Hua/nanobot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'main' into pr-1635

Browse Source
This commit is contained in:
Re-bin
2026-03-08 03:14:20 +00:00
parent 79f3ca4f12 0a5daf3c86
commit fb4f696085
40 changed files with 2182 additions and 190 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
nanobot/agent/loop.py
View File

@@ -202,18 +202,9 @@ class AgentLoop:
if response.has_tool_calls:
if on_progress:
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)
thought = self._strip_think(response.content)
if thought:
await on_progress(thought)
await on_progress(self._tool_hint(response.tool_calls), tool_hint=True)
tool_call_dicts = [

77
nanobot/agent/tools/base.py
View File

@@ -52,6 +52,75 @@ class Tool(ABC):
"""
pass
def cast_params(self, params: dict[str, Any]) -> dict[str, Any]:
"""Apply safe schema-driven casts before validation."""
schema = self.parameters or {}
if schema.get("type", "object") != "object":
return params
return self._cast_object(params, schema)
def _cast_object(self, obj: Any, schema: dict[str, Any]) -> dict[str, Any]:
"""Cast an object (dict) according to schema."""
if not isinstance(obj, dict):
return obj
props = schema.get("properties", {})
result = {}
for key, value in obj.items():
if key in props:
result[key] = self._cast_value(value, props[key])
else:
result[key] = value
return result
def _cast_value(self, val: Any, schema: dict[str, Any]) -> Any:
"""Cast a single value according to schema."""
target_type = schema.get("type")
if target_type == "boolean" and isinstance(val, bool):
return val
if target_type == "integer" and isinstance(val, int) and not isinstance(val, bool):
return val
if target_type in self._TYPE_MAP and target_type not in ("boolean", "integer", "array", "object"):
expected = self._TYPE_MAP[target_type]
if isinstance(val, expected):
return val
if target_type == "integer" and isinstance(val, str):
try:
return int(val)
except ValueError:
return val
if target_type == "number" and isinstance(val, str):
try:
return float(val)
except ValueError:
return val
if target_type == "string":
return val if val is None else str(val)
if target_type == "boolean" and isinstance(val, str):
val_lower = val.lower()
if val_lower in ("true", "1", "yes"):
return True
if val_lower in ("false", "0", "no"):
return False
return val
if target_type == "array" and isinstance(val, list):
item_schema = schema.get("items")
return [self._cast_value(item, item_schema) for item in val] if item_schema else val
if target_type == "object" and isinstance(val, dict):
return self._cast_object(val, schema)
return val
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):
@@ -63,7 +132,13 @@ class Tool(ABC):
def _validate(self, val: Any, schema: dict[str, Any], path: str) -> list[str]:
t, label = schema.get("type"), path or "parameter"
if t in self._TYPE_MAP and not isinstance(val, self._TYPE_MAP[t]):
if t == "integer" and (not isinstance(val, int) or isinstance(val, bool)):
return [f"{label} should be integer"]
if t == "number" and (
not isinstance(val, self._TYPE_MAP[t]) or isinstance(val, bool)
):
return [f"{label} should be number"]
if t in self._TYPE_MAP and t not in ("integer", "number") and not isinstance(val, self._TYPE_MAP[t]):
return [f"{label} should be {t}"]
errors = []

2
nanobot/agent/tools/message.py
View File

@@ -96,7 +96,7 @@ class MessageTool(Tool):
media=media or [],
metadata={
"message_id": message_id,
}
},
)
try:

4
nanobot/agent/tools/registry.py
View File

@@ -44,6 +44,10 @@ class ToolRegistry:
return f"Error: Tool '{name}' not found. Available: {', '.join(self.tool_names)}"
try:
# Attempt to cast parameters to match schema types
params = tool.cast_params(params)
# Validate parameters
errors = tool.validate_params(params)
if errors:
return f"Error: Invalid parameters for tool '{name}': " + "; ".join(errors) + _HINT

5
nanobot/channels/base.py
View File

@@ -66,10 +66,7 @@ class BaseChannel(ABC):
return False
if "*" in allow_list:
return True
sender_str = str(sender_id)
return sender_str in allow_list or any(
p in allow_list for p in sender_str.split("|") if p
)
return str(sender_id) in allow_list
async def _handle_message(
self,

57
nanobot/channels/dingtalk.py
View File

@@ -70,12 +70,24 @@ class NanobotDingTalkHandler(CallbackHandler):
sender_id = chatbot_msg.sender_staff_id or chatbot_msg.sender_id
sender_name = chatbot_msg.sender_nick or "Unknown"
conversation_type = message.data.get("conversationType")
conversation_id = (
message.data.get("conversationId")
or message.data.get("openConversationId")
)
logger.info("Received DingTalk message from {} ({}): {}", sender_name, sender_id, content)
# Forward to Nanobot via _on_message (non-blocking).
# Store reference to prevent GC before task completes.
task = asyncio.create_task(
self.channel._on_message(content, sender_id, sender_name)
self.channel._on_message(
content,
sender_id,
sender_name,
conversation_type,
conversation_id,
)
)
self.channel._background_tasks.add(task)
task.add_done_callback(self.channel._background_tasks.discard)
@@ -95,8 +107,8 @@ class DingTalkChannel(BaseChannel):
Uses WebSocket to receive events via `dingtalk-stream` SDK.
Uses direct HTTP API to send messages (SDK is mainly for receiving).
Note: Currently only supports private (1:1) chat. Group messages are
received but replies are sent back as private messages to the sender.
Supports both private (1:1) and group chats.
Group chat_id is stored with a "group:" prefix to route replies back.
"""
name = "dingtalk"
@@ -301,14 +313,25 @@ class DingTalkChannel(BaseChannel):
logger.warning("DingTalk HTTP client not initialized, cannot send")
return False
url = "https://api.dingtalk.com/v1.0/robot/oToMessages/batchSend"
headers = {"x-acs-dingtalk-access-token": token}
payload = {
"robotCode": self.config.client_id,
"userIds": [chat_id],
"msgKey": msg_key,
"msgParam": json.dumps(msg_param, ensure_ascii=False),
}
if chat_id.startswith("group:"):
# Group chat
url = "https://api.dingtalk.com/v1.0/robot/groupMessages/send"
payload = {
"robotCode": self.config.client_id,
"openConversationId": chat_id[6:], # Remove "group:" prefix,
"msgKey": msg_key,
"msgParam": json.dumps(msg_param, ensure_ascii=False),
}
else:
# Private chat
url = "https://api.dingtalk.com/v1.0/robot/oToMessages/batchSend"
payload = {
"robotCode": self.config.client_id,
"userIds": [chat_id],
"msgKey": msg_key,
"msgParam": json.dumps(msg_param, ensure_ascii=False),
}
try:
resp = await self._http.post(url, json=payload, headers=headers)
@@ -417,7 +440,14 @@ class DingTalkChannel(BaseChannel):
f"[Attachment send failed: {filename}]",
)
async def _on_message(self, content: str, sender_id: str, sender_name: str) -> None:
async def _on_message(
self,
content: str,
sender_id: str,
sender_name: str,
conversation_type: str | None = None,
conversation_id: str | None = None,
) -> None:
"""Handle incoming message (called by NanobotDingTalkHandler).
Delegates to BaseChannel._handle_message() which enforces allow_from
@@ -425,13 +455,16 @@ class DingTalkChannel(BaseChannel):
"""
try:
logger.info("DingTalk inbound: {} from {}", content, sender_name)
is_group = conversation_type == "2" and conversation_id
chat_id = f"group:{conversation_id}" if is_group else sender_id
await self._handle_message(
sender_id=sender_id,
chat_id=sender_id, # For private chat, chat_id == sender_id
chat_id=chat_id,
content=str(content),
metadata={
"sender_name": sender_name,
"platform": "dingtalk",
"conversation_type": conversation_type,
},
)
except Exception as e:

