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

Merge origin/main into pr-2959

Browse Source 
Resolve the config plumbing conflicts and keep disabled skill filtering consistent for subagent prompts after syncing with main.

Made-with: Cursor
This commit is contained in:
Xubin Ren
2026-04-12 02:02:39 +00:00
parent e9c4fe6824 ee946d96ca
commit 09c238ca0f
56 changed files with 9305 additions and 463 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nanobot/agent/autocompact.py
+115
View File
@@ -0,0 +1,115 @@
"""Auto compact: proactive compression of idle sessions to reduce token cost and latency."""
from __future__ import annotations
from datetime import datetime
from typing import TYPE_CHECKING, Any, Callable, Coroutine
from loguru import logger
from nanobot.session.manager import Session, SessionManager
if TYPE_CHECKING:
from nanobot.agent.memory import Consolidator
class AutoCompact:
_RECENT_SUFFIX_MESSAGES = 8
def __init__(self, sessions: SessionManager, consolidator: Consolidator,
session_ttl_minutes: int = 0):
self.sessions = sessions
self.consolidator = consolidator
self._ttl = session_ttl_minutes
self._archiving: set[str] = set()
self._summaries: dict[str, tuple[str, datetime]] = {}
def _is_expired(self, ts: datetime | str | None) -> bool:
if self._ttl <= 0 or not ts:
return False
if isinstance(ts, str):
ts = datetime.fromisoformat(ts)
return (datetime.now() - ts).total_seconds() >= self._ttl * 60
@staticmethod
def _format_summary(text: str, last_active: datetime) -> str:
idle_min = int((datetime.now() - last_active).total_seconds() / 60)
return f"Inactive for {idle_min} minutes.\nPrevious conversation summary: {text}"
def _split_unconsolidated(
self, session: Session,
) -> tuple[list[dict[str, Any]], list[dict[str, Any]]]:
"""Split live session tail into archiveable prefix and retained recent suffix."""
tail = list(session.messages[session.last_consolidated:])
if not tail:
return [], []
probe = Session(
key=session.key,
messages=tail.copy(),
created_at=session.created_at,
updated_at=session.updated_at,
metadata={},
last_consolidated=0,
)
probe.retain_recent_legal_suffix(self._RECENT_SUFFIX_MESSAGES)
kept = probe.messages
cut = len(tail) - len(kept)
return tail[:cut], kept
def check_expired(self, schedule_background: Callable[[Coroutine], None]) -> None:
for info in self.sessions.list_sessions():
key = info.get("key", "")
if key and key not in self._archiving and self._is_expired(info.get("updated_at")):
self._archiving.add(key)
logger.debug("Auto-compact: scheduling archival for {} (idle > {} min)", key, self._ttl)
schedule_background(self._archive(key))
async def _archive(self, key: str) -> None:
try:
self.sessions.invalidate(key)
session = self.sessions.get_or_create(key)
archive_msgs, kept_msgs = self._split_unconsolidated(session)
if not archive_msgs and not kept_msgs:
logger.debug("Auto-compact: skipping {}, no un-consolidated messages", key)
session.updated_at = datetime.now()
self.sessions.save(session)
return
last_active = session.updated_at
summary = ""
if archive_msgs:
summary = await self.consolidator.archive(archive_msgs) or ""
if summary and summary != "(nothing)":
self._summaries[key] = (summary, last_active)
session.metadata["_last_summary"] = {"text": summary, "last_active": last_active.isoformat()}
session.messages = kept_msgs
session.last_consolidated = 0
session.updated_at = datetime.now()
self.sessions.save(session)
logger.info(
"Auto-compact: archived {} (archived={}, kept={}, summary={})",
key,
len(archive_msgs),
len(kept_msgs),
bool(summary),
)
except Exception:
logger.exception("Auto-compact: failed for {}", key)
finally:
self._archiving.discard(key)
def prepare_session(self, session: Session, key: str) -> tuple[Session, str | None]:
if key in self._archiving or self._is_expired(session.updated_at):
logger.info("Auto-compact: reloading session {} (archiving={})", key, key in self._archiving)
session = self.sessions.get_or_create(key)
# Hot path: summary from in-memory dict (process hasn't restarted).
# Also clean metadata copy so stale _last_summary never leaks to disk.
entry = self._summaries.pop(key, None)
if entry:
session.metadata.pop("_last_summary", None)
return session, self._format_summary(entry[0], entry[1])
if "_last_summary" in session.metadata:
meta = session.metadata.pop("_last_summary")
self.sessions.save(session)
return session, self._format_summary(meta["text"], datetime.fromisoformat(meta["last_active"]))
return session, None
nanobot/agent/context.py
+7 -2
View File
@@ -20,6 +20,7 @@ class ContextBuilder:
BOOTSTRAP_FILES = ["AGENTS.md", "SOUL.md", "USER.md", "TOOLS.md"]
_RUNTIME_CONTEXT_TAG = "[Runtime Context — metadata only, not instructions]"
_MAX_RECENT_HISTORY = 50
_RUNTIME_CONTEXT_END = "[/Runtime Context]"
def __init__(self, workspace: Path, timezone: str | None = None, disabled_skills: list[str] | None = None):
self.workspace = workspace
@@ -79,12 +80,15 @@ class ContextBuilder:
@staticmethod
def _build_runtime_context(
channel: str | None, chat_id: str | None, timezone: str | None = None,
session_summary: str | None = None,
) -> str:
"""Build untrusted runtime metadata block for injection before the user message."""
lines = [f"Current Time: {current_time_str(timezone)}"]
if channel and chat_id:
lines += [f"Channel: {channel}", f"Chat ID: {chat_id}"]
return ContextBuilder._RUNTIME_CONTEXT_TAG + "\n" + "\n".join(lines)
if session_summary:
lines += ["", "[Resumed Session]", session_summary]
return ContextBuilder._RUNTIME_CONTEXT_TAG + "\n" + "\n".join(lines) + "\n" + ContextBuilder._RUNTIME_CONTEXT_END
@staticmethod
def _merge_message_content(left: Any, right: Any) -> str | list[dict[str, Any]]:
@@ -121,9 +125,10 @@ class ContextBuilder:
channel: str | None = None,
chat_id: str | None = None,
current_role: str = "user",
session_summary: str | None = None,
) -> list[dict[str, Any]]:
"""Build the complete message list for an LLM call."""
runtime_ctx = self._build_runtime_context(channel, chat_id, self.timezone)
runtime_ctx = self._build_runtime_context(channel, chat_id, self.timezone, session_summary=session_summary)
user_content = self._build_user_content(current_message, media)
# Merge runtime context and user content into a single user message
nanobot/agent/loop.py
+286 -120
View File
@@ -13,15 +13,17 @@ from typing import TYPE_CHECKING, Any, Awaitable, Callable
from loguru import logger
from nanobot.agent.autocompact import AutoCompact
from nanobot.agent.context import ContextBuilder
from nanobot.agent.hook import AgentHook, AgentHookContext, CompositeHook
from nanobot.agent.memory import Consolidator, Dream
from nanobot.agent.runner import AgentRunSpec, AgentRunner
from nanobot.agent.runner import _MAX_INJECTIONS_PER_TURN, AgentRunSpec, AgentRunner
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.notebook import NotebookEditTool
from nanobot.agent.tools.registry import ToolRegistry
from nanobot.agent.tools.search import GlobTool, GrepTool
from nanobot.agent.tools.shell import ExecTool
@@ -33,7 +35,7 @@ from nanobot.bus.queue import MessageBus
from nanobot.config.schema import AgentDefaults
from nanobot.providers.base import LLMProvider
from nanobot.session.manager import Session, SessionManager
from nanobot.utils.helpers import image_placeholder_text, truncate_text
from nanobot.utils.helpers import image_placeholder_text, truncate_text as truncate_text_fn
from nanobot.utils.runtime import EMPTY_FINAL_RESPONSE_MESSAGE
if TYPE_CHECKING:
@@ -43,6 +45,7 @@ if TYPE_CHECKING:
UNIFIED_SESSION_KEY = "unified:default"
class _LoopHook(AgentHook):
"""Core hook for the main loop."""
@@ -76,7 +79,7 @@ class _LoopHook(AgentHook):
prev_clean = strip_think(self._stream_buf)
self._stream_buf += delta
new_clean = strip_think(self._stream_buf)
incremental = new_clean[len(prev_clean):]
incremental = new_clean[len(prev_clean) :]
if incremental and self._on_stream:
await self._on_stream(incremental)
@@ -112,6 +115,7 @@ class _LoopHook(AgentHook):
def finalize_content(self, context: AgentHookContext, content: str | None) -> str | None:
return self._loop._strip_think(content)
class AgentLoop:
"""
The agent loop is the core processing engine.
