merge origin/main into pr-1824

- wire tools.exec.enable and deny_patterns into the current AgentLoop
- preserve the current WebSearchTool config-based registration path
- treat deny_patterns=[] as an explicit override instead of falling back
  to the default blacklist
- add regression coverage for disabled exec registration and custom deny
  patterns

Made-with: Cursor
This commit is contained in:
Xubin Ren
2026-03-20 17:21:42 +00:00
94 changed files with 11768 additions and 1465 deletions
+102 -95
View File
@@ -4,8 +4,9 @@ from __future__ import annotations
import asyncio
import json
import os
import re
import weakref
import sys
from contextlib import AsyncExitStack
from pathlib import Path
from typing import TYPE_CHECKING, Any, Awaitable, Callable
@@ -13,9 +14,10 @@ from typing import TYPE_CHECKING, Any, Awaitable, Callable
from loguru import logger
from nanobot.agent.context import ContextBuilder
from nanobot.agent.memory import MemoryStore
from nanobot.agent.memory import MemoryConsolidator
from nanobot.agent.subagent import SubagentManager
from nanobot.agent.tools.cron import CronTool
from nanobot.agent.skills import BUILTIN_SKILLS_DIR
from nanobot.agent.tools.filesystem import EditFileTool, ListDirTool, ReadFileTool, WriteFileTool
from nanobot.agent.tools.message import MessageTool
from nanobot.agent.tools.registry import ToolRegistry
@@ -28,7 +30,7 @@ from nanobot.providers.base import LLMProvider
from nanobot.session.manager import Session, SessionManager
if TYPE_CHECKING:
from nanobot.config.schema import ChannelsConfig, ExecToolConfig
from nanobot.config.schema import ChannelsConfig, ExecToolConfig, WebSearchConfig
from nanobot.cron.service import CronService
@@ -44,7 +46,7 @@ class AgentLoop:
5. Sends responses back
"""
_TOOL_RESULT_MAX_CHARS = 500
_TOOL_RESULT_MAX_CHARS = 16_000
def __init__(
self,
@@ -53,11 +55,8 @@ class AgentLoop:
workspace: Path,
model: str | None = None,
max_iterations: int = 40,
temperature: float = 0.1,
max_tokens: int = 4096,
memory_window: int = 100,
reasoning_effort: str | None = None,
brave_api_key: str | None = None,
context_window_tokens: int = 65_536,
web_search_config: WebSearchConfig | None = None,
web_proxy: str | None = None,
exec_config: ExecToolConfig | None = None,
cron_service: CronService | None = None,
@@ -66,18 +65,16 @@ class AgentLoop:
mcp_servers: dict | None = None,
channels_config: ChannelsConfig | None = None,
):
from nanobot.config.schema import ExecToolConfig
from nanobot.config.schema import ExecToolConfig, WebSearchConfig
self.bus = bus
self.channels_config = channels_config
self.provider = provider
self.workspace = workspace
self.model = model or provider.get_default_model()
self.max_iterations = max_iterations
self.temperature = temperature
self.max_tokens = max_tokens
self.memory_window = memory_window
self.reasoning_effort = reasoning_effort
self.brave_api_key = brave_api_key
self.context_window_tokens = context_window_tokens
self.web_search_config = web_search_config or WebSearchConfig()
self.web_proxy = web_proxy
self.exec_config = exec_config or ExecToolConfig()
self.cron_service = cron_service
@@ -91,10 +88,7 @@ class AgentLoop:
workspace=workspace,
bus=bus,
model=self.model,
temperature=self.temperature,
max_tokens=self.max_tokens,
reasoning_effort=reasoning_effort,
brave_api_key=brave_api_key,
web_search_config=self.web_search_config,
web_proxy=web_proxy,
exec_config=self.exec_config,
restrict_to_workspace=restrict_to_workspace,
@@ -105,17 +99,26 @@ class AgentLoop:
self._mcp_stack: AsyncExitStack | None = None
self._mcp_connected = False
self._mcp_connecting = False
self._consolidating: set[str] = set() # Session keys with consolidation in progress
self._consolidation_tasks: set[asyncio.Task] = set() # Strong refs to in-flight tasks
self._consolidation_locks: weakref.WeakValueDictionary[str, asyncio.Lock] = weakref.WeakValueDictionary()
self._active_tasks: dict[str, list[asyncio.Task]] = {} # session_key -> tasks
self._background_tasks: list[asyncio.Task] = []
self._processing_lock = asyncio.Lock()
self.memory_consolidator = MemoryConsolidator(
workspace=workspace,
provider=provider,
model=self.model,
sessions=self.sessions,
context_window_tokens=context_window_tokens,
build_messages=self.context.build_messages,
get_tool_definitions=self.tools.get_definitions,
)
self._register_default_tools()
def _register_default_tools(self) -> None:
"""Register the default set of tools."""
