + litellm_prefix="openai", # β†’ openai/{model} skip_prefixes=(), env_extras=(), is_gateway=True, @@ -119,10 +115,9 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( detect_by_key_prefix="", detect_by_base_keyword="aihubmix", default_api_base="https://aihubmix.com/v1", - strip_model_prefix=True, # anthropic/claude-3 β†’ claude-3 β†’ openai/claude-3 + strip_model_prefix=True, # anthropic/claude-3 β†’ claude-3 β†’ openai/claude-3 model_overrides=(), ), - # SiliconFlow (η‘…εŸΊζ΅εŠ¨): OpenAI-compatible gateway, model names keep org prefix ProviderSpec( name="siliconflow", @@ -140,7 +135,6 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( strip_model_prefix=False, model_overrides=(), ), - # VolcEngine (η«ε±±εΌ•ζ“Ž): OpenAI-compatible gateway ProviderSpec( name="volcengine", @@ -158,9 +152,7 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( strip_model_prefix=False, model_overrides=(), ), - # === Standard providers (matched by model-name keywords) =============== - # Anthropic: LiteLLM recognizes "claude-*" natively, no prefix needed. ProviderSpec( name="anthropic", @@ -179,7 +171,6 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( model_overrides=(), supports_prompt_caching=True, ), - # OpenAI: LiteLLM recognizes "gpt-*" natively, no prefix needed. ProviderSpec( name="openai", @@ -197,14 +188,13 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( strip_model_prefix=False, model_overrides=(), ), - # OpenAI Codex: uses OAuth, not API key. ProviderSpec( name="openai_codex", keywords=("openai-codex",), - env_key="", # OAuth-based, no API key + env_key="", # OAuth-based, no API key display_name="OpenAI Codex", - litellm_prefix="", # Not routed through LiteLLM + litellm_prefix="", # Not routed through LiteLLM skip_prefixes=(), env_extras=(), is_gateway=False, @@ -214,16 +204,15 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( default_api_base="https://chatgpt.com/backend-api", strip_model_prefix=False, model_overrides=(), - is_oauth=True, # OAuth-based authentication + is_oauth=True, # OAuth-based authentication ), - # Github Copilot: uses OAuth, not API key. ProviderSpec( name="github_copilot", keywords=("github_copilot", "copilot"), - env_key="", # OAuth-based, no API key + env_key="", # OAuth-based, no API key display_name="Github Copilot", - litellm_prefix="github_copilot", # github_copilot/model β†’ github_copilot/model + litellm_prefix="github_copilot", # github_copilot/model β†’ github_copilot/model skip_prefixes=("github_copilot/",), env_extras=(), is_gateway=False, @@ -233,17 +222,16 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( default_api_base="", strip_model_prefix=False, model_overrides=(), - is_oauth=True, # OAuth-based authentication + is_oauth=True, # OAuth-based authentication ), - # DeepSeek: needs "deepseek/" prefix for LiteLLM routing. ProviderSpec( name="deepseek", keywords=("deepseek",), env_key="DEEPSEEK_API_KEY", display_name="DeepSeek", - litellm_prefix="deepseek", # deepseek-chat β†’ deepseek/deepseek-chat - skip_prefixes=("deepseek/",), # avoid double-prefix + litellm_prefix="deepseek", # deepseek-chat β†’ deepseek/deepseek-chat + skip_prefixes=("deepseek/",), # avoid double-prefix env_extras=(), is_gateway=False, is_local=False, @@ -253,15 +241,14 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( strip_model_prefix=False, model_overrides=(), ), - # Gemini: needs "gemini/" prefix for LiteLLM. ProviderSpec( name="gemini", keywords=("gemini",), env_key="GEMINI_API_KEY", display_name="Gemini", - litellm_prefix="gemini", # gemini-pro β†’ gemini/gemini-pro - skip_prefixes=("gemini/",), # avoid double-prefix + litellm_prefix="gemini", # gemini-pro β†’ gemini/gemini-pro + skip_prefixes=("gemini/",), # avoid double-prefix env_extras=(), is_gateway=False, is_local=False, @@ -271,7 +258,6 