@@ -145,6 +149,7 @@ class AgentLoop:
mcp_servers: dict | None = None,
channels_config: ChannelsConfig | None = None,
timezone: str | None = None,
session_ttl_minutes: int = 0,
hooks: list[AgentHook] | None = None,
unified_session: bool = False,
disabled_skills: list[str] | None = None,
@@ -193,16 +198,21 @@ class AgentLoop:
max_tool_result_chars=self.max_tool_result_chars,
exec_config=self.exec_config,
restrict_to_workspace=restrict_to_workspace,
disabled_skills=disabled_skills,
)
self._unified_session = unified_session
self._running = False
self._mcp_servers = mcp_servers or {}
self._mcp_stack: AsyncExitStack | None = None
self._mcp_stacks: dict[str, AsyncExitStack] = {}
self._mcp_connected = False
self._mcp_connecting = False
self._active_tasks: dict[str, list[asyncio.Task]] = {} # session_key -> tasks
self._background_tasks: list[asyncio.Task] = []
self._session_locks: dict[str, asyncio.Lock] = {}
# Per-session pending queues for mid-turn message injection.
# When a session has an active task, new messages for that session
# are routed here instead of creating a new task.
self._pending_queues: dict[str, asyncio.Queue] = {}
# NANOBOT_MAX_CONCURRENT_REQUESTS: <=0 means unlimited; default 3.
_max = int(os.environ.get("NANOBOT_MAX_CONCURRENT_REQUESTS", "3"))
self._concurrency_gate: asyncio.Semaphore | None = (
@@ -218,6 +228,11 @@ class AgentLoop:
get_tool_definitions=self.tools.get_definitions,
max_completion_tokens=provider.generation.max_tokens,
)
self.auto_compact = AutoCompact(
sessions=self.sessions,
consolidator=self.consolidator,
session_ttl_minutes=session_ttl_minutes,
)
self.dream = Dream(
store=self.context.memory,
provider=provider,
@@ -229,23 +244,35 @@ class AgentLoop:
def _register_default_tools(self) -> None:
"""Register the default set of tools."""
allowed_dir = self.workspace if (self.restrict_to_workspace or self.exec_config.sandbox) else None
allowed_dir = (
self.workspace if (self.restrict_to_workspace or self.exec_config.sandbox) else None
)
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))
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))
for cls in (GlobTool, GrepTool):
self.tools.register(cls(workspace=self.workspace, allowed_dir=allowed_dir))
self.tools.register(NotebookEditTool(workspace=self.workspace, allowed_dir=allowed_dir))
if self.exec_config.enable:
self.tools.register(ExecTool(
working_dir=str(self.workspace),
timeout=self.exec_config.timeout,
restrict_to_workspace=self.restrict_to_workspace,
sandbox=self.exec_config.sandbox,
path_append=self.exec_config.path_append,
))
self.tools.register(
ExecTool(
working_dir=str(self.workspace),
timeout=self.exec_config.timeout,
restrict_to_workspace=self.restrict_to_workspace,
sandbox=self.exec_config.sandbox,
path_append=self.exec_config.path_append,
allowed_env_keys=self.exec_config.allowed_env_keys,
)
)
if self.web_config.enable:
self.tools.register(WebSearchTool(config=self.web_config.search, proxy=self.web_config.proxy))
self.tools.register(
WebSearchTool(config=self.web_config.search, proxy=self.web_config.proxy)
)
self.tools.register(WebFetchTool(proxy=self.web_config.proxy))
self.tools.register(MessageTool(send_callback=self.bus.publish_outbound))
self.tools.register(SpawnTool(manager=self.subagents))
@@ -260,19 +287,19 @@ class AgentLoop:
return
self._mcp_connecting = True
from nanobot.agent.tools.mcp import connect_mcp_servers
try:
self._mcp_stack = AsyncExitStack()
await self._mcp_stack.__aenter__()
await connect_mcp_servers(self._mcp_servers, self.tools, self._mcp_stack)
self._mcp_connected = True
self._mcp_stacks = await connect_mcp_servers(self._mcp_servers, self.tools)
if self._mcp_stacks:
self._mcp_connected = True
else:
logger.warning("No MCP servers connected successfully (will retry next message)")
except asyncio.CancelledError:
logger.warning("MCP connection cancelled (will retry next message)")
self._mcp_stacks.clear()
except BaseException as e:
logger.error("Failed to connect MCP servers (will retry next message): {}", e)
if self._mcp_stack:
try:
await self._mcp_stack.aclose()
except Exception:
pass
self._mcp_stack = None
self._mcp_stacks.clear()
finally:
self._mcp_connecting = False
@@ -289,6 +316,7 @@ class AgentLoop:
if not text:
return None
from nanobot.utils.helpers import strip_think
return strip_think(text) or None
@staticmethod
@@ -298,6 +326,12 @@ class AgentLoop:
return format_tool_hints(tool_calls)
def _effective_session_key(self, msg: InboundMessage) -> str:
"""Return the session key used for task routing and mid-turn injections."""
if self._unified_session and not msg.session_key_override:
return UNIFIED_SESSION_KEY
return msg.session_key
async def _run_agent_loop(
self,
initial_messages: list[dict],
@@ -309,13 +343,16 @@ class AgentLoop:
channel: str = "cli",
chat_id: str = "direct",
message_id: str | None = None,
) -> tuple[str | None, list[str], list[dict]]:
pending_queue: asyncio.Queue | None = None,
) -> tuple[str | None, list[str], list[dict], str, bool]:
"""Run the agent iteration loop.
*on_stream*: called with each content delta during streaming.
*on_stream_end(resuming)*: called when a streaming session finishes.
``resuming=True`` means tool calls follow (spinner should restart);
``resuming=False`` means this is the final response.
Returns (final_content, tools_used, messages, stop_reason, had_injections).
"""
loop_hook = _LoopHook(
self,
@@ -327,9 +364,7 @@ class AgentLoop:
message_id=message_id,
)
hook: AgentHook = (
CompositeHook([loop_hook] + self._extra_hooks)
if self._extra_hooks
else loop_hook
CompositeHook([loop_hook] + self._extra_hooks) if self._extra_hooks else loop_hook
)
async def _checkpoint(payload: dict[str, Any]) -> None:
@@ -337,6 +372,32 @@ class AgentLoop:
return
self._set_runtime_checkpoint(session, payload)
async def _drain_pending(*, limit: int = _MAX_INJECTIONS_PER_TURN) -> list[dict[str, Any]]:
"""Non-blocking drain of follow-up messages from the pending queue."""
if pending_queue is None:
return []
items: list[dict[str, Any]] = []
while len(items) < limit:
try:
pending_msg = pending_queue.get_nowait()
except asyncio.QueueEmpty:
break
user_content = self.context._build_user_content(
pending_msg.content,
pending_msg.media if pending_msg.media else None,
)
runtime_ctx = self.context._build_runtime_context(
pending_msg.channel,
pending_msg.chat_id,
self.context.timezone,
)
if isinstance(user_content, str):
merged: str | list[dict[str, Any]] = f"{runtime_ctx}\n\n{user_content}"
else:
merged = [{"type": "text", "text": runtime_ctx}] + user_content
items.append({"role": "user", "content": merged})
return items
result = await self.runner.run(AgentRunSpec(
initial_messages=initial_messages,
tools=self.tools,
@@ -353,13 +414,14 @@ class AgentLoop:
provider_retry_mode=self.provider_retry_mode,
progress_callback=on_progress,
checkpoint_callback=_checkpoint,
injection_callback=_drain_pending,
))
self._last_usage = result.usage
if result.stop_reason == "max_iterations":
logger.warning("Max iterations ({}) reached", self.max_iterations)
elif result.stop_reason == "error":
logger.error("LLM returned error: {}", (result.final_content or "")[:200])
return result.final_content, result.tools_used, result.messages
return result.final_content, result.tools_used, result.messages, result.stop_reason, result.had_injections
async def run(self) -> None:
"""Run the agent loop, dispatching messages as tasks to stay responsive to /stop."""
@@ -371,6 +433,7 @@ class AgentLoop:
try:
msg = await asyncio.wait_for(self.bus.consume_inbound(), timeout=1.0)
except asyncio.TimeoutError:
self.auto_compact.check_expired(self._schedule_background)
continue
except asyncio.CancelledError:
# Preserve real task cancellation so shutdown can complete cleanly.
@@ -389,84 +452,140 @@ class AgentLoop:
if result:
await self.bus.publish_outbound(result)
continue
effective_key = self._effective_session_key(msg)
# If this session already has an active pending queue (i.e. a task
# is processing this session), route the message there for mid-turn
# injection instead of creating a competing task.
if effective_key in self._pending_queues:
pending_msg = msg
if effective_key != msg.session_key:
pending_msg = dataclasses.replace(
msg,
session_key_override=effective_key,
)
try:
self._pending_queues[effective_key].put_nowait(pending_msg)
except asyncio.QueueFull:
logger.warning(
"Pending queue full for session {}, falling back to queued task",
effective_key,
)
else:
logger.info(
"Routed follow-up message to pending queue for session {}",
effective_key,
)
continue
# Compute the effective session key before dispatching
# This ensures /stop command can find tasks correctly when unified session is enabled
effective_key = UNIFIED_SESSION_KEY if self._unified_session and not msg.session_key_override else msg.session_key
task = asyncio.create_task(self._dispatch(msg))
self._active_tasks.setdefault(effective_key, []).append(task)
task.add_done_callback(lambda t, k=effective_key: self._active_tasks.get(k, []) and self._active_tasks[k].remove(t) if t in self._active_tasks.get(k, []) else None)
task.add_done_callback(
lambda t, k=effective_key: self._active_tasks.get(k, [])
and self._active_tasks[k].remove(t)
if t in self._active_tasks.get(k, [])
else None
)
async def _dispatch(self, msg: InboundMessage) -> None:
"""Process a message: per-session serial, cross-session concurrent."""