73
nanobot/channels/discord.py
View File

@@ -12,6 +12,7 @@ from loguru import logger
from nanobot.bus.events import OutboundMessage
from nanobot.bus.queue import MessageBus
from nanobot.channels.base import BaseChannel
from nanobot.config.paths import get_media_dir
from nanobot.config.schema import DiscordConfig
from nanobot.utils.helpers import split_message
@@ -75,7 +76,7 @@ class DiscordChannel(BaseChannel):
self._http = None
async def send(self, msg: OutboundMessage) -> None:
"""Send a message through Discord REST API."""
"""Send a message through Discord REST API, including file attachments."""
if not self._http:
logger.warning("Discord HTTP client not initialized")
return
@@ -84,15 +85,31 @@ class DiscordChannel(BaseChannel):
headers = {"Authorization": f"Bot {self.config.token}"}
try:
sent_media = False
failed_media: list[str] = []
# Send file attachments first
for media_path in msg.media or []:
if await self._send_file(url, headers, media_path, reply_to=msg.reply_to):
sent_media = True
else:
failed_media.append(Path(media_path).name)
# Send text content
chunks = split_message(msg.content or "", MAX_MESSAGE_LEN)
if not chunks and failed_media and not sent_media:
chunks = split_message(
"\n".join(f"[attachment: {name} - send failed]" for name in failed_media),
MAX_MESSAGE_LEN,
)
if not chunks:
return
for i, chunk in enumerate(chunks):
payload: dict[str, Any] = {"content": chunk}
# Only set reply reference on the first chunk
if i == 0 and msg.reply_to:
# Let the first successful attachment carry the reply if present.
if i == 0 and msg.reply_to and not sent_media:
payload["message_reference"] = {"message_id": msg.reply_to}
payload["allowed_mentions"] = {"replied_user": False}
@@ -123,6 +140,54 @@ class DiscordChannel(BaseChannel):
await asyncio.sleep(1)
return False
async def _send_file(
self,
url: str,
headers: dict[str, str],
file_path: str,
reply_to: str | None = None,
) -> bool:
"""Send a file attachment via Discord REST API using multipart/form-data."""
path = Path(file_path)
if not path.is_file():
logger.warning("Discord file not found, skipping: {}", file_path)
return False
if path.stat().st_size > MAX_ATTACHMENT_BYTES:
logger.warning("Discord file too large (>20MB), skipping: {}", path.name)
return False
payload_json: dict[str, Any] = {}
if reply_to:
payload_json["message_reference"] = {"message_id": reply_to}
payload_json["allowed_mentions"] = {"replied_user": False}
for attempt in range(3):
try:
with open(path, "rb") as f:
files = {"files[0]": (path.name, f, "application/octet-stream")}
data: dict[str, Any] = {}
if payload_json:
data["payload_json"] = json.dumps(payload_json)
response = await self._http.post(
url, headers=headers, files=files, data=data
)
if response.status_code == 429:
resp_data = response.json()
retry_after = float(resp_data.get("retry_after", 1.0))
logger.warning("Discord rate limited, retrying in {}s", retry_after)
await asyncio.sleep(retry_after)
continue
response.raise_for_status()
logger.info("Discord file sent: {}", path.name)
return True
except Exception as e:
if attempt == 2:
logger.error("Error sending Discord file {}: {}", path.name, e)
else:
await asyncio.sleep(1)
return False
async def _gateway_loop(self) -> None:
"""Main gateway loop: identify, heartbeat, dispatch events."""
if not self._ws:
@@ -225,7 +290,7 @@ class DiscordChannel(BaseChannel):
content_parts = [content] if content else []
media_paths: list[str] = []
media_dir = Path.home() / ".nanobot" / "media"
media_dir = get_media_dir("discord")
for attachment in payload.get("attachments") or []:
url = attachment.get("url")