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( strip_model_prefix=False, model_overrides=(), ), - # Zhipu: LiteLLM uses "zai/" prefix. # Also mirrors key to ZHIPUAI_API_KEY (some LiteLLM paths check that). # skip_prefixes: don't add "zai/" when already routed via gateway. @@ -280,11 +266,9 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( keywords=("zhipu", "glm", "zai"), env_key="ZAI_API_KEY", display_name="Zhipu AI", - litellm_prefix="zai", # glm-4 β†’ zai/glm-4 + litellm_prefix="zai", # glm-4 β†’ zai/glm-4 skip_prefixes=("zhipu/", "zai/", "openrouter/", "hosted_vllm/"), - env_extras=( - ("ZHIPUAI_API_KEY", "{api_key}"), - ), + env_extras=(("ZHIPUAI_API_KEY", "{api_key}"),), is_gateway=False, is_local=False, detect_by_key_prefix="", @@ -293,14 +277,13 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( strip_model_prefix=False, model_overrides=(), ), - # DashScope: Qwen models, needs "dashscope/" prefix. ProviderSpec( name="dashscope", keywords=("qwen", "dashscope"), env_key="DASHSCOPE_API_KEY", display_name="DashScope", - litellm_prefix="dashscope", # qwen-max β†’ dashscope/qwen-max + litellm_prefix="dashscope", # qwen-max β†’ dashscope/qwen-max skip_prefixes=("dashscope/", "openrouter/"), env_extras=(), is_gateway=False, @@ -311,7 +294,6 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( strip_model_prefix=False, model_overrides=(), ), - # Moonshot: Kimi models, needs "moonshot/" prefix. # LiteLLM requires MOONSHOT_API_BASE env var to find the endpoint. # Kimi K2.5 API enforces temperature >= 1.0. @@ -320,22 +302,17 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( keywords=("moonshot", "kimi"), env_key="MOONSHOT_API_KEY", display_name="Moonshot", - litellm_prefix="moonshot", # kimi-k2.5 β†’ moonshot/kimi-k2.5 + litellm_prefix="moonshot", # kimi-k2.5 β†’ moonshot/kimi-k2.5 skip_prefixes=("moonshot/", "openrouter/"), - env_extras=( - ("MOONSHOT_API_BASE", "{api_base}"), - ), + env_extras=(("MOONSHOT_API_BASE", "{api_base}"),), is_gateway=False, is_local=False, detect_by_key_prefix="", detect_by_base_keyword="", - default_api_base="https://api.moonshot.ai/v1", # intl; use api.moonshot.cn for China + default_api_base="https://api.moonshot.ai/v1", # intl; use api.moonshot.cn for China strip_model_prefix=False, - model_overrides=( - ("kimi-k2.5", {"temperature": 1.0}), - ), + model_overrides=(("kimi-k2.5", {"temperature": 1.0}),), ), - # MiniMax: needs "minimax/" prefix for LiteLLM routing. # Uses OpenAI-compatible API at api.minimax.io/v1. ProviderSpec( @@ -343,7 +320,7 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( keywords=("minimax",), env_key="MINIMAX_API_KEY", display_name="MiniMax", - litellm_prefix="minimax", # MiniMax-M2.1 β†’ minimax/MiniMax-M2.1 + litellm_prefix="minimax", # MiniMax-M2.1 β†’ minimax/MiniMax-M2.1 skip_prefixes=("minimax/", "openrouter/"), env_extras=(), is_gateway=False, @@ -354,9 +331,7 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( strip_model_prefix=False, model_overrides=(), ), - # === Local deployment (matched by config key, NOT by api_base) ========= - # vLLM / any OpenAI-compatible local server. # Detected when config key is "vllm" (provider_name="vllm"). ProviderSpec( @@ -364,20 +339,18 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( keywords=("vllm",), env_key="HOSTED_VLLM_API_KEY", display_name="vLLM/Local", - litellm_prefix="hosted_vllm", # Llama-3-8B β†’ hosted_vllm/Llama-3-8B + litellm_prefix="hosted_vllm", # Llama-3-8B β†’ hosted_vllm/Llama-3-8B skip_prefixes=(), env_extras=(), is_gateway=False, is_local=True, detect_by_key_prefix="", detect_by_base_keyword="", - default_api_base="", # user must provide in config + default_api_base="", # user must provide in config strip_model_prefix=False, model_overrides=(), ), - # === Auxiliary (not a primary LLM