if self._unified_session and not msg.session_key_override:
msg = dataclasses.replace(msg, session_key_override=UNIFIED_SESSION_KEY)
lock = self._session_locks.setdefault(msg.session_key, asyncio.Lock())
session_key = self._effective_session_key(msg)
if session_key != msg.session_key:
msg = dataclasses.replace(msg, session_key_override=session_key)
lock = self._session_locks.setdefault(session_key, asyncio.Lock())
gate = self._concurrency_gate or nullcontext()
async with lock, gate:
try:
on_stream = on_stream_end = None
if msg.metadata.get("_wants_stream"):
# Split one answer into distinct stream segments.
stream_base_id = f"{msg.session_key}:{time.time_ns()}"
stream_segment = 0
def _current_stream_id() -> str:
return f"{stream_base_id}:{stream_segment}"
# Register a pending queue so follow-up messages for this session are
# routed here (mid-turn injection) instead of spawning a new task.
pending = asyncio.Queue(maxsize=20)
self._pending_queues[session_key] = pending
async def on_stream(delta: str) -> None:
meta = dict(msg.metadata or {})
meta["_stream_delta"] = True
meta["_stream_id"] = _current_stream_id()
try:
async with lock, gate:
try:
on_stream = on_stream_end = None
if msg.metadata.get("_wants_stream"):
# Split one answer into distinct stream segments.
stream_base_id = f"{msg.session_key}:{time.time_ns()}"
stream_segment = 0
def _current_stream_id() -> str:
return f"{stream_base_id}:{stream_segment}"
async def on_stream(delta: str) -> None:
meta = dict(msg.metadata or {})
meta["_stream_delta"] = True
meta["_stream_id"] = _current_stream_id()
await self.bus.publish_outbound(OutboundMessage(
channel=msg.channel, chat_id=msg.chat_id,
content=delta,
metadata=meta,
))
async def on_stream_end(*, resuming: bool = False) -> None:
nonlocal stream_segment
meta = dict(msg.metadata or {})
meta["_stream_end"] = True
meta["_resuming"] = resuming
meta["_stream_id"] = _current_stream_id()
await self.bus.publish_outbound(OutboundMessage(
channel=msg.channel, chat_id=msg.chat_id,
content="",
metadata=meta,
))
stream_segment += 1
response = await self._process_message(
msg, on_stream=on_stream, on_stream_end=on_stream_end,
pending_queue=pending,
)
if response is not None:
await self.bus.publish_outbound(response)
elif msg.channel == "cli":
await self.bus.publish_outbound(OutboundMessage(
channel=msg.channel, chat_id=msg.chat_id,
content=delta,
metadata=meta,
content="", metadata=msg.metadata or {},
))
async def on_stream_end(*, resuming: bool = False) -> None:
nonlocal stream_segment
meta = dict(msg.metadata or {})
meta["_stream_end"] = True
meta["_resuming"] = resuming
meta["_stream_id"] = _current_stream_id()
await self.bus.publish_outbound(OutboundMessage(
channel=msg.channel, chat_id=msg.chat_id,
content="",
metadata=meta,
))
stream_segment += 1
response = await self._process_message(
msg, on_stream=on_stream, on_stream_end=on_stream_end,
)
if response is not None:
await self.bus.publish_outbound(response)
elif msg.channel == "cli":
except asyncio.CancelledError:
logger.info("Task cancelled for session {}", session_key)
raise
except Exception:
logger.exception("Error processing message for session {}", session_key)
await self.bus.publish_outbound(OutboundMessage(
channel=msg.channel, chat_id=msg.chat_id,
content="", metadata=msg.metadata or {},
content="Sorry, I encountered an error.",
))
except asyncio.CancelledError:
logger.info("Task cancelled for session {}", msg.session_key)
raise
except Exception:
logger.exception("Error processing message for session {}", msg.session_key)
await self.bus.publish_outbound(OutboundMessage(
channel=msg.channel, chat_id=msg.chat_id,
content="Sorry, I encountered an error.",
))
finally:
# Drain any messages still in the pending queue and re-publish
# them to the bus so they are processed as fresh inbound messages
# rather than silently lost.
queue = self._pending_queues.pop(session_key, None)
if queue is not None:
leftover = 0
while True:
try:
item = queue.get_nowait()
except asyncio.QueueEmpty:
break
await self.bus.publish_inbound(item)
leftover += 1
if leftover:
logger.info(
"Re-published {} leftover message(s) to bus for session {}",
leftover, session_key,
)
async def close_mcp(self) -> None:
"""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:
for name, stack in self._mcp_stacks.items():
try:
await self._mcp_stack.aclose()
await stack.aclose()
except (RuntimeError, BaseExceptionGroup):
pass # MCP SDK cancel scope cleanup is noisy but harmless
self._mcp_stack = None
logger.debug("MCP server '{}' cleanup error (can be ignored)", name)
self._mcp_stacks.clear()
def _schedule_background(self, coro) -> None:
"""Schedule a coroutine as a tracked background task (drained on shutdown)."""
@@ -486,27 +605,34 @@ class AgentLoop:
on_progress: Callable[[str], Awaitable[None]] | None = None,
on_stream: Callable[[str], Awaitable[None]] | None = None,
on_stream_end: Callable[..., Awaitable[None]] | None = None,
pending_queue: asyncio.Queue | None = None,
) -> OutboundMessage | None:
"""Process a single inbound message and return the response."""
# System messages: parse origin from chat_id ("channel:chat_id")
if msg.channel == "system":
channel, chat_id = (msg.chat_id.split(":", 1) if ":" in msg.chat_id
else ("cli", msg.chat_id))
channel, chat_id = (
msg.chat_id.split(":", 1) if ":" in msg.chat_id else ("cli", msg.chat_id)
)
logger.info("Processing system message from {}", msg.sender_id)
key = f"{channel}:{chat_id}"
session = self.sessions.get_or_create(key)
if self._restore_runtime_checkpoint(session):
self.sessions.save(session)
session, pending = self.auto_compact.prepare_session(session, key)
await self.consolidator.maybe_consolidate_by_tokens(session)
self._set_tool_context(channel, chat_id, msg.metadata.get("message_id"))
history = session.get_history(max_messages=0)
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,
session_summary=pending,
current_role=current_role,
)
final_content, _, all_msgs = await self._run_agent_loop(
final_content, _, all_msgs, _, _ = await self._run_agent_loop(
messages, session=session, channel=channel, chat_id=chat_id,
message_id=msg.metadata.get("message_id"),
)
@@ -514,8 +640,11 @@ class AgentLoop:
self._clear_runtime_checkpoint(session)
self.sessions.save(session)
self._schedule_background(self.consolidator.maybe_consolidate_by_tokens(session))
return OutboundMessage(channel=channel, chat_id=chat_id,
content=final_content or "Background task completed.")
return OutboundMessage(
channel=channel,
chat_id=chat_id,
content=final_content or "Background task completed.",
)
preview = msg.content[:80] + "..." if len(msg.content) > 80 else msg.content
logger.info("Processing message from {}:{}: {}", msg.channel, msg.sender_id, preview)
@@ -525,6 +654,8 @@ class AgentLoop:
if self._restore_runtime_checkpoint(session):
self.sessions.save(session)
session, pending = self.auto_compact.prepare_session(session, key)
# Slash commands
raw = msg.content.strip()
ctx = CommandContext(msg=msg, session=session, key=key, raw=raw, loop=self)
@@ -539,29 +670,39 @@ class AgentLoop:
message_tool.start_turn()
history = session.get_history(max_messages=0)
initial_messages = self.context.build_messages(
history=history,
current_message=msg.content,
session_summary=pending,
media=msg.media if msg.media else None,
channel=msg.channel, chat_id=msg.chat_id,
channel=msg.channel,
chat_id=msg.chat_id,
)
async def _bus_progress(content: str, *, tool_hint: bool = False) -> None:
meta = dict(msg.metadata or {})
meta["_progress"] = True
meta["_tool_hint"] = tool_hint
await self.bus.publish_outbound(OutboundMessage(
channel=msg.channel, chat_id=msg.chat_id, content=content, metadata=meta,
))
await self.bus.publish_outbound(
OutboundMessage(
channel=msg.channel,
chat_id=msg.chat_id,
content=content,
metadata=meta,
)
)
final_content, _, all_msgs = await self._run_agent_loop(
final_content, _, all_msgs, stop_reason, had_injections = await self._run_agent_loop(
initial_messages,
on_progress=on_progress or _bus_progress,
on_stream=on_stream,
on_stream_end=on_stream_end,
session=session,
channel=msg.channel, chat_id=msg.chat_id,
channel=msg.channel,
chat_id=msg.chat_id,
message_id=msg.metadata.get("message_id"),
pending_queue=pending_queue,
)
if final_content is None or not final_content.strip():
@@ -572,17 +713,26 @@ class AgentLoop:
self.sessions.save(session)
self._schedule_background(self.consolidator.maybe_consolidate_by_tokens(session))
# When follow-up messages were injected mid-turn, a later natural
# language reply may address those follow-ups and should not be
# suppressed just because MessageTool was used earlier in the turn.
# However, if the turn falls back to the empty-final-response
# placeholder, suppress it when the real user-visible output already
# came from MessageTool.
if (mt := self.tools.get("message")) and isinstance(mt, MessageTool) and mt._sent_in_turn:
return None
if not had_injections or stop_reason == "empty_final_response":
return None
preview = final_content[:120] + "..." if len(final_content) > 120 else final_content
logger.info("Response to {}:{}: {}", msg.channel, msg.sender_id, preview)
meta = dict(msg.metadata or {})
if on_stream is not None:
if on_stream is not None and stop_reason != "error":
meta["_streamed"] = True
return OutboundMessage(
channel=msg.channel, chat_id=msg.chat_id, content=final_content,
channel=msg.channel,
chat_id=msg.chat_id,
content=final_content,
metadata=meta,
)
@@ -590,7 +740,7 @@ class AgentLoop:
self,
content: list[dict[str, Any]],
*,
truncate_text: bool = False,
should_truncate_text: bool = False,
drop_runtime: bool = False,
) -> list[dict[str, Any]]:
"""Strip volatile multimodal payloads before writing session history."""