allowed_dir = self.workspace if self.restrict_to_workspace else None
for cls in (ReadFileTool, WriteFileTool, EditFileTool, ListDirTool):
extra_read = [BUILTIN_SKILLS_DIR] if allowed_dir else None
self.tools.register(ReadFileTool(workspace=self.workspace, allowed_dir=allowed_dir, extra_allowed_dirs=extra_read))
for cls in (WriteFileTool, EditFileTool, ListDirTool):
self.tools.register(cls(workspace=self.workspace, allowed_dir=allowed_dir))
if self.exec_config.enable:
self.tools.register(ExecTool(
@@ -125,7 +128,7 @@ class AgentLoop:
path_append=self.exec_config.path_append,
deny_patterns=self.exec_config.deny_patterns,
))
self.tools.register(WebSearchTool(api_key=self.brave_api_key, proxy=self.web_proxy))
self.tools.register(WebSearchTool(config=self.web_search_config, proxy=self.web_proxy))
self.tools.register(WebFetchTool(proxy=self.web_proxy))
self.tools.register(MessageTool(send_callback=self.bus.publish_outbound))
self.tools.register(SpawnTool(manager=self.subagents))
@@ -143,7 +146,7 @@ class AgentLoop:
await self._mcp_stack.__aenter__()
await connect_mcp_servers(self._mcp_servers, self.tools, self._mcp_stack)
self._mcp_connected = True
except Exception as e:
except BaseException as e:
logger.error("Failed to connect MCP servers (will retry next message): {}", e)
if self._mcp_stack:
try:
@@ -184,7 +187,7 @@ class AgentLoop:
initial_messages: list[dict],
on_progress: Callable[..., Awaitable[None]] | None = None,
) -> tuple[str | None, list[str], list[dict]]:
"""Run the agent iteration loop. Returns (final_content, tools_used, messages)."""
"""Run the agent iteration loop."""
messages = initial_messages
iteration = 0
final_content = None
@@ -193,13 +196,12 @@ class AgentLoop:
while iteration < self.max_iterations:
iteration += 1
response = await self.provider.chat(
tool_defs = self.tools.get_definitions()
response = await self.provider.chat_with_retry(
messages=messages,
tools=self.tools.get_definitions(),
tools=tool_defs,
model=self.model,
temperature=self.temperature,
max_tokens=self.max_tokens,
reasoning_effort=self.reasoning_effort,
)
if response.has_tool_calls:
@@ -207,17 +209,12 @@ class AgentLoop:
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_hint = self._tool_hint(response.tool_calls)
tool_hint = self._strip_think(tool_hint)
await on_progress(tool_hint, tool_hint=True)
tool_call_dicts = [
{
"id": tc.id,
"type": "function",
"function": {
"name": tc.name,
"arguments": json.dumps(tc.arguments, ensure_ascii=False)
}
}
tc.to_openai_tool_call()
for tc in response.tool_calls
]
messages = self.context.add_assistant_message(
@@ -269,9 +266,21 @@ class AgentLoop:
msg = await asyncio.wait_for(self.bus.consume_inbound(), timeout=1.0)
except asyncio.TimeoutError:
continue
except asyncio.CancelledError:
# Preserve real task cancellation so shutdown can complete cleanly.
# Only ignore non-task CancelledError signals that may leak from integrations.
if not self._running or asyncio.current_task().cancelling():
raise
continue
except Exception as e:
logger.warning("Error consuming inbound message: {}, continuing...", e)
continue
if msg.content.strip().lower() == "/stop":
cmd = msg.content.strip().lower()
if cmd == "/stop":
await self._handle_stop(msg)
elif cmd == "/restart":
await self._handle_restart(msg)
else:
task = asyncio.create_task(self._dispatch(msg))
self._active_tasks.setdefault(msg.session_key, []).append(task)
@@ -288,11 +297,25 @@ class AgentLoop:
pass
sub_cancelled = await self.subagents.cancel_by_session(msg.session_key)
total = cancelled + sub_cancelled
content = f"Stopped {total} task(s)." if total else "No active task to stop."
content = f"Stopped {total} task(s)." if total else "No active task to stop."
await self.bus.publish_outbound(OutboundMessage(
channel=msg.channel, chat_id=msg.chat_id, content=content,
))
async def _handle_restart(self, msg: InboundMessage) -> None:
"""Restart the process in-place via os.execv."""
await self.bus.publish_outbound(OutboundMessage(
channel=msg.channel, chat_id=msg.chat_id, content="Restarting...",
))
async def _do_restart():
await asyncio.sleep(1)
# Use -m nanobot instead of sys.argv[0] for Windows compatibility
# (sys.argv[0] may be just "nanobot" without full path on Windows)
os.execv(sys.executable, [sys.executable, "-m", "nanobot"] + sys.argv[1:])
asyncio.create_task(_do_restart())
async def _dispatch(self, msg: InboundMessage) -> None:
"""Process a message under the global lock."""
async with self._processing_lock:
@@ -316,7 +339,10 @@ class AgentLoop:
))
async def close_mcp(self) -> None:
"""Close MCP connections."""
"""Drain pending background archives, then close MCP connections."""
if self._background_tasks:
await asyncio.gather(*self._background_tasks, return_exceptions=True)
self._background_tasks.clear()
if self._mcp_stack:
try:
await self._mcp_stack.aclose()
@@ -324,6 +350,12 @@ class AgentLoop:
pass # MCP SDK cancel scope cleanup is noisy but harmless
self._mcp_stack = None
def _schedule_background(self, coro) -> None:
"""Schedule a coroutine as a tracked background task (drained on shutdown)."""
task = asyncio.create_task(coro)
self._background_tasks.append(task)
task.add_done_callback(self._background_tasks.remove)
def stop(self) -> None:
"""Stop the agent loop."""
self._running = False
@@ -343,15 +375,20 @@ class AgentLoop:
logger.info("Processing system message from {}", msg.sender_id)
key = f"{channel}:{chat_id}"
session = self.sessions.get_or_create(key)
await self.memory_consolidator.maybe_consolidate_by_tokens(session)
self._set_tool_context(channel, chat_id, msg.metadata.get("message_id"))
history = session.get_history(max_messages=self.memory_window)
history = session.get_history(max_messages=0)
# Subagent results should be assistant role, other system messages use user role
current_role = "assistant" if msg.sender_id == "subagent" else "user"
messages = self.context.build_messages(
history=history,
current_message=msg.content, channel=channel, chat_id=chat_id,
current_role=current_role,
)
final_content, _, all_msgs = await self._run_agent_loop(messages)
self._save_turn(session, all_msgs, 1 + len(history))
self.sessions.save(session)
self._schedule_background(self.memory_consolidator.maybe_consolidate_by_tokens(session))
return OutboundMessage(channel=channel, chat_id=chat_id,
content=final_content or "Background task completed.")