60
nanobot/channels/feishu.py
View File

@@ -14,6 +14,7 @@ from loguru import logger
from nanobot.bus.events import OutboundMessage
from nanobot.bus.queue import MessageBus
from nanobot.channels.base import BaseChannel
from nanobot.config.paths import get_media_dir
from nanobot.config.schema import FeishuConfig
import importlib.util
@@ -244,15 +245,22 @@ class FeishuChannel(BaseChannel):
name = "feishu"
def __init__(self, config: FeishuConfig, bus: MessageBus):
def __init__(self, config: FeishuConfig, bus: MessageBus, groq_api_key: str = ""):
super().__init__(config, bus)
self.config: FeishuConfig = config
self.groq_api_key = groq_api_key
self._client: Any = None
self._ws_client: Any = None
self._ws_thread: threading.Thread | None = None
self._processed_message_ids: OrderedDict[str, None] = OrderedDict() # Ordered dedup cache
self._loop: asyncio.AbstractEventLoop | None = None
@staticmethod
def _register_optional_event(builder: Any, method_name: str, handler: Any) -> Any:
"""Register an event handler only when the SDK supports it."""
method = getattr(builder, method_name, None)
return method(handler) if callable(method) else builder
async def start(self) -> None:
"""Start the Feishu bot with WebSocket long connection."""
if not FEISHU_AVAILABLE:
@@ -273,14 +281,24 @@ class FeishuChannel(BaseChannel):
.app_secret(self.config.app_secret) \
.log_level(lark.LogLevel.INFO) \
.build()
# Create event handler (only register message receive, ignore other events)
event_handler = lark.EventDispatcherHandler.builder(
builder = lark.EventDispatcherHandler.builder(
self.config.encrypt_key or "",
self.config.verification_token or "",
).register_p2_im_message_receive_v1(
self._on_message_sync
).build()
)
builder = self._register_optional_event(
builder, "register_p2_im_message_reaction_created_v1", self._on_reaction_created
)
builder = self._register_optional_event(
builder, "register_p2_im_message_message_read_v1", self._on_message_read
)
builder = self._register_optional_event(
builder,
"register_p2_im_chat_access_event_bot_p2p_chat_entered_v1",
self._on_bot_p2p_chat_entered,
)
event_handler = builder.build()
# Create WebSocket client for long connection
self._ws_client = lark.ws.Client(
@@ -715,8 +733,7 @@ class FeishuChannel(BaseChannel):
(file_path, content_text) - file_path is None if download failed
"""
loop = asyncio.get_running_loop()
media_dir = Path.home() / ".nanobot" / "media"
media_dir.mkdir(parents=True, exist_ok=True)
media_dir = get_media_dir("feishu")
data, filename = None, None
@@ -841,7 +858,7 @@ class FeishuChannel(BaseChannel):
except Exception as e:
logger.error("Error sending Feishu message: {}", e)
def _on_message_sync(self, data: "P2ImMessageReceiveV1") -> None:
def _on_message_sync(self, data: Any) -> None:
"""
Sync handler for incoming messages (called from WebSocket thread).
Schedules async handling in the main event loop.
@@ -849,7 +866,7 @@ class FeishuChannel(BaseChannel):
if self._loop and self._loop.is_running():
asyncio.run_coroutine_threadsafe(self._on_message(data), self._loop)
async def _on_message(self, data: "P2ImMessageReceiveV1") -> None:
async def _on_message(self, data: Any) -> None:
"""Handle incoming message from Feishu."""
try:
event = data.event
@@ -909,6 +926,18 @@ class FeishuChannel(BaseChannel):
file_path, content_text = await self._download_and_save_media(msg_type, content_json, message_id)
if file_path:
media_paths.append(file_path)
# Transcribe audio using Groq Whisper
if msg_type == "audio" and file_path and self.groq_api_key:
try:
from nanobot.providers.transcription import GroqTranscriptionProvider
transcriber = GroqTranscriptionProvider(api_key=self.groq_api_key)
transcription = await transcriber.transcribe(file_path)
if transcription:
content_text = f"[transcription: {transcription}]"
except Exception as e:
logger.warning("Failed to transcribe audio: {}", e)
content_parts.append(content_text)
elif msg_type in ("share_chat", "share_user", "interactive", "share_calendar_event", "system", "merge_forward"):
@@ -941,3 +970,16 @@ class FeishuChannel(BaseChannel):
except Exception as e:
logger.error("Error processing Feishu message: {}", e)
def _on_reaction_created(self, data: Any) -> None:
"""Ignore reaction events so they do not generate SDK noise."""
pass
def _on_message_read(self, data: Any) -> None:
"""Ignore read events so they do not generate SDK noise."""
pass
def _on_bot_p2p_chat_entered(self, data: Any) -> None:
"""Ignore p2p-enter events when a user opens a bot chat."""
logger.debug("Bot entered p2p chat (user opened chat window)")
pass

3
nanobot/channels/manager.py
View File

@@ -74,7 +74,8 @@ class ChannelManager:
try:
from nanobot.channels.feishu import FeishuChannel
self.channels["feishu"] = FeishuChannel(
self.config.channels.feishu, self.bus
self.config.channels.feishu, self.bus,
groq_api_key=self.config.providers.groq.api_key,
)
logger.info("Feishu channel enabled")
except ImportError as e:

6
nanobot/channels/matrix.py
View File

@@ -38,7 +38,7 @@ except ImportError as e:
from nanobot.bus.events import OutboundMessage
from nanobot.channels.base import BaseChannel
from nanobot.config.loader import get_data_dir
from nanobot.config.paths import get_data_dir, get_media_dir
from nanobot.utils.helpers import safe_filename
TYPING_NOTICE_TIMEOUT_MS = 30_000
@@ -490,9 +490,7 @@ class MatrixChannel(BaseChannel):
return False
def _media_dir(self) -> Path:
d = get_data_dir() / "media" / "matrix"
d.mkdir(parents=True, exist_ok=True)
return d
return get_media_dir("matrix")
@staticmethod
def _event_source_content(event: RoomMessage) -> dict[str, Any]:

4
nanobot/channels/mochat.py
View File

@@ -15,8 +15,8 @@ from loguru import logger
from nanobot.bus.events import OutboundMessage
from nanobot.bus.queue import MessageBus
from nanobot.channels.base import BaseChannel
from nanobot.config.paths import get_runtime_subdir
from nanobot.config.schema import MochatConfig
from nanobot.utils.helpers import get_data_path
try:
import socketio
@@ -224,7 +224,7 @@ class MochatChannel(BaseChannel):
self._socket: Any = None
self._ws_connected = self._ws_ready = False
self._state_dir = get_data_path() / "mochat"
self._state_dir = get_runtime_subdir("mochat")
self._cursor_path = self._state_dir / "session_cursors.json"
self._session_cursor: dict[str, int] = {}
self._cursor_save_task: asyncio.Task | None = None

59
nanobot/channels/qq.py
View File

@@ -13,16 +13,17 @@ from nanobot.config.schema import QQConfig
try:
import botpy
from botpy.message import C2CMessage
from botpy.message import C2CMessage, GroupMessage
QQ_AVAILABLE = True
except ImportError:
QQ_AVAILABLE = False
botpy = None
C2CMessage = None
GroupMessage = None
if TYPE_CHECKING:
from botpy.message import C2CMessage
from botpy.message import C2CMessage, GroupMessage
def _make_bot_class(channel: "QQChannel") -> "type[botpy.Client]":
@@ -38,10 +39,13 @@ def _make_bot_class(channel: "QQChannel") -> "type[botpy.Client]":
logger.info("QQ bot ready: {}", self.robot.name)
async def on_c2c_message_create(self, message: "C2CMessage"):
await channel._on_message(message)
await channel._on_message(message, is_group=False)
async def on_group_at_message_create(self, message: "GroupMessage"):
await channel._on_message(message, is_group=True)
async def on_direct_message_create(self, message):
await channel._on_message(message)
await channel._on_message(message, is_group=False)
return _Bot
@@ -57,6 +61,7 @@ class QQChannel(BaseChannel):
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
self._chat_type_cache: dict[str, str] = {}
async def start(self) -> None:
"""Start the QQ bot."""
@@ -71,8 +76,7 @@ class QQChannel(BaseChannel):
self._running = True
BotClass = _make_bot_class(self)
self._client = BotClass()
logger.info("QQ bot started (C2C private message)")
logger.info("QQ bot started (C2C & Group supported)")
await self._run_bot()
async def _run_bot(self) -> None:
@@ -101,20 +105,31 @@ class QQChannel(BaseChannel):
if not self._client:
logger.warning("QQ client not initialized")
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
)
self._msg_seq += 1
msg_type = self._chat_type_cache.get(msg.chat_id, "c2c")
if msg_type == "group":
await self._client.api.post_group_message(
group_openid=msg.chat_id,
msg_type=0,
content=msg.content,
msg_id=msg_id,
msg_seq=self._msg_seq,
)
else:
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,
)
except Exception as e:
logger.error("Error sending QQ message: {}", e)
async def _on_message(self, data: "C2CMessage") -> None:
async def _on_message(self, data: "C2CMessage | GroupMessage", is_group: bool = False) -> None:
"""Handle incoming message from QQ."""
try:
# Dedup by message ID
@@ -122,18 +137,24 @@ class QQChannel(BaseChannel):
return
self._processed_ids.append(data.id)
author = data.author
user_id = str(getattr(author, 'id', None) or getattr(author, 'user_openid', 'unknown'))
content = (data.content or "").strip()
if not content:
return
if is_group:
chat_id = data.group_openid
user_id = data.author.member_openid
self._chat_type_cache[chat_id] = "group"
else:
chat_id = str(getattr(data.author, 'id', None) or getattr(data.author, 'user_openid', 'unknown'))
user_id = chat_id
self._chat_type_cache[chat_id] = "c2c"
await self._handle_message(
sender_id=user_id,
chat_id=user_id,
chat_id=chat_id,
content=content,
metadata={"message_id": data.id},
)
except Exception:
logger.exception("Error handling QQ message")