provider) ============================ - # Groq: mainly used for Whisper voice transcription, also usable for LLM. # Needs "groq/" prefix for LiteLLM routing. Placed last β€” it rarely wins fallback. ProviderSpec( @@ -385,8 +358,8 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( keywords=("groq",), env_key="GROQ_API_KEY", display_name="Groq", - litellm_prefix="groq", # llama3-8b-8192 β†’ groq/llama3-8b-8192 - skip_prefixes=("groq/",), # avoid double-prefix + litellm_prefix="groq", # llama3-8b-8192 β†’ groq/llama3-8b-8192 + skip_prefixes=("groq/",), # avoid double-prefix env_extras=(), is_gateway=False, is_local=False, @@ -403,6 +376,7 @@ PROVIDERS: tuple[ProviderSpec, ...] = ( # Lookup helpers # --------------------------------------------------------------------------- + def find_by_model(model: str) -> ProviderSpec | None: """Match a standard provider by model-name keyword (case-insensitive). Skips gateways/local β€” those are matched by api_key/api_base instead.""" @@ -418,7 +392,9 @@ def find_by_model(model: str) -> ProviderSpec | None: return spec for spec in std_specs: - if any(kw in model_lower or kw.replace("-", "_") in model_normalized for kw in spec.keywords): + if any( + kw in model_lower or kw.replace("-", "_") in model_normalized for kw in spec.keywords + ): return spec return None diff --git a/nanobot/utils/helpers.py b/nanobot/utils/helpers.py index 3a8c802..c57c365 100644 --- a/nanobot/utils/helpers.py +++ b/nanobot/utils/helpers.py @@ -5,6 +5,19 @@ from datetime import datetime from pathlib import Path +def detect_image_mime(data: bytes) -> str | None: + """Detect image MIME type from magic bytes, ignoring file extension.""" + if data[:8] == b"\x89PNG\r\n\x1a\n": + return "image/png" + if data[:3] == b"\xff\xd8\xff": + return "image/jpeg" + if data[:6] in (b"GIF87a", b"GIF89a"): + return "image/gif" + if data[:4] == b"RIFF" and data[8:12] == b"WEBP": + return "image/webp" + return None + + def ensure_dir(path: Path) -> Path: """Ensure directory exists, return it.""" path.mkdir(parents=True, exist_ok=True) @@ -34,6 +47,38 @@ def safe_filename(name: str) -> str: return _UNSAFE_CHARS.sub("_", name).strip() +def split_message(content: str, max_len: int = 2000) -> list[str]: + """ + Split content into chunks within max_len, preferring line breaks. + + Args: + content: The text content to split. + max_len: Maximum length per chunk (default 2000 for Discord compatibility). + + Returns: + List of message chunks, each within max_len. + """ + if not content: + return [] + if len(content) <= max_len: + return [content] + chunks: list[str] = [] + while content: + if len(content) <= max_len: + chunks.append(content) + break + cut = content[:max_len] + # Try to break at newline first, then space, then hard break + pos = cut.rfind('\n') + if pos <= 0: + pos = cut.rfind(' ') + if pos <= 0: + pos = max_len + chunks.append(content[:pos]) + content = content[pos:].lstrip() + return chunks + + def sync_workspace_templates(workspace: Path, silent: bool = False) -> list[str]: """Sync bundled templates to workspace. Only creates missing files.""" from importlib.resources import files as pkg_files diff --git a/pyproject.toml b/pyproject.toml index d86bb28..41d0fbb 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -30,7 +30,7 @@ dependencies = [ "rich>=14.0.0,<15.0.0", "croniter>=6.0.0,<7.0.0", "dingtalk-stream>=0.24.0,<1.0.0", - "python-telegram-bot[socks]>=22.0,<23.0", + "python-telegram-bot[socks]>=22.6,<23.0", "lark-oapi>=1.5.0,<2.0.0", "socksio>=1.0.0,<2.0.0", "python-socketio>=5.16.0,<6.0.0", diff --git a/tests/test_feishu_table_split.py b/tests/test_feishu_table_split.py new file mode 100644 index 0000000..af8fa16 --- /dev/null +++ b/tests/test_feishu_table_split.py @@ -0,0 +1,104 @@ +"""Tests for FeishuChannel._split_elements_by_table_limit. + +Feishu