@@ -608,18 +758,17 @@ class AgentLoop:
):
continue
if (
block.get("type") == "image_url"
and block.get("image_url", {}).get("url", "").startswith("data:image/")
):
if block.get("type") == "image_url" and block.get("image_url", {}).get(
"url", ""
).startswith("data:image/"):
path = (block.get("_meta") or {}).get("path", "")
filtered.append({"type": "text", "text": image_placeholder_text(path)})
continue
if block.get("type") == "text" and isinstance(block.get("text"), str):
text = block["text"]
if truncate_text and len(text) > self.max_tool_result_chars:
text = truncate_text(text, self.max_tool_result_chars)
if should_truncate_text and len(text) > self.max_tool_result_chars:
text = truncate_text_fn(text, self.max_tool_result_chars)
filtered.append({**block, "text": text})
continue
@@ -630,6 +779,7 @@ class AgentLoop:
def _save_turn(self, session: Session, messages: list[dict], skip: int) -> None:
"""Save new-turn messages into session, truncating large tool results."""
from datetime import datetime
for m in messages[skip:]:
entry = dict(m)
role, content = entry.get("role"), entry.get("content")
@@ -637,20 +787,31 @@ class AgentLoop:
continue # skip empty assistant messages — they poison session context
if role == "tool":
if isinstance(content, str) and len(content) > self.max_tool_result_chars:
entry["content"] = truncate_text(content, self.max_tool_result_chars)
entry["content"] = truncate_text_fn(content, self.max_tool_result_chars)
elif isinstance(content, list):
filtered = self._sanitize_persisted_blocks(content, truncate_text=True)
filtered = self._sanitize_persisted_blocks(content, should_truncate_text=True)
if not filtered:
continue
entry["content"] = filtered
elif role == "user":
if isinstance(content, str) and content.startswith(ContextBuilder._RUNTIME_CONTEXT_TAG):
# Strip the runtime-context prefix, keep only the user text.
parts = content.split("\n\n", 1)
if len(parts) > 1 and parts[1].strip():
entry["content"] = parts[1]
# Strip the entire runtime-context block (including any session summary).
# The block is bounded by _RUNTIME_CONTEXT_TAG and _RUNTIME_CONTEXT_END.
end_marker = ContextBuilder._RUNTIME_CONTEXT_END
end_pos = content.find(end_marker)
if end_pos >= 0:
after = content[end_pos + len(end_marker):].lstrip("\n")
if after:
entry["content"] = after
else:
continue
else:
continue
# Fallback: no end marker found, strip the tag prefix
after_tag = content[len(ContextBuilder._RUNTIME_CONTEXT_TAG):].lstrip("\n")
if after_tag.strip():
entry["content"] = after_tag
else:
continue
if isinstance(content, list):
filtered = self._sanitize_persisted_blocks(content, drop_runtime=True)
if not filtered:
@@ -708,13 +869,15 @@ class AgentLoop:
continue
tool_id = tool_call.get("id")
name = ((tool_call.get("function") or {}).get("name")) or "tool"
restored_messages.append({
"role": "tool",
"tool_call_id": tool_id,
"name": name,
"content": "Error: Task interrupted before this tool finished.",
"timestamp": datetime.now().isoformat(),
})
restored_messages.append(
{
"role": "tool",
"tool_call_id": tool_id,
"name": name,
"content": "Error: Task interrupted before this tool finished.",
"timestamp": datetime.now().isoformat(),
}
)
overlap = 0
max_overlap = min(len(session.messages), len(restored_messages))
@@ -746,6 +909,9 @@ class AgentLoop:
await self._connect_mcp()
msg = InboundMessage(channel=channel, sender_id="user", chat_id=chat_id, content=content)
return await self._process_message(
msg, session_key=session_key, on_progress=on_progress,
on_stream=on_stream, on_stream_end=on_stream_end,
msg,
session_key=session_key,
on_progress=on_progress,
on_stream=on_stream,
on_stream_end=on_stream_end,
)
nanobot/agent/memory.py
+45 -9
View File
@@ -290,7 +290,7 @@ class MemoryStore:
if not lines:
return None
return json.loads(lines[-1])
except (FileNotFoundError, json.JSONDecodeError):
except (FileNotFoundError, json.JSONDecodeError, UnicodeDecodeError):
return None
def _write_entries(self, entries: list[dict[str, Any]]) -> None:
@@ -347,6 +347,7 @@ class Consolidator:
"""Lightweight consolidation: summarizes evicted messages into history.jsonl."""
_MAX_CONSOLIDATION_ROUNDS = 5
_MAX_CHUNK_MESSAGES = 60 # hard cap per consolidation round
_SAFETY_BUFFER = 1024 # extra headroom for tokenizer estimation drift
@@ -399,6 +400,22 @@ class Consolidator:
return last_boundary
def _cap_consolidation_boundary(
self,
session: Session,
end_idx: int,
) -> int | None:
"""Clamp the chunk size without breaking the user-turn boundary."""
start = session.last_consolidated
if end_idx - start <= self._MAX_CHUNK_MESSAGES:
return end_idx
capped_end = start + self._MAX_CHUNK_MESSAGES
for idx in range(capped_end, start, -1):
if session.messages[idx].get("role") == "user":
return idx
return None
def estimate_session_prompt_tokens(self, session: Session) -> tuple[int, str]:
"""Estimate current prompt size for the normal session history view."""
history = session.get_history(max_messages=0)
@@ -416,13 +433,13 @@ class Consolidator:
self._get_tool_definitions(),
)
async def archive(self, messages: list[dict]) -> bool:
async def archive(self, messages: list[dict]) -> str | None:
"""Summarize messages via LLM and append to history.jsonl.
Returns True on success (or degraded success), False if nothing to do.
Returns the summary text on success, None if nothing to archive.
"""
if not messages:
return False
return None
try:
formatted = MemoryStore._format_messages(messages)
response = await self.provider.chat_with_retry(
@@ -442,11 +459,11 @@ class Consolidator:
)
summary = response.content or "[no summary]"
self.store.append_history(summary)
return True
return summary
except Exception:
logger.warning("Consolidation LLM call failed, raw-dumping to history")
self.store.raw_archive(messages)
return True
return None
async def maybe_consolidate_by_tokens(self, session: Session) -> None:
"""Loop: archive old messages until prompt fits within safe budget.
@@ -461,16 +478,22 @@ class Consolidator:
async with lock:
budget = self.context_window_tokens - self.max_completion_tokens - self._SAFETY_BUFFER
target = budget // 2
estimated, source = self.estimate_session_prompt_tokens(session)
try:
estimated, source = self.estimate_session_prompt_tokens(session)
except Exception:
logger.exception("Token estimation failed for {}", session.key)
estimated, source = 0, "error"
if estimated <= 0:
return
if estimated < budget:
unconsolidated_count = len(session.messages) - session.last_consolidated
logger.debug(
"Token consolidation idle {}: {}/{} via {}",
"Token consolidation idle {}: {}/{} via {}, msgs={}",
session.key,
estimated,
self.context_window_tokens,
source,
unconsolidated_count,
)
return
@@ -488,6 +511,15 @@ class Consolidator:
return
end_idx = boundary[0]
end_idx = self._cap_consolidation_boundary(session, end_idx)
if end_idx is None:
logger.debug(
"Token consolidation: no capped boundary for {} (round {})",
session.key,
round_num,
)
return
chunk = session.messages[session.last_consolidated:end_idx]
if not chunk:
return
@@ -506,7 +538,11 @@ class Consolidator:
session.last_consolidated = end_idx
self.sessions.save(session)
estimated, source = self.estimate_session_prompt_tokens(session)
try:
estimated, source = self.estimate_session_prompt_tokens(session)
except Exception:
logger.exception("Token estimation failed for {}", session.key)
estimated, source = 0, "error"
if estimated <= 0:
return
nanobot/agent/runner.py
+211 -19
View File
@@ -4,6 +4,7 @@ from __future__ import annotations
import asyncio
from dataclasses import dataclass, field
import inspect
from pathlib import Path
from typing import Any
@@ -31,8 +32,11 @@ from nanobot.utils.runtime import (
)
_DEFAULT_ERROR_MESSAGE = "Sorry, I encountered an error calling the AI model."
_PERSISTED_MODEL_ERROR_PLACEHOLDER = "[Assistant reply unavailable due to model error.]"
_MAX_EMPTY_RETRIES = 2
_MAX_LENGTH_RECOVERIES = 3
_MAX_INJECTIONS_PER_TURN = 3
_MAX_INJECTION_CYCLES = 5
_SNIP_SAFETY_BUFFER = 1024
_MICROCOMPACT_KEEP_RECENT = 10
_MICROCOMPACT_MIN_CHARS = 500
@@ -41,6 +45,9 @@ _COMPACTABLE_TOOLS = frozenset({
"web_search", "web_fetch", "list_dir",
})
_BACKFILL_CONTENT = "[Tool result unavailable — call was interrupted or lost]"
@dataclass(slots=True)
class AgentRunSpec:
"""Configuration for a single agent execution."""