7
nanobot/channels/slack.py
View File

@@ -82,13 +82,14 @@ class SlackChannel(BaseChannel):
thread_ts = slack_meta.get("thread_ts")
channel_type = slack_meta.get("channel_type")
# Only reply in thread for channel/group messages; DMs don't use threads
use_thread = thread_ts and channel_type != "im"
thread_ts_param = thread_ts if use_thread else None
if msg.content:
# Slack rejects empty text payloads. Keep media-only messages media-only,
# but send a single blank message when the bot has no text or files to send.
if msg.content or not (msg.media or []):
await self._web_client.chat_postMessage(
channel=msg.chat_id,
text=self._to_mrkdwn(msg.content),
text=self._to_mrkdwn(msg.content) if msg.content else " ",
thread_ts=thread_ts_param,
)

167
nanobot/channels/telegram.py
View File

@@ -15,6 +15,7 @@ from telegram.request import HTTPXRequest
from nanobot.bus.events import OutboundMessage
from nanobot.bus.queue import MessageBus
from nanobot.channels.base import BaseChannel
from nanobot.config.paths import get_media_dir
from nanobot.config.schema import TelegramConfig
from nanobot.utils.helpers import split_message
@@ -177,6 +178,26 @@ class TelegramChannel(BaseChannel):
self._typing_tasks: dict[str, asyncio.Task] = {} # chat_id -> typing loop task
self._media_group_buffers: dict[str, dict] = {}
self._media_group_tasks: dict[str, asyncio.Task] = {}
self._message_threads: dict[tuple[str, int], int] = {}
def is_allowed(self, sender_id: str) -> bool:
"""Preserve Telegram's legacy id|username allowlist matching."""
if super().is_allowed(sender_id):
return True
allow_list = getattr(self.config, "allow_from", [])
if not allow_list or "*" in allow_list:
return False
sender_str = str(sender_id)
if sender_str.count("|") != 1:
return False
sid, username = sender_str.split("|", 1)
if not sid.isdigit() or not username:
return False
return sid in allow_list or username in allow_list
async def start(self) -> None:
"""Start the Telegram bot with long polling."""
@@ -187,16 +208,21 @@ class TelegramChannel(BaseChannel):
self._running = True
# Build the application with larger connection pool to avoid pool-timeout on long runs
req = HTTPXRequest(connection_pool_size=16, pool_timeout=5.0, connect_timeout=30.0, read_timeout=30.0)
req = HTTPXRequest(
connection_pool_size=16,
pool_timeout=5.0,
connect_timeout=30.0,
read_timeout=30.0,
proxy=self.config.proxy if self.config.proxy else None,
)
builder = Application.builder().token(self.config.token).request(req).get_updates_request(req)
if self.config.proxy:
builder = builder.proxy(self.config.proxy).get_updates_proxy(self.config.proxy)
self._app = builder.build()
self._app.add_error_handler(self._on_error)
# Add command handlers
self._app.add_handler(CommandHandler("start", self._on_start))
self._app.add_handler(CommandHandler("new", self._forward_command))
self._app.add_handler(CommandHandler("stop", self._forward_command))
self._app.add_handler(CommandHandler("help", self._on_help))
# Add message handler for text, photos, voice, documents
@@ -281,10 +307,16 @@ class TelegramChannel(BaseChannel):
except ValueError:
logger.error("Invalid chat_id: {}", msg.chat_id)
return
reply_to_message_id = msg.metadata.get("message_id")
message_thread_id = msg.metadata.get("message_thread_id")
if message_thread_id is None and reply_to_message_id is not None:
message_thread_id = self._message_threads.get((msg.chat_id, reply_to_message_id))
thread_kwargs = {}
if message_thread_id is not None:
thread_kwargs["message_thread_id"] = message_thread_id
reply_params = None
if self.config.reply_to_message:
reply_to_message_id = msg.metadata.get("message_id")
if reply_to_message_id:
reply_params = ReplyParameters(
message_id=reply_to_message_id,
@@ -305,7 +337,8 @@ class TelegramChannel(BaseChannel):
await sender(
chat_id=chat_id,
**{param: f},
reply_parameters=reply_params
reply_parameters=reply_params,
**thread_kwargs,
)
except Exception as e:
filename = media_path.rsplit("/", 1)[-1]
@@ -313,7 +346,8 @@ class TelegramChannel(BaseChannel):
await self._app.bot.send_message(
chat_id=chat_id,
text=f"[Failed to send: {filename}]",
reply_parameters=reply_params
reply_parameters=reply_params,
**thread_kwargs,
)
# Send text content
@@ -323,28 +357,44 @@ class TelegramChannel(BaseChannel):
for chunk in split_message(msg.content, TELEGRAM_MAX_MESSAGE_LEN):
# Final response: simulate streaming via draft, then persist
if not is_progress:
await self._send_with_streaming(chat_id, chunk, reply_params)
await self._send_with_streaming(chat_id, chunk, reply_params, thread_kwargs)
else:
await self._send_text(chat_id, chunk, reply_params)
await self._send_text(chat_id, chunk, reply_params, thread_kwargs)
async def _send_text(self, chat_id: int, text: str, reply_params=None) -> None:
async def _send_text(
self,
chat_id: int,
text: str,
reply_params=None,
thread_kwargs: dict | None = None,
) -> None:
"""Send a plain text message with HTML fallback."""
try:
html = _markdown_to_telegram_html(text)
await self._app.bot.send_message(
chat_id=chat_id, text=html, parse_mode="HTML",
reply_parameters=reply_params,
**(thread_kwargs or {}),
)
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=text, reply_parameters=reply_params,
chat_id=chat_id,
text=text,
reply_parameters=reply_params,
**(thread_kwargs or {}),
)
except Exception as e2:
logger.error("Error sending Telegram message: {}", e2)
async def _send_with_streaming(self, chat_id: int, text: str, reply_params=None) -> None:
async def _send_with_streaming(
self,
chat_id: int,
text: str,
reply_params=None,
thread_kwargs: dict | None = None,
) -> None:
"""Simulate streaming via send_message_draft, then persist with send_message."""
draft_id = int(time.time() * 1000) % (2**31)
try:
@@ -360,7 +410,7 @@ class TelegramChannel(BaseChannel):
await asyncio.sleep(0.15)
except Exception:
pass
await self._send_text(chat_id, text, reply_params)
await self._send_text(chat_id, text, reply_params, thread_kwargs)
async def _on_start(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
"""Handle /start command."""
@@ -391,14 +441,50 @@ class TelegramChannel(BaseChannel):
sid = str(user.id)
return f"{sid}|{user.username}" if user.username else sid
@staticmethod