cards reject messages that contain more than one table element +(API error 11310: card table number over limit). The helper splits a flat +list of card elements into groups so that each group contains at most one +table, allowing nanobot to send multiple cards instead of failing. +""" + +from nanobot.channels.feishu import FeishuChannel + + +def _md(text: str) -> dict: + return {"tag": "markdown", "content": text} + + +def _table() -> dict: + return { + "tag": "table", + "columns": [{"tag": "column", "name": "c0", "display_name": "A", "width": "auto"}], + "rows": [{"c0": "v"}], + "page_size": 2, + } + + +split = FeishuChannel._split_elements_by_table_limit + + +def test_empty_list_returns_single_empty_group() -> None: + assert split([]) == [[]] + + +def test_no_tables_returns_single_group() -> None: + els = [_md("hello"), _md("world")] + result = split(els) + assert result == [els] + + +def test_single_table_stays_in_one_group() -> None: + els = [_md("intro"), _table(), _md("outro")] + result = split(els) + assert len(result) == 1 + assert result[0] == els + + +def test_two_tables_split_into_two_groups() -> None: + # Use different row values so the two tables are not equal + t1 = { + "tag": "table", + "columns": [{"tag": "column", "name": "c0", "display_name": "A", "width": "auto"}], + "rows": [{"c0": "table-one"}], + "page_size": 2, + } + t2 = { + "tag": "table", + "columns": [{"tag": "column", "name": "c0", "display_name": "B", "width": "auto"}], + "rows": [{"c0": "table-two"}], + "page_size": 2, + } + els = [_md("before"), t1, _md("between"), t2, _md("after")] + result = split(els) + assert len(result) == 2 + # First group: text before table-1 + table-1 + assert t1 in result[0] + assert t2 not in result[0] + # Second group: text between tables + table-2 + text after + assert t2 in result[1] + assert t1 not in result[1] + + +def test_three_tables_split_into_three_groups() -> None: + tables = [ + {"tag": "table", "columns": [], "rows": [{"c0": f"t{i}"}], "page_size": 1} + for i in range(3) + ] + els = tables[:] + result = split(els) + assert len(result) == 3 + for i, group in enumerate(result): + assert tables[i] in group + + +def test_leading_markdown_stays_with_first_table() -> None: + intro = _md("intro") + t = _table() + result = split([intro, t]) + assert len(result) == 1 + assert result[0] == [intro, t] + + +def test_trailing_markdown_after_second_table() -> None: + t1, t2 = _table(), _table() + tail = _md("end") + result = split([t1, t2, tail]) + assert len(result) == 2 + assert result[1] == [t2, tail] + + +def test_non_table_elements_before_first_table_kept_in_first_group() -> None: + head = _md("head") + t1, t2 = _table(), _table() + result = split([head, t1, t2]) + # head + t1 in group 0; t2 in group 1 + assert result[0] == [head, t1] + assert result[1] == [t2] diff --git a/tests/test_memory_consolidation_types.py b/tests/test_memory_consolidation_types.py index 375c802..ff15584 100644 --- a/tests/test_memory_consolidation_types.py +++ b/tests/test_memory_consolidation_types.py @@ -145,3 +145,78 @@ class TestMemoryConsolidationTypeHandling: 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() + + # Simulate arguments being a list containing a dict + 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) + session = _make_session(message_count=60) + + result = await store.consolidate(session, provider, "test-model", memory_window=50) + + 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) + session = _make_session(message_count=60) + + result = await store.consolidate(session, provider, "test-model", memory_window=50) + + 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) + session = _make_session(message_count=60) + + result = await store.consolidate(session, provider, "test-model", memory_window=50) + + assert result is False