@@ -364,61 +401,35 @@ class AgentLoop:
# Slash commands
cmd = msg.content.strip().lower()
if cmd == "/new":
lock = self._consolidation_locks.setdefault(session.key, asyncio.Lock())
self._consolidating.add(session.key)
try:
async with lock:
snapshot = session.messages[session.last_consolidated:]
if snapshot:
temp = Session(key=session.key)
temp.messages = list(snapshot)
if not await self._consolidate_memory(temp, archive_all=True):
return OutboundMessage(
channel=msg.channel, chat_id=msg.chat_id,
content="Memory archival failed, session not cleared. Please try again.",
)
except Exception:
logger.exception("/new archival failed for {}", session.key)
return OutboundMessage(
channel=msg.channel, chat_id=msg.chat_id,
content="Memory archival failed, session not cleared. Please try again.",
)
finally:
self._consolidating.discard(session.key)
snapshot = session.messages[session.last_consolidated:]
session.clear()
self.sessions.save(session)
self.sessions.invalidate(session.key)
if snapshot:
self._schedule_background(self.memory_consolidator.archive_messages(snapshot))
return OutboundMessage(channel=msg.channel, chat_id=msg.chat_id,
content="New session started.")
if cmd == "/help":
return OutboundMessage(channel=msg.channel, chat_id=msg.chat_id,
content="🐈 nanobot commands:\n/new — Start a new conversation\n/stop — Stop the current task\n/help — Show available commands")
unconsolidated = len(session.messages) - session.last_consolidated
if (unconsolidated >= self.memory_window and session.key not in self._consolidating):
self._consolidating.add(session.key)
lock = self._consolidation_locks.setdefault(session.key, asyncio.Lock())
async def _consolidate_and_unlock():
try:
async with lock:
await self._consolidate_memory(session)
finally:
self._consolidating.discard(session.key)
_task = asyncio.current_task()
if _task is not None:
self._consolidation_tasks.discard(_task)
_task = asyncio.create_task(_consolidate_and_unlock())
self._consolidation_tasks.add(_task)
lines = [
"🐈 nanobot commands:",
"/new — Start a new conversation",
"/stop — Stop the current task",
"/restart — Restart the bot",
"/help — Show available commands",
]
return OutboundMessage(
channel=msg.channel, chat_id=msg.chat_id, content="\n".join(lines),
)
await self.memory_consolidator.maybe_consolidate_by_tokens(session)
self._set_tool_context(msg.channel, msg.chat_id, msg.metadata.get("message_id"))
if message_tool := self.tools.get("message"):
if isinstance(message_tool, MessageTool):
message_tool.start_turn()
history = session.get_history(max_messages=self.memory_window)
history = session.get_history(max_messages=0)
initial_messages = self.context.build_messages(
history=history,
current_message=msg.content,
@@ -443,6 +454,7 @@ class AgentLoop:
self._save_turn(session, all_msgs, 1 + len(history))
self.sessions.save(session)
self._schedule_background(self.memory_consolidator.maybe_consolidate_by_tokens(session))
if (mt := self.tools.get("message")) and isinstance(mt, MessageTool) and mt._sent_in_turn:
return None
@@ -479,7 +491,9 @@ class AgentLoop:
continue # Strip runtime context from multimodal messages
if (c.get("type") == "image_url"
and c.get("image_url", {}).get("url", "").startswith("data:image/")):
filtered.append({"type": "text", "text": "[image]"})
path = (c.get("_meta") or {}).get("path", "")
placeholder = f"[image: {path}]" if path else "[image]"
filtered.append({"type": "text", "text": placeholder})
else:
filtered.append(c)
if not filtered:
@@ -489,13 +503,6 @@ class AgentLoop:
session.messages.append(entry)
session.updated_at = datetime.now()
async def _consolidate_memory(self, session, archive_all: bool = False) -> bool:
"""Delegate to MemoryStore.consolidate(). Returns True on success."""
return await MemoryStore(self.workspace).consolidate(
session, self.provider, self.model,
archive_all=archive_all, memory_window=self.memory_window,
)
async def process_direct(
self,
content: str,