def _derive_topic_session_key(message) -> str | None:
"""Derive topic-scoped session key for non-private Telegram chats."""
message_thread_id = getattr(message, "message_thread_id", None)
if message.chat.type == "private" or message_thread_id is None:
return None
return f"telegram:{message.chat_id}:topic:{message_thread_id}"
@staticmethod
def _build_message_metadata(message, user) -> dict:
"""Build common Telegram inbound metadata payload."""
return {
"message_id": message.message_id,
"user_id": user.id,
"username": user.username,
"first_name": user.first_name,
"is_group": message.chat.type != "private",
"message_thread_id": getattr(message, "message_thread_id", None),
"is_forum": bool(getattr(message.chat, "is_forum", False)),
}
def _remember_thread_context(self, message) -> None:
"""Cache topic thread id by chat/message id for follow-up replies."""
message_thread_id = getattr(message, "message_thread_id", None)
if message_thread_id is None:
return
key = (str(message.chat_id), message.message_id)
self._message_threads[key] = message_thread_id
if len(self._message_threads) > 1000:
self._message_threads.pop(next(iter(self._message_threads)))
async def _forward_command(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
"""Forward slash commands to the bus for unified handling in AgentLoop."""
if not update.message or not update.effective_user:
return
message = update.message
user = update.effective_user
self._remember_thread_context(message)
await self._handle_message(
sender_id=self._sender_id(update.effective_user),
chat_id=str(update.message.chat_id),
content=update.message.text,
sender_id=self._sender_id(user),
chat_id=str(message.chat_id),
content=message.text,
metadata=self._build_message_metadata(message, user),
session_key=self._derive_topic_session_key(message),
)
async def _on_message(self, update: Update, context: ContextTypes.DEFAULT_TYPE) -> None:
@@ -410,6 +496,7 @@ class TelegramChannel(BaseChannel):
user = update.effective_user
chat_id = message.chat_id
sender_id = self._sender_id(user)
self._remember_thread_context(message)
# Store chat_id for replies
self._chat_ids[sender_id] = chat_id
@@ -445,12 +532,12 @@ class TelegramChannel(BaseChannel):
if media_file and self._app:
try:
file = await self._app.bot.get_file(media_file.file_id)
ext = self._get_extension(media_type, getattr(media_file, 'mime_type', None))
# Save to workspace/media/
from pathlib import Path
media_dir = Path.home() / ".nanobot" / "media"
media_dir.mkdir(parents=True, exist_ok=True)
ext = self._get_extension(
media_type,
getattr(media_file, 'mime_type', None),
getattr(media_file, 'file_name', None),
)
media_dir = get_media_dir("telegram")
file_path = media_dir / f"{media_file.file_id[:16]}{ext}"
await file.download_to_drive(str(file_path))
@@ -480,6 +567,8 @@ class TelegramChannel(BaseChannel):
logger.debug("Telegram message from {}: {}...", sender_id, content[:50])
str_chat_id = str(chat_id)
metadata = self._build_message_metadata(message, user)
session_key = self._derive_topic_session_key(message)
# Telegram media groups: buffer briefly, forward as one aggregated turn.
if media_group_id := getattr(message, "media_group_id", None):
@@ -488,11 +577,8 @@ class TelegramChannel(BaseChannel):
self._media_group_buffers[key] = {
"sender_id": sender_id, "chat_id": str_chat_id,
"contents": [], "media": [],
"metadata": {
"message_id": message.message_id, "user_id": user.id,
"username": user.username, "first_name": user.first_name,
"is_group": message.chat.type != "private",
},
"metadata": metadata,
"session_key": session_key,
}
self._start_typing(str_chat_id)
buf = self._media_group_buffers[key]
@@ -512,13 +598,8 @@ class TelegramChannel(BaseChannel):
chat_id=str_chat_id,
content=content,
media=media_paths,
metadata={
"message_id": message.message_id,
"user_id": user.id,
"username": user.username,
"first_name": user.first_name,
"is_group": message.chat.type != "private"
}
metadata=metadata,
session_key=session_key,
)
async def _flush_media_group(self, key: str) -> None:
@@ -532,6 +613,7 @@ class TelegramChannel(BaseChannel):
sender_id=buf["sender_id"], chat_id=buf["chat_id"],
content=content, media=list(dict.fromkeys(buf["media"])),
metadata=buf["metadata"],
session_key=buf.get("session_key"),
)
finally:
self._media_group_tasks.pop(key, None)
@@ -563,8 +645,13 @@ class TelegramChannel(BaseChannel):
"""Log polling / handler errors instead of silently swallowing them."""
logger.error("Telegram error: {}", context.error)
def _get_extension(self, media_type: str, mime_type: str | None) -> str:
"""Get file extension based on media type."""
def _get_extension(
self,
media_type: str,
mime_type: str | None,
filename: str | None = None,
) -> str:
"""Get file extension based on media type or original filename."""
if mime_type:
ext_map = {
"image/jpeg": ".jpg", "image/png": ".png", "image/gif": ".gif",
@@ -574,4 +661,12 @@ class TelegramChannel(BaseChannel):
return ext_map[mime_type]
type_map = {"image": ".jpg", "voice": ".ogg", "audio": ".mp3", "file": ""}
return type_map.get(media_type, "")
if ext := type_map.get(media_type, ""):
return ext
if filename:
from pathlib import Path
return "".join(Path(filename).suffixes)
return ""

13
nanobot/channels/whatsapp.py
View File

@@ -2,6 +2,7 @@
import asyncio
import json
import mimetypes
from collections import OrderedDict
from loguru import logger
@@ -128,10 +129,22 @@ class WhatsAppChannel(BaseChannel):
logger.info("Voice message received from {}, but direct download from bridge is not yet supported.", sender_id)
content = "[Voice Message: Transcription not available for WhatsApp yet]"
# Extract media paths (images/documents/videos downloaded by the bridge)
media_paths = data.get("media") or []
# Build content tags matching Telegram's pattern: [image: /path] or [file: /path]
if media_paths:
for p in media_paths:
mime, _ = mimetypes.guess_type(p)
media_type = "image" if mime and mime.startswith("image/") else "file"
media_tag = f"[{media_type}: {p}]"
content = f"{content}\n{media_tag}" if content else media_tag
await self._handle_message(
sender_id=sender_id,
chat_id=sender, # Use full LID for replies
content=content,
media=media_paths,
metadata={
"message_id": message_id,
"timestamp": data.get("timestamp"),