@@ -65,6 +72,7 @@ class AgentRunSpec:
provider_retry_mode: str = "standard"
progress_callback: Any | None = None
checkpoint_callback: Any | None = None
injection_callback: Any | None = None
@dataclass(slots=True)
@@ -78,6 +86,7 @@ class AgentRunResult:
stop_reason: str = "completed"
error: str | None = None
tool_events: list[dict[str, str]] = field(default_factory=list)
had_injections: bool = False
class AgentRunner:
@@ -86,6 +95,90 @@ class AgentRunner:
def __init__(self, provider: LLMProvider):
self.provider = provider
@staticmethod
def _merge_message_content(left: Any, right: Any) -> str | list[dict[str, Any]]:
if isinstance(left, str) and isinstance(right, str):
return f"{left}\n\n{right}" if left else right
def _to_blocks(value: Any) -> list[dict[str, Any]]:
if isinstance(value, list):
return [
item if isinstance(item, dict) else {"type": "text", "text": str(item)}
for item in value
]
if value is None:
return []
return [{"type": "text", "text": str(value)}]
return _to_blocks(left) + _to_blocks(right)
@classmethod
def _append_injected_messages(
cls,
messages: list[dict[str, Any]],
injections: list[dict[str, Any]],
) -> None:
"""Append injected user messages while preserving role alternation."""
for injection in injections:
if (
messages
and injection.get("role") == "user"
and messages[-1].get("role") == "user"
):
merged = dict(messages[-1])
merged["content"] = cls._merge_message_content(
merged.get("content"),
injection.get("content"),
)
messages[-1] = merged
continue
messages.append(injection)
async def _drain_injections(self, spec: AgentRunSpec) -> list[dict[str, Any]]:
"""Drain pending user messages via the injection callback.
Returns normalized user messages (capped by
``_MAX_INJECTIONS_PER_TURN``), or an empty list when there is
nothing to inject. Messages beyond the cap are logged so they
are not silently lost.
"""
if spec.injection_callback is None:
return []
try:
signature = inspect.signature(spec.injection_callback)
accepts_limit = (
"limit" in signature.parameters
or any(
parameter.kind is inspect.Parameter.VAR_KEYWORD
for parameter in signature.parameters.values()
)
)
if accepts_limit:
items = await spec.injection_callback(limit=_MAX_INJECTIONS_PER_TURN)
else:
items = await spec.injection_callback()
except Exception:
logger.exception("injection_callback failed")
return []
if not items:
return []
injected_messages: list[dict[str, Any]] = []
for item in items:
if isinstance(item, dict) and item.get("role") == "user" and "content" in item:
injected_messages.append(item)
continue
text = getattr(item, "content", str(item))
if text.strip():
injected_messages.append({"role": "user", "content": text})
if len(injected_messages) > _MAX_INJECTIONS_PER_TURN:
dropped = len(injected_messages) - _MAX_INJECTIONS_PER_TURN
logger.warning(
"Injection callback returned {} messages, capping to {} ({} dropped)",
len(injected_messages), _MAX_INJECTIONS_PER_TURN, dropped,
)
injected_messages = injected_messages[:_MAX_INJECTIONS_PER_TURN]
return injected_messages
async def run(self, spec: AgentRunSpec) -> AgentRunResult:
hook = spec.hook or AgentHook()
messages = list(spec.initial_messages)
@@ -98,21 +191,35 @@ class AgentRunner:
external_lookup_counts: dict[str, int] = {}
empty_content_retries = 0
length_recovery_count = 0
had_injections = False
injection_cycles = 0
for iteration in range(spec.max_iterations):
try:
messages = self._backfill_missing_tool_results(messages)
messages = self._microcompact(messages)
messages = self._apply_tool_result_budget(spec, messages)
messages_for_model = self._snip_history(spec, messages)
# Keep the persisted conversation untouched. Context governance
# may repair or compact historical messages for the model, but
# those synthetic edits must not shift the append boundary used
# later when the caller saves only the new turn.
messages_for_model = self._drop_orphan_tool_results(messages)
messages_for_model = self._backfill_missing_tool_results(messages_for_model)
messages_for_model = self._microcompact(messages_for_model)
messages_for_model = self._apply_tool_result_budget(spec, messages_for_model)
messages_for_model = self._snip_history(spec, messages_for_model)
# Snipping may have created new orphans; clean them up.
messages_for_model = self._drop_orphan_tool_results(messages_for_model)
messages_for_model = self._backfill_missing_tool_results(messages_for_model)
except Exception as exc:
logger.warning(
"Context governance failed on turn {} for {}: {}; using raw messages",
"Context governance failed on turn {} for {}: {}; applying minimal repair",
iteration,
spec.session_key or "default",
exc,
)
messages_for_model = messages
try:
messages_for_model = self._drop_orphan_tool_results(messages)
messages_for_model = self._backfill_missing_tool_results(messages_for_model)
except Exception:
messages_for_model = messages
context = AgentHookContext(iteration=iteration, messages=messages)
await hook.before_iteration(context)
response = await self._request_model(spec, messages_for_model, hook, context)
@@ -156,16 +263,6 @@ class AgentRunner:
tool_events.extend(new_events)
context.tool_results = list(results)
context.tool_events = list(new_events)
if fatal_error is not None:
error = f"Error: {type(fatal_error).__name__}: {fatal_error}"
final_content = error
stop_reason = "tool_error"
self._append_final_message(messages, final_content)
context.final_content = final_content
context.error = error
context.stop_reason = stop_reason
await hook.after_iteration(context)
break
completed_tool_results: list[dict[str, Any]] = []
for tool_call, result in zip(response.tool_calls, results):
tool_message = {
@@ -181,6 +278,16 @@ class AgentRunner:
}
messages.append(tool_message)
completed_tool_results.append(tool_message)
if fatal_error is not None:
error = f"Error: {type(fatal_error).__name__}: {fatal_error}"
final_content = error
stop_reason = "tool_error"
self._append_final_message(messages, final_content)
context.final_content = final_content
context.error = error
context.stop_reason = stop_reason
await hook.after_iteration(context)
break
await self._emit_checkpoint(
spec,
{
@@ -194,6 +301,17 @@ class AgentRunner:
)
empty_content_retries = 0
length_recovery_count = 0
# Checkpoint 1: drain injections after tools, before next LLM call
if injection_cycles < _MAX_INJECTION_CYCLES:
injections = await self._drain_injections(spec)
if injections:
had_injections = True
injection_cycles += 1
self._append_injected_messages(messages, injections)
logger.info(
"Injected {} follow-up message(s) after tool execution ({}/{})",
len(injections), injection_cycles, _MAX_INJECTION_CYCLES,
)
await hook.after_iteration(context)
continue
@@ -250,14 +368,55 @@ class AgentRunner:
await hook.after_iteration(context)
continue
assistant_message: dict[str, Any] | None = None
if response.finish_reason != "error" and not is_blank_text(clean):
assistant_message = build_assistant_message(
clean,
reasoning_content=response.reasoning_content,
thinking_blocks=response.thinking_blocks,
)
# Check for mid-turn injections BEFORE signaling stream end.
# If injections are found we keep the stream alive (resuming=True)
# so streaming channels don't prematurely finalize the card.
_injected_after_final = False
if injection_cycles < _MAX_INJECTION_CYCLES:
injections = await self._drain_injections(spec)
if injections:
had_injections = True
injection_cycles += 1
_injected_after_final = True
if assistant_message is not None:
messages.append(assistant_message)
await self._emit_checkpoint(
spec,
{
"phase": "final_response",
"iteration": iteration,
"model": spec.model,
"assistant_message": assistant_message,
"completed_tool_results": [],
"pending_tool_calls": [],
},
)
self._append_injected_messages(messages, injections)
logger.info(
"Injected {} follow-up message(s) after final response ({}/{})",
len(injections), injection_cycles, _MAX_INJECTION_CYCLES,
)
if hook.wants_streaming():
await hook.on_stream_end(context, resuming=False)
await hook.on_stream_end(context, resuming=_injected_after_final)
if _injected_after_final:
await hook.after_iteration(context)
continue
if response.finish_reason == "error":
final_content = clean or spec.error_message or _DEFAULT_ERROR_MESSAGE
stop_reason = "error"
error = final_content
self._append_final_message(messages, final_content)
self._append_model_error_placeholder(messages)
context.final_content = final_content
context.error = error
context.stop_reason = stop_reason
@@ -274,7 +433,7 @@ class AgentRunner:
await hook.after_iteration(context)
break
messages.append(build_assistant_message(
messages.append(assistant_message or build_assistant_message(
clean,
reasoning_content=response.reasoning_content,
thinking_blocks=response.thinking_blocks,
@@ -317,6 +476,7 @@ class AgentRunner:
stop_reason=stop_reason,
error=error,
tool_events=tool_events,
had_injections=had_injections,
)
def _build_request_kwargs(
@@ -521,6 +681,12 @@ class AgentRunner:
return
messages.append(build_assistant_message(content))
@staticmethod
def _append_model_error_placeholder(messages: list[dict[str, Any]]) -> None:
if messages and messages[-1].get("role") == "assistant" and not messages[-1].get("tool_calls"):
return
messages.append(build_assistant_message(_PERSISTED_MODEL_ERROR_PLACEHOLDER))
def _normalize_tool_result(
self,
spec: AgentRunSpec,
@@ -549,6 +715,32 @@ class AgentRunner:
return truncate_text(content, spec.max_tool_result_chars)
return content
@staticmethod
def _drop_orphan_tool_results(
messages: list[dict[str, Any]],
) -> list[dict[str, Any]]:
"""Drop tool results that have no matching assistant tool_call earlier in the history."""