47
nanobot/cli/commands.py
View File

@@ -29,6 +29,7 @@ from rich.table import Table
from rich.text import Text
from nanobot import __logo__, __version__
from nanobot.config.paths import get_workspace_path
from nanobot.config.schema import Config
from nanobot.utils.helpers import sync_workspace_templates
@@ -98,7 +99,9 @@ def _init_prompt_session() -> None:
except Exception:
pass
history_file = Path.home() / ".nanobot" / "history" / "cli_history"
from nanobot.config.paths import get_cli_history_path
history_file = get_cli_history_path()
history_file.parent.mkdir(parents=True, exist_ok=True)
_PROMPT_SESSION = PromptSession(
@@ -169,7 +172,6 @@ def onboard():
"""Initialize nanobot configuration and workspace."""
from nanobot.config.loader import get_config_path, load_config, save_config
from nanobot.config.schema import Config
from nanobot.utils.helpers import get_workspace_path
config_path = get_config_path()
@@ -212,6 +214,7 @@ def onboard():
def _make_provider(config: Config):
"""Create the appropriate LLM provider from config."""
from nanobot.providers.openai_codex_provider import OpenAICodexProvider
from nanobot.providers.azure_openai_provider import AzureOpenAIProvider
model = config.agents.defaults.model
provider_name = config.get_provider_name(model)
@@ -230,6 +233,20 @@ def _make_provider(config: Config):
default_model=model,
)
# Azure OpenAI: direct Azure OpenAI endpoint with deployment name
if provider_name == "azure_openai":
if not p or not p.api_key or not p.api_base:
console.print("[red]Error: Azure OpenAI requires api_key and api_base.[/red]")
console.print("Set them in ~/.nanobot/config.json under providers.azure_openai section")
console.print("Use the model field to specify the deployment name.")
raise typer.Exit(1)
return AzureOpenAIProvider(
api_key=p.api_key,
api_base=p.api_base,
default_model=model,
)
from nanobot.providers.litellm_provider import LiteLLMProvider
from nanobot.providers.registry import find_by_name
spec = find_by_name(provider_name)
@@ -267,13 +284,24 @@ def _load_runtime_config(config: str | None = None, workspace: str | None = None
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"),
config: str | None = typer.Option(None, "--config", "-c", help="Path to config file"),
):
"""Start the nanobot gateway."""
# Set config path if provided (must be done before any imports that use get_data_dir)
if config:
from nanobot.config.loader import set_config_path
config_path = Path(config).expanduser().resolve()
if not config_path.exists():
console.print(f"[red]Error: Config file not found: {config_path}[/red]")
raise typer.Exit(1)
set_config_path(config_path)
console.print(f"[dim]Using config: {config_path}[/dim]")
from nanobot.agent.loop import AgentLoop
from nanobot.bus.queue import MessageBus
from nanobot.channels.manager import ChannelManager
from nanobot.config.paths import get_cron_dir
from nanobot.cron.service import CronService
from nanobot.cron.types import CronJob
from nanobot.heartbeat.service import HeartbeatService
@@ -292,8 +320,7 @@ def gateway(
session_manager = SessionManager(config.workspace_path)
# Create cron service first (callback set after agent creation)
# Use workspace path for per-instance cron store
cron_store_path = config.workspace_path / "cron" / "jobs.json"
cron_store_path = get_cron_dir() / "jobs.json"
cron = CronService(cron_store_path)
# Create agent with cron service
@@ -464,7 +491,7 @@ def agent(
from nanobot.agent.loop import AgentLoop
from nanobot.bus.queue import MessageBus
from nanobot.config.loader import get_data_dir
from nanobot.config.paths import get_cron_dir
from nanobot.cron.service import CronService
config = _load_runtime_config(config, workspace)
@@ -474,7 +501,7 @@ def agent(
provider = _make_provider(config)
# Create cron service for tool usage (no callback needed for CLI unless running)
cron_store_path = get_data_dir() / "cron" / "jobs.json"
cron_store_path = get_cron_dir() / "jobs.json"
cron = CronService(cron_store_path)
if logs:
@@ -740,7 +767,9 @@ def _get_bridge_dir() -> Path:
import subprocess
# User's bridge location
user_bridge = Path.home() / ".nanobot" / "bridge"
from nanobot.config.paths import get_bridge_install_dir
user_bridge = get_bridge_install_dir()
# Check if already built
if (user_bridge / "dist" / "index.js").exists():
@@ -798,6 +827,7 @@ def channels_login():
import subprocess
from nanobot.config.loader import load_config
from nanobot.config.paths import get_runtime_subdir
config = load_config()
bridge_dir = _get_bridge_dir()
@@ -808,6 +838,7 @@ def channels_login():
env = {**os.environ}
if config.channels.whatsapp.bridge_token:
env["BRIDGE_TOKEN"] = config.channels.whatsapp.bridge_token
env["AUTH_DIR"] = str(get_runtime_subdir("whatsapp-auth"))
try:
subprocess.run(["npm", "start"], cwd=bridge_dir, check=True, env=env)

26
nanobot/config/__init__.py
View File

@@ -1,6 +1,30 @@
"""Configuration module for nanobot."""
from nanobot.config.loader import get_config_path, load_config
from nanobot.config.paths import (
get_bridge_install_dir,
get_cli_history_path,
get_cron_dir,
get_data_dir,
get_legacy_sessions_dir,
get_logs_dir,
get_media_dir,
get_runtime_subdir,
get_workspace_path,
)
from nanobot.config.schema import Config
__all__ = ["Config", "load_config", "get_config_path"]
__all__ = [
"Config",
"load_config",
"get_config_path",
"get_data_dir",
"get_runtime_subdir",
"get_media_dir",
"get_cron_dir",
"get_logs_dir",
"get_workspace_path",
"get_cli_history_path",
"get_bridge_install_dir",
"get_legacy_sessions_dir",
]

20
nanobot/config/loader.py
View File

@@ -6,17 +6,23 @@ from pathlib import Path
from nanobot.config.schema import Config
# Global variable to store current config path (for multi-instance support)
_current_config_path: Path | None = None
def set_config_path(path: Path) -> None:
"""Set the current config path (used to derive data directory)."""
global _current_config_path
_current_config_path = path
def get_config_path() -> Path:
"""Get the default configuration file path."""
"""Get the configuration file path."""
if _current_config_path:
return _current_config_path
return Path.home() / ".nanobot" / "config.json"
def get_data_dir() -> Path:
"""Get the nanobot data directory."""
from nanobot.utils.helpers import get_data_path
return get_data_path()
def load_config(config_path: Path | None = None) -> Config:
"""
Load configuration from file or create default.