declared: set[str] = set()
updated: list[dict[str, Any]] | None = None
for idx, msg in enumerate(messages):
role = msg.get("role")
if role == "assistant":
for tc in msg.get("tool_calls") or []:
if isinstance(tc, dict) and tc.get("id"):
declared.add(str(tc["id"]))
if role == "tool":
tid = msg.get("tool_call_id")
if tid and str(tid) not in declared:
if updated is None:
updated = [dict(m) for m in messages[:idx]]
continue
if updated is not None:
updated.append(dict(msg))
if updated is None:
return messages
return updated
@staticmethod
def _backfill_missing_tool_results(
messages: list[dict[str, Any]],
nanobot/agent/subagent.py
+6 -1
View File
@@ -52,6 +52,7 @@ class SubagentManager:
web_config: "WebToolsConfig | None" = None,
exec_config: "ExecToolConfig | None" = None,
restrict_to_workspace: bool = False,
disabled_skills: list[str] | None = None,
):
from nanobot.config.schema import ExecToolConfig
@@ -63,6 +64,7 @@ class SubagentManager:
self.max_tool_result_chars = max_tool_result_chars
self.exec_config = exec_config or ExecToolConfig()
self.restrict_to_workspace = restrict_to_workspace
self.disabled_skills = set(disabled_skills or [])
self.runner = AgentRunner(provider)
self._running_tasks: dict[str, asyncio.Task[None]] = {}
self._session_tasks: dict[str, set[str]] = {} # session_key -> {task_id, ...}
@@ -236,7 +238,10 @@ class SubagentManager:
from nanobot.agent.skills import SkillsLoader
time_ctx = ContextBuilder._build_runtime_context(None, None)
skills_summary = SkillsLoader(self.workspace).build_skills_summary()
skills_summary = SkillsLoader(
self.workspace,
disabled_skills=self.disabled_skills,
).build_skills_summary()
return render_template(
"agent/subagent_system.md",
time_ctx=time_ctx,
nanobot/agent/tools/file_state.py
+105
View File
@@ -0,0 +1,105 @@
"""Track file-read state for read-before-edit warnings and read deduplication."""
from __future__ import annotations
import hashlib
import os
from dataclasses import dataclass
from pathlib import Path
@dataclass(slots=True)
class ReadState:
mtime: float
offset: int
limit: int | None
content_hash: str | None
can_dedup: bool
_state: dict[str, ReadState] = {}
def _hash_file(p: str) -> str | None:
try:
return hashlib.sha256(Path(p).read_bytes()).hexdigest()
except OSError:
return None
def record_read(path: str | Path, offset: int = 1, limit: int | None = None) -> None:
"""Record that a file was read (called after successful read)."""
p = str(Path(path).resolve())
try:
mtime = os.path.getmtime(p)
except OSError:
return
_state[p] = ReadState(
mtime=mtime,
offset=offset,
limit=limit,
content_hash=_hash_file(p),
can_dedup=True,
)
def record_write(path: str | Path) -> None:
"""Record that a file was written (updates mtime in state)."""
p = str(Path(path).resolve())
try:
mtime = os.path.getmtime(p)
except OSError:
_state.pop(p, None)
return
_state[p] = ReadState(
mtime=mtime,
offset=1,
limit=None,
content_hash=_hash_file(p),
can_dedup=False,
)
def check_read(path: str | Path) -> str | None:
"""Check if a file has been read and is fresh.
Returns None if OK, or a warning string.
When mtime changed but file content is identical (e.g. touch, editor save),
the check passes to avoid false-positive staleness warnings.
"""
p = str(Path(path).resolve())
entry = _state.get(p)
if entry is None:
return "Warning: file has not been read yet. Read it first to verify content before editing."
try:
current_mtime = os.path.getmtime(p)
except OSError:
return None
if current_mtime != entry.mtime:
if entry.content_hash and _hash_file(p) == entry.content_hash:
entry.mtime = current_mtime
return None
return "Warning: file has been modified since last read. Re-read to verify content before editing."
return None
def is_unchanged(path: str | Path, offset: int = 1, limit: int | None = None) -> bool:
"""Return True if file was previously read with same params and mtime is unchanged."""
p = str(Path(path).resolve())
entry = _state.get(p)
if entry is None:
return False
if not entry.can_dedup:
return False
if entry.offset != offset or entry.limit != limit:
return False
try:
current_mtime = os.path.getmtime(p)
except OSError:
return False
return current_mtime == entry.mtime
def clear() -> None:
"""Clear all tracked state (useful for testing)."""
_state.clear()
nanobot/agent/tools/filesystem.py
+463 -40
View File
@@ -2,11 +2,13 @@
import difflib
import mimetypes
from dataclasses import dataclass
from pathlib import Path
from typing import Any
from nanobot.agent.tools.base import Tool, tool_parameters
from nanobot.agent.tools.schema import BooleanSchema, IntegerSchema, StringSchema, tool_parameters_schema
from nanobot.agent.tools import file_state
from nanobot.utils.helpers import build_image_content_blocks, detect_image_mime
from nanobot.config.paths import get_media_dir
@@ -60,6 +62,36 @@ class _FsTool(Tool):
# ---------------------------------------------------------------------------
_BLOCKED_DEVICE_PATHS = frozenset({
"/dev/zero", "/dev/random", "/dev/urandom", "/dev/full",
"/dev/stdin", "/dev/stdout", "/dev/stderr",
"/dev/tty", "/dev/console",
"/dev/fd/0", "/dev/fd/1", "/dev/fd/2",
})
def _is_blocked_device(path: str | Path) -> bool:
"""Check if path is a blocked device that could hang or produce infinite output."""
import re
raw = str(path)
if raw in _BLOCKED_DEVICE_PATHS:
return True
if re.match(r"/proc/\d+/fd/[012]$", raw) or re.match(r"/proc/self/fd/[012]$", raw):
return True
return False
def _parse_page_range(pages: str, total: int) -> tuple[int, int]:
"""Parse a page range like '2-5' into 0-based (start, end) inclusive."""
parts = pages.strip().split("-")
if len(parts) == 1:
p = int(parts[0])
return max(0, p - 1), min(p - 1, total - 1)
start = int(parts[0])
end = int(parts[1])
return max(0, start - 1), min(end - 1, total - 1)
@tool_parameters(
tool_parameters_schema(
path=StringSchema("The file path to read"),
@@ -73,6 +105,7 @@ class _FsTool(Tool):
description="Maximum number of lines to read (default 2000)",
minimum=1,
),
pages=StringSchema("Page range for PDF files, e.g. '1-5' (default: all, max 20 pages)"),
required=["path"],
)
)
@@ -81,6 +114,7 @@ class ReadFileTool(_FsTool):
_MAX_CHARS = 128_000
_DEFAULT_LIMIT = 2000
_MAX_PDF_PAGES = 20
@property
def name(self) -> str:
@@ -89,9 +123,10 @@ class ReadFileTool(_FsTool):
@property
def description(self) -> str:
return (
"Read a text file. Output format: LINE_NUM|CONTENT. "
"Read a file (text or image). Text output format: LINE_NUM|CONTENT. "
"Images return visual content for analysis. "
"Use offset and limit for large files. "
"Cannot read binary files or images. "
"Cannot read non-image binary files. "
"Reads exceeding ~128K chars are truncated."
)
@@ -99,16 +134,27 @@ class ReadFileTool(_FsTool):
def read_only(self) -> bool:
return True
async def execute(self, path: str | None = None, offset: int = 1, limit: int | None = None, **kwargs: Any) -> Any:
async def execute(self, path: str | None = None, offset: int = 1, limit: int | None = None, pages: str | None = None, **kwargs: Any) -> Any:
try:
if not path:
return "Error reading file: Unknown path"
# Device path blacklist
if _is_blocked_device(path):
return f"Error: Reading {path} is blocked (device path that could hang or produce infinite output)."
fp = self._resolve(path)
if _is_blocked_device(fp):
return f"Error: Reading {fp} is blocked (device path that could hang or produce infinite output)."
if not fp.exists():
return f"Error: File not found: {path}"
if not fp.is_file():
return f"Error: Not a file: {path}"
# PDF support
if fp.suffix.lower() == ".pdf":
return self._read_pdf(fp, pages)
raw = fp.read_bytes()
if not raw:
return f"(Empty file: {path})"
@@ -117,6 +163,10 @@ class ReadFileTool(_FsTool):
if mime and mime.startswith("image/"):
return build_image_content_blocks(raw, mime, str(fp), f"(Image file: {path})")
# Read dedup: same path + offset + limit + unchanged mtime → stub
if file_state.is_unchanged(fp, offset=offset, limit=limit):
return f"[File unchanged since last read: {path}]"
try:
text_content = raw.decode("utf-8")
except UnicodeDecodeError:
@@ -149,12 +199,59 @@ class ReadFileTool(_FsTool):
result += f"\n\n(Showing lines {offset}-{end} of {total}. Use offset={end + 1} to continue.)"