55
nanobot/config/paths.py Normal file
View File

@@ -0,0 +1,55 @@
"""Runtime path helpers derived from the active config context."""
from __future__ import annotations
from pathlib import Path
from nanobot.config.loader import get_config_path
from nanobot.utils.helpers import ensure_dir
def get_data_dir() -> Path:
"""Return the instance-level runtime data directory."""
return ensure_dir(get_config_path().parent)
def get_runtime_subdir(name: str) -> Path:
"""Return a named runtime subdirectory under the instance data dir."""
return ensure_dir(get_data_dir() / name)
def get_media_dir(channel: str | None = None) -> Path:
"""Return the media directory, optionally namespaced per channel."""
base = get_runtime_subdir("media")
return ensure_dir(base / channel) if channel else base
def get_cron_dir() -> Path:
"""Return the cron storage directory."""
return get_runtime_subdir("cron")
def get_logs_dir() -> Path:
"""Return the logs directory."""
return get_runtime_subdir("logs")
def get_workspace_path(workspace: str | None = None) -> Path:
"""Resolve and ensure the agent workspace path."""
path = Path(workspace).expanduser() if workspace else Path.home() / ".nanobot" / "workspace"
return ensure_dir(path)
def get_cli_history_path() -> Path:
"""Return the shared CLI history file path."""
return Path.home() / ".nanobot" / "history" / "cli_history"
def get_bridge_install_dir() -> Path:
"""Return the shared WhatsApp bridge installation directory."""
return Path.home() / ".nanobot" / "bridge"
def get_legacy_sessions_dir() -> Path:
"""Return the legacy global session directory used for migration fallback."""
return Path.home() / ".nanobot" / "sessions"

1
nanobot/config/schema.py
View File

@@ -251,6 +251,7 @@ class ProvidersConfig(Base):
"""Configuration for LLM providers."""
custom: ProviderConfig = Field(default_factory=ProviderConfig) # Any OpenAI-compatible endpoint
azure_openai: ProviderConfig = Field(default_factory=ProviderConfig) # Azure OpenAI (model = deployment name)
anthropic: ProviderConfig = Field(default_factory=ProviderConfig)
openai: ProviderConfig = Field(default_factory=ProviderConfig)
openrouter: ProviderConfig = Field(default_factory=ProviderConfig)

3
nanobot/providers/__init__.py
View File

@@ -3,5 +3,6 @@
from nanobot.providers.base import LLMProvider, LLMResponse
from nanobot.providers.litellm_provider import LiteLLMProvider
from nanobot.providers.openai_codex_provider import OpenAICodexProvider
from nanobot.providers.azure_openai_provider import AzureOpenAIProvider
__all__ = ["LLMProvider", "LLMResponse", "LiteLLMProvider", "OpenAICodexProvider"]
__all__ = ["LLMProvider", "LLMResponse", "LiteLLMProvider", "OpenAICodexProvider", "AzureOpenAIProvider"]

210
nanobot/providers/azure_openai_provider.py Normal file
View File

@@ -0,0 +1,210 @@
"""Azure OpenAI provider implementation with API version 2024-10-21."""
from __future__ import annotations
import uuid
from typing import Any
from urllib.parse import urljoin
import httpx
import json_repair
from nanobot.providers.base import LLMProvider, LLMResponse, ToolCallRequest
_AZURE_MSG_KEYS = frozenset({"role", "content", "tool_calls", "tool_call_id", "name"})
class AzureOpenAIProvider(LLMProvider):
"""
Azure OpenAI provider with API version 2024-10-21 compliance.
Features:
- Hardcoded API version 2024-10-21
- Uses model field as Azure deployment name in URL path
- Uses api-key header instead of Authorization Bearer
- Uses max_completion_tokens instead of max_tokens
- Direct HTTP calls, bypasses LiteLLM
"""
def __init__(
self,
api_key: str = "",
api_base: str = "",
default_model: str = "gpt-5.2-chat",
):
super().__init__(api_key, api_base)
self.default_model = default_model
self.api_version = "2024-10-21"
# Validate required parameters
if not api_key:
raise ValueError("Azure OpenAI api_key is required")
if not api_base:
raise ValueError("Azure OpenAI api_base is required")
# Ensure api_base ends with /
if not api_base.endswith('/'):
api_base += '/'
self.api_base = api_base
def _build_chat_url(self, deployment_name: str) -> str:
"""Build the Azure OpenAI chat completions URL."""
# Azure OpenAI URL format:
# https://{resource}.openai.azure.com/openai/deployments/{deployment}/chat/completions?api-version={version}
base_url = self.api_base
if not base_url.endswith('/'):
base_url += '/'
url = urljoin(
base_url,
f"openai/deployments/{deployment_name}/chat/completions"
)
return f"{url}?api-version={self.api_version}"
def _build_headers(self) -> dict[str, str]:
"""Build headers for Azure OpenAI API with api-key header."""
return {
"Content-Type": "application/json",
"api-key": self.api_key, # Azure OpenAI uses api-key header, not Authorization
"x-session-affinity": uuid.uuid4().hex, # For cache locality
}
@staticmethod
def _supports_temperature(
deployment_name: str,
reasoning_effort: str | None = None,
) -> bool:
"""Return True when temperature is likely supported for this deployment."""
if reasoning_effort:
return False
name = deployment_name.lower()
return not any(token in name for token in ("gpt-5", "o1", "o3", "o4"))
def _prepare_request_payload(
self,
deployment_name: str,
messages: list[dict[str, Any]],
tools: list[dict[str, Any]] | None = None,
max_tokens: int = 4096,
temperature: float = 0.7,
reasoning_effort: str | None = None,
) -> dict[str, Any]:
"""Prepare the request payload with Azure OpenAI 2024-10-21 compliance."""
payload: dict[str, Any] = {
"messages": self._sanitize_request_messages(
self._sanitize_empty_content(messages),
_AZURE_MSG_KEYS,
),
"max_completion_tokens": max(1, max_tokens), # Azure API 2024-10-21 uses max_completion_tokens
}
if self._supports_temperature(deployment_name, reasoning_effort):
payload["temperature"] = temperature
if reasoning_effort:
payload["reasoning_effort"] = reasoning_effort
if tools:
payload["tools"] = tools
payload["tool_choice"] = "auto"
return payload
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,
reasoning_effort: str | None = None,
) -> LLMResponse:
"""
Send a chat completion request to Azure OpenAI.
Args:
messages: List of message dicts with 'role' and 'content'.
tools: Optional list of tool definitions in OpenAI format.
model: Model identifier (used as deployment name).
max_tokens: Maximum tokens in response (mapped to max_completion_tokens).
temperature: Sampling temperature.
reasoning_effort: Optional reasoning effort parameter.
Returns:
LLMResponse with content and/or tool calls.
"""
deployment_name = model or self.default_model
url = self._build_chat_url(deployment_name)
headers = self._build_headers()
payload = self._prepare_request_payload(
deployment_name, messages, tools, max_tokens, temperature, reasoning_effort
)
try:
async with httpx.AsyncClient(timeout=60.0, verify=True) as client:
response = await client.post(url, headers=headers, json=payload)
if response.status_code != 200:
return LLMResponse(
content=f"Azure OpenAI API Error {response.status_code}: {response.text}",
finish_reason="error",
)
response_data = response.json()
return self._parse_response(response_data)
except Exception as e:
return LLMResponse(
content=f"Error calling Azure OpenAI: {repr(e)}",
finish_reason="error",
)
def _parse_response(self, response: dict[str, Any]) -> LLMResponse:
"""Parse Azure OpenAI response into our standard format."""
try:
choice = response["choices"][0]
message = choice["message"]
tool_calls = []
if message.get("tool_calls"):
for tc in message["tool_calls"]:
# Parse arguments from JSON string if needed
args = tc["function"]["arguments"]
if isinstance(args, str):
args = json_repair.loads(args)
tool_calls.append(
ToolCallRequest(
id=tc["id"],
name=tc["function"]["name"],
arguments=args,
)
)
usage = {}
if response.get("usage"):
usage_data = response["usage"]
usage = {
"prompt_tokens": usage_data.get("prompt_tokens", 0),
"completion_tokens": usage_data.get("completion_tokens", 0),
"total_tokens": usage_data.get("total_tokens", 0),
}
reasoning_content = message.get("reasoning_content") or None
return LLMResponse(
content=message.get("content"),
tool_calls=tool_calls,
finish_reason=choice.get("finish_reason", "stop"),
usage=usage,
reasoning_content=reasoning_content,
)
except (KeyError, IndexError) as e:
return LLMResponse(
content=f"Error parsing Azure OpenAI response: {str(e)}",
finish_reason="error",
)
def get_default_model(self) -> str:
"""Get the default model (also used as default deployment name)."""
return self.default_model