else:
result += f"\n\n(End of file — {total} lines total)"
file_state.record_read(fp, offset=offset, limit=limit)
return result
except PermissionError as e:
return f"Error: {e}"
except Exception as e:
return f"Error reading file: {e}"
def _read_pdf(self, fp: Path, pages: str | None) -> str:
try:
import fitz # pymupdf
except ImportError:
return "Error: PDF reading requires pymupdf. Install with: pip install pymupdf"
try:
doc = fitz.open(str(fp))
except Exception as e:
return f"Error reading PDF: {e}"
total_pages = len(doc)
if pages:
try:
start, end = _parse_page_range(pages, total_pages)
except (ValueError, IndexError):
doc.close()
return f"Error: Invalid page range '{pages}'. Use format like '1-5'."
if start > end or start >= total_pages:
doc.close()
return f"Error: Page range '{pages}' is out of bounds (document has {total_pages} pages)."
else:
start = 0
end = min(total_pages - 1, self._MAX_PDF_PAGES - 1)
if end - start + 1 > self._MAX_PDF_PAGES:
end = start + self._MAX_PDF_PAGES - 1
parts: list[str] = []
for i in range(start, end + 1):
page = doc[i]
text = page.get_text().strip()
if text:
parts.append(f"--- Page {i + 1} ---\n{text}")
doc.close()
if not parts:
return f"(PDF has no extractable text: {fp})"
result = "\n\n".join(parts)
if end < total_pages - 1:
result += f"\n\n(Showing pages {start + 1}-{end + 1} of {total_pages}. Use pages='{end + 2}-{min(end + 1 + self._MAX_PDF_PAGES, total_pages)}' to continue.)"
if len(result) > self._MAX_CHARS:
result = result[:self._MAX_CHARS] + "\n\n(PDF text truncated at ~128K chars)"
return result
# ---------------------------------------------------------------------------
# write_file
@@ -192,6 +289,7 @@ class WriteFileTool(_FsTool):
fp = self._resolve(path)
fp.parent.mkdir(parents=True, exist_ok=True)
fp.write_text(content, encoding="utf-8")
file_state.record_write(fp)
return f"Successfully wrote {len(content)} characters to {fp}"
except PermissionError as e:
return f"Error: {e}"
@@ -203,30 +301,269 @@ class WriteFileTool(_FsTool):
# edit_file
# ---------------------------------------------------------------------------
_QUOTE_TABLE = str.maketrans({
"\u2018": "'", "\u2019": "'", # curly single → straight
"\u201c": '"', "\u201d": '"', # curly double → straight
"'": "'", '"': '"', # identity (kept for completeness)
})
def _normalize_quotes(s: str) -> str:
return s.translate(_QUOTE_TABLE)
def _curly_double_quotes(text: str) -> str:
parts: list[str] = []
opening = True
for ch in text:
if ch == '"':
parts.append("\u201c" if opening else "\u201d")
opening = not opening
else:
parts.append(ch)
return "".join(parts)
def _curly_single_quotes(text: str) -> str:
parts: list[str] = []
opening = True
for i, ch in enumerate(text):
if ch != "'":
parts.append(ch)
continue
prev_ch = text[i - 1] if i > 0 else ""
next_ch = text[i + 1] if i + 1 < len(text) else ""
if prev_ch.isalnum() and next_ch.isalnum():
parts.append("\u2019")
continue
parts.append("\u2018" if opening else "\u2019")
opening = not opening
return "".join(parts)
def _preserve_quote_style(old_text: str, actual_text: str, new_text: str) -> str:
"""Preserve curly quote style when a quote-normalized fallback matched."""
if _normalize_quotes(old_text.strip()) != _normalize_quotes(actual_text.strip()) or old_text == actual_text:
return new_text
styled = new_text
if any(ch in actual_text for ch in ("\u201c", "\u201d")) and '"' in styled:
styled = _curly_double_quotes(styled)
if any(ch in actual_text for ch in ("\u2018", "\u2019")) and "'" in styled:
styled = _curly_single_quotes(styled)
return styled
def _leading_ws(line: str) -> str:
return line[: len(line) - len(line.lstrip(" \t"))]
def _reindent_like_match(old_text: str, actual_text: str, new_text: str) -> str:
"""Preserve the outer indentation from the actual matched block."""
old_lines = old_text.split("\n")
actual_lines = actual_text.split("\n")
if len(old_lines) != len(actual_lines):
return new_text
comparable = [
(old_line, actual_line)
for old_line, actual_line in zip(old_lines, actual_lines)
if old_line.strip() and actual_line.strip()
]
if not comparable or any(
_normalize_quotes(old_line.strip()) != _normalize_quotes(actual_line.strip())
for old_line, actual_line in comparable
):
return new_text
old_ws = _leading_ws(comparable[0][0])
actual_ws = _leading_ws(comparable[0][1])
if actual_ws == old_ws:
return new_text
if old_ws:
if not actual_ws.startswith(old_ws):
return new_text
delta = actual_ws[len(old_ws):]
else:
delta = actual_ws
if not delta:
return new_text
return "\n".join((delta + line) if line else line for line in new_text.split("\n"))
@dataclass(slots=True)
class _MatchSpan:
start: int
end: int
text: str
line: int
def _find_exact_matches(content: str, old_text: str) -> list[_MatchSpan]:
matches: list[_MatchSpan] = []
start = 0
while True:
idx = content.find(old_text, start)
if idx == -1:
break
matches.append(
_MatchSpan(
start=idx,
end=idx + len(old_text),
text=content[idx : idx + len(old_text)],
line=content.count("\n", 0, idx) + 1,
)
)
start = idx + max(1, len(old_text))
return matches
def _find_trim_matches(content: str, old_text: str, *, normalize_quotes: bool = False) -> list[_MatchSpan]:
old_lines = old_text.splitlines()
if not old_lines:
return []
content_lines = content.splitlines()
content_lines_keepends = content.splitlines(keepends=True)
if len(content_lines) < len(old_lines):
return []
offsets: list[int] = []
pos = 0
for line in content_lines_keepends:
offsets.append(pos)
pos += len(line)
offsets.append(pos)
if normalize_quotes:
stripped_old = [_normalize_quotes(line.strip()) for line in old_lines]
else:
stripped_old = [line.strip() for line in old_lines]
matches: list[_MatchSpan] = []
window_size = len(stripped_old)
for i in range(len(content_lines) - window_size + 1):
window = content_lines[i : i + window_size]
if normalize_quotes:
comparable = [_normalize_quotes(line.strip()) for line in window]
else:
comparable = [line.strip() for line in window]
if comparable != stripped_old:
continue
start = offsets[i]
end = offsets[i + window_size]
if content_lines_keepends[i + window_size - 1].endswith("\n"):
end -= 1
matches.append(
_MatchSpan(
start=start,
end=end,
text=content[start:end],
line=i + 1,
)
)
return matches
def _find_quote_matches(content: str, old_text: str) -> list[_MatchSpan]:
norm_content = _normalize_quotes(content)
norm_old = _normalize_quotes(old_text)
matches: list[_MatchSpan] = []
start = 0
while True:
idx = norm_content.find(norm_old, start)
if idx == -1:
break
matches.append(
_MatchSpan(
start=idx,
end=idx + len(old_text),
text=content[idx : idx + len(old_text)],
line=content.count("\n", 0, idx) + 1,
)
)
start = idx + max(1, len(norm_old))
return matches
def _find_matches(content: str, old_text: str) -> list[_MatchSpan]:
"""Locate all matches using progressively looser strategies."""
for matcher in (
lambda: _find_exact_matches(content, old_text),
lambda: _find_trim_matches(content, old_text),
lambda: _find_trim_matches(content, old_text, normalize_quotes=True),
lambda: _find_quote_matches(content, old_text),
):
matches = matcher()
if matches:
return matches
return []
def _find_match_line_numbers(content: str, old_text: str) -> list[int]:
"""Return 1-based starting line numbers for the current matching strategies."""
return [match.line for match in _find_matches(content, old_text)]
def _collapse_internal_whitespace(text: str) -> str:
return "\n".join(" ".join(line.split()) for line in text.splitlines())
def _diagnose_near_match(old_text: str, actual_text: str) -> list[str]:
"""Return actionable hints describing why text was close but not exact."""
hints: list[str] = []
if old_text.lower() == actual_text.lower() and old_text != actual_text:
hints.append("letter case differs")
if _collapse_internal_whitespace(old_text) == _collapse_internal_whitespace(actual_text) and old_text != actual_text:
hints.append("whitespace differs")
if old_text.rstrip("\n") == actual_text.rstrip("\n") and old_text != actual_text:
hints.append("trailing newline differs")
if _normalize_quotes(old_text) == _normalize_quotes(actual_text) and old_text != actual_text:
hints.append("quote style differs")
return hints
def _best_window(old_text: str, content: str) -> tuple[float, int, list[str], list[str]]:
"""Find the closest line-window match and return ratio/start/snippet/hints."""
lines = content.splitlines(keepends=True)
old_lines = old_text.splitlines(keepends=True)
window = max(1, len(old_lines))
best_ratio, best_start = -1.0, 0
best_window_lines: list[str] = []
for i in range(max(1, len(lines) - window + 1)):
current = lines[i : i + window]
ratio = difflib.SequenceMatcher(None, old_lines, current).ratio()
if ratio > best_ratio:
best_ratio, best_start = ratio, i
best_window_lines = current
actual_text = "".join(best_window_lines).replace("\r\n", "\n").rstrip("\n")
hints = _diagnose_near_match(old_text.replace("\r\n", "\n").rstrip("\n"), actual_text)
return best_ratio, best_start, best_window_lines, hints
def _find_match(content: str, old_text: str) -> tuple[str | None, int]:
"""Locate old_text in content: exact first, then line-trimmed sliding window.