14
nanobot/providers/base.py
View File

@@ -87,6 +87,20 @@ class LLMProvider(ABC):
result.append(msg)
return result
@staticmethod
def _sanitize_request_messages(
messages: list[dict[str, Any]],
allowed_keys: frozenset[str],
) -> list[dict[str, Any]]:
"""Keep only provider-safe message keys and normalize assistant content."""
sanitized = []
for msg in messages:
clean = {k: v for k, v in msg.items() if k in allowed_keys}
if clean.get("role") == "assistant" and "content" not in clean:
clean["content"] = None
sanitized.append(clean)
return sanitized
@abstractmethod
async def chat(
self,

41
nanobot/providers/litellm_provider.py
View File

@@ -1,5 +1,6 @@
"""LiteLLM provider implementation for multi-provider support."""
import hashlib
import os
import secrets
import string
@@ -166,17 +167,43 @@ class LiteLLMProvider(LLMProvider):
return _ANTHROPIC_EXTRA_KEYS
return frozenset()
@staticmethod
def _normalize_tool_call_id(tool_call_id: Any) -> Any:
"""Normalize tool_call_id to a provider-safe 9-char alphanumeric form."""
if not isinstance(tool_call_id, str):
return tool_call_id
if len(tool_call_id) == 9 and tool_call_id.isalnum():
return tool_call_id
return hashlib.sha1(tool_call_id.encode()).hexdigest()[:9]
@staticmethod
def _sanitize_messages(messages: list[dict[str, Any]], extra_keys: frozenset[str] = frozenset()) -> list[dict[str, Any]]:
"""Strip non-standard keys and ensure assistant messages have a content key."""
allowed = _ALLOWED_MSG_KEYS | extra_keys
sanitized = []
for msg in messages:
clean = {k: v for k, v in msg.items() if k in allowed}
# Strict providers require "content" even when assistant only has tool_calls
if clean.get("role") == "assistant" and "content" not in clean:
clean["content"] = None
sanitized.append(clean)
sanitized = LLMProvider._sanitize_request_messages(messages, allowed)
id_map: dict[str, str] = {}
def map_id(value: Any) -> Any:
if not isinstance(value, str):
return value
return id_map.setdefault(value, LiteLLMProvider._normalize_tool_call_id(value))
for clean in sanitized:
# Keep assistant tool_calls[].id and tool tool_call_id in sync after
# shortening, otherwise strict providers reject the broken linkage.
if isinstance(clean.get("tool_calls"), list):
normalized_tool_calls = []
for tc in clean["tool_calls"]:
if not isinstance(tc, dict):
normalized_tool_calls.append(tc)
continue
tc_clean = dict(tc)
tc_clean["id"] = map_id(tc_clean.get("id"))
normalized_tool_calls.append(tc_clean)
clean["tool_calls"] = normalized_tool_calls
if "tool_call_id" in clean and clean["tool_call_id"]:
clean["tool_call_id"] = map_id(clean["tool_call_id"])
return sanitized
async def chat(

10
nanobot/providers/registry.py
View File

@@ -79,6 +79,16 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
litellm_prefix="",
is_direct=True,
),
# === Azure OpenAI (direct API calls with API version 2024-10-21) =====
ProviderSpec(
name="azure_openai",
keywords=("azure", "azure-openai"),
env_key="",
display_name="Azure OpenAI",
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-"

3
nanobot/session/manager.py
View File

@@ -9,6 +9,7 @@ from typing import Any
from loguru import logger
from nanobot.config.paths import get_legacy_sessions_dir
from nanobot.utils.helpers import ensure_dir, safe_filename
@@ -79,7 +80,7 @@ class SessionManager:
def __init__(self, workspace: Path):
self.workspace = workspace
self.sessions_dir = ensure_dir(self.workspace / "sessions")
self.legacy_sessions_dir = Path.home() / ".nanobot" / "sessions"
self.legacy_sessions_dir = get_legacy_sessions_dir()
self._cache: dict[str, Session] = {}
def _get_session_path(self, key: str) -> Path:

4
nanobot/utils/__init__.py
View File

@@ -1,5 +1,5 @@
"""Utility functions for nanobot."""
from nanobot.utils.helpers import ensure_dir, get_data_path, get_workspace_path
from nanobot.utils.helpers import ensure_dir
__all__ = ["ensure_dir", "get_workspace_path", "get_data_path"]
__all__ = ["ensure_dir"]

11
nanobot/utils/helpers.py
View File

@@ -24,17 +24,6 @@ def ensure_dir(path: Path) -> Path:
return path
def get_data_path() -> Path:
"""~/.nanobot data directory."""
return ensure_dir(Path.home() / ".nanobot")
def get_workspace_path(workspace: str | None = None) -> Path:
"""Resolve and ensure workspace path. Defaults to ~/.nanobot/workspace."""
path = Path(workspace).expanduser() if workspace else Path.home() / ".nanobot" / "workspace"
return ensure_dir(path)
def timestamp() -> str:
"""Current ISO timestamp."""
return datetime.now().isoformat()