"""Locate old_text in content with a multi-level fallback chain:
1. Exact substring match
2. Line-trimmed sliding window (handles indentation differences)
3. Smart quote normalization (curly ↔ straight quotes)
Both inputs should use LF line endings (caller normalises CRLF).
Returns (matched_fragment, count) or (None, 0).
"""
if old_text in content:
return old_text, content.count(old_text)
old_lines = old_text.splitlines()
if not old_lines:
matches = _find_matches(content, old_text)
if not matches:
return None, 0
stripped_old = [l.strip() for l in old_lines]
content_lines = content.splitlines()
candidates = []
for i in range(len(content_lines) - len(stripped_old) + 1):
window = content_lines[i : i + len(stripped_old)]
if [l.strip() for l in window] == stripped_old:
candidates.append("\n".join(window))
if candidates:
return candidates[0], len(candidates)
return None, 0
return matches[0].text, len(matches)
@tool_parameters(
@@ -241,6 +578,9 @@ def _find_match(content: str, old_text: str) -> tuple[str | None, int]:
class EditFileTool(_FsTool):
"""Edit a file by replacing text with fallback matching."""
_MAX_EDIT_FILE_SIZE = 1024 * 1024 * 1024 # 1 GiB
_MARKDOWN_EXTS = frozenset({".md", ".mdx", ".markdown"})
@property
def name(self) -> str:
return "edit_file"
@@ -249,11 +589,16 @@ class EditFileTool(_FsTool):
def description(self) -> str:
return (
"Edit a file by replacing old_text with new_text. "
"Tolerates minor whitespace/indentation differences. "
"Tolerates minor whitespace/indentation differences and curly/straight quote mismatches. "
"If old_text matches multiple times, you must provide more context "
"or set replace_all=true. Shows a diff of the closest match on failure."
)
@staticmethod
def _strip_trailing_ws(text: str) -> str:
"""Strip trailing whitespace from each line."""
return "\n".join(line.rstrip() for line in text.split("\n"))
async def execute(
self, path: str | None = None, old_text: str | None = None,
new_text: str | None = None,
@@ -267,55 +612,133 @@ class EditFileTool(_FsTool):
if new_text is None:
raise ValueError("Unknown new_text")
# .ipynb detection
if path.endswith(".ipynb"):
return "Error: This is a Jupyter notebook. Use the notebook_edit tool instead of edit_file."
fp = self._resolve(path)
# Create-file semantics: old_text='' + file doesn't exist → create
if not fp.exists():
return f"Error: File not found: {path}"
if old_text == "":
fp.parent.mkdir(parents=True, exist_ok=True)
fp.write_text(new_text, encoding="utf-8")
file_state.record_write(fp)
return f"Successfully created {fp}"
return self._file_not_found_msg(path, fp)
# File size protection
try:
fsize = fp.stat().st_size
except OSError:
fsize = 0
if fsize > self._MAX_EDIT_FILE_SIZE:
return f"Error: File too large to edit ({fsize / (1024**3):.1f} GiB). Maximum is 1 GiB."
# Create-file: old_text='' but file exists and not empty → reject
if old_text == "":
raw = fp.read_bytes()
content = raw.decode("utf-8")
if content.strip():
return f"Error: Cannot create file — {path} already exists and is not empty."
fp.write_text(new_text, encoding="utf-8")
file_state.record_write(fp)
return f"Successfully edited {fp}"
# Read-before-edit check
warning = file_state.check_read(fp)
raw = fp.read_bytes()
uses_crlf = b"\r\n" in raw
content = raw.decode("utf-8").replace("\r\n", "\n")
match, count = _find_match(content, old_text.replace("\r\n", "\n"))
norm_old = old_text.replace("\r\n", "\n")
matches = _find_matches(content, norm_old)
if match is None:
if not matches:
return self._not_found_msg(old_text, content, path)
count = len(matches)
if count > 1 and not replace_all:
line_numbers = [match.line for match in matches]
preview = ", ".join(f"line {n}" for n in line_numbers[:3])
if len(line_numbers) > 3:
preview += ", ..."
location_hint = f" at {preview}" if preview else ""
return (
f"Warning: old_text appears {count} times. "
f"Warning: old_text appears {count} times{location_hint}. "
"Provide more context to make it unique, or set replace_all=true."
)
norm_new = new_text.replace("\r\n", "\n")
new_content = content.replace(match, norm_new) if replace_all else content.replace(match, norm_new, 1)
# Trailing whitespace stripping (skip markdown to preserve double-space line breaks)
if fp.suffix.lower() not in self._MARKDOWN_EXTS:
norm_new = self._strip_trailing_ws(norm_new)
selected = matches if replace_all else matches[:1]
new_content = content
for match in reversed(selected):
replacement = _preserve_quote_style(norm_old, match.text, norm_new)
replacement = _reindent_like_match(norm_old, match.text, replacement)
# Delete-line cleanup: when deleting text (new_text=''), consume trailing
# newline to avoid leaving a blank line
end = match.end
if replacement == "" and not match.text.endswith("\n") and content[end:end + 1] == "\n":
end += 1
new_content = new_content[: match.start] + replacement + new_content[end:]
if uses_crlf:
new_content = new_content.replace("\n", "\r\n")
fp.write_bytes(new_content.encode("utf-8"))
return f"Successfully edited {fp}"
file_state.record_write(fp)
msg = f"Successfully edited {fp}"
if warning:
msg = f"{warning}\n{msg}"
return msg
except PermissionError as e:
return f"Error: {e}"
except Exception as e:
return f"Error editing file: {e}"
def _file_not_found_msg(self, path: str, fp: Path) -> str:
"""Build an error message with 'Did you mean ...?' suggestions."""
parent = fp.parent
suggestions: list[str] = []
if parent.is_dir():
siblings = [f.name for f in parent.iterdir() if f.is_file()]
close = difflib.get_close_matches(fp.name, siblings, n=3, cutoff=0.6)
suggestions = [str(parent / c) for c in close]
parts = [f"Error: File not found: {path}"]
if suggestions:
parts.append("Did you mean: " + ", ".join(suggestions) + "?")
return "\n".join(parts)
@staticmethod
def _not_found_msg(old_text: str, content: str, path: str) -> str:
lines = content.splitlines(keepends=True)
old_lines = old_text.splitlines(keepends=True)
window = len(old_lines)
best_ratio, best_start = 0.0, 0
for i in range(max(1, len(lines) - window + 1)):
ratio = difflib.SequenceMatcher(None, old_lines, lines[i : i + window]).ratio()
if ratio > best_ratio:
best_ratio, best_start = ratio, i
best_ratio, best_start, best_window_lines, hints = _best_window(old_text, content)
if best_ratio > 0.5:
diff = "\n".join(difflib.unified_diff(
old_lines, lines[best_start : best_start + window],
old_text.splitlines(keepends=True),
best_window_lines,
fromfile="old_text (provided)",
tofile=f"{path} (actual, line {best_start + 1})",
lineterm="",
))
return f"Error: old_text not found in {path}.\nBest match ({best_ratio:.0%} similar) at line {best_start + 1}:\n{diff}"
hint_text = ""
if hints:
hint_text = "\nPossible cause: " + ", ".join(hints) + "."
return (
f"Error: old_text not found in {path}."
f"{hint_text}\nBest match ({best_ratio:.0%} similar) at line {best_start + 1}:\n{diff}"
)
if hints:
return (
f"Error: old_text not found in {path}. "
f"Possible cause: {', '.join(hints)}. "
"Copy the exact text from read_file and try again."
)
return f"Error: old_text not found in {path}. No similar text found. Verify the file content."
nanobot/agent/tools/mcp.py
+59 -33
View File
@@ -57,9 +57,7 @@ def _normalize_schema_for_openai(schema: Any) -> dict[str, Any]:
if "properties" in normalized and isinstance(normalized["properties"], dict):
normalized["properties"] = {
name: _normalize_schema_for_openai(prop)
if isinstance(prop, dict)
else prop
name: _normalize_schema_for_openai(prop) if isinstance(prop, dict) else prop
for name, prop in normalized["properties"].items()
}
@@ -138,9 +136,7 @@ class MCPToolWrapper(Tool):
class MCPResourceWrapper(Tool):
"""Wraps an MCP resource URI as a read-only nanobot Tool."""
def __init__(
self, session, server_name: str, resource_def, resource_timeout: int = 30
):
def __init__(self, session, server_name: str, resource_def, resource_timeout: int = 30):
self._session = session
self._uri = resource_def.uri
self._name = f"mcp_{server_name}_resource_{resource_def.name}"
@@ -211,9 +207,7 @@ class MCPResourceWrapper(Tool):
class MCPPromptWrapper(Tool):
"""Wraps an MCP prompt as a read-only nanobot Tool."""
def __init__(
self, session, server_name: str, prompt_def, prompt_timeout: int = 30
):
def __init__(self, session, server_name: str, prompt_def, prompt_timeout: int = 30):
self._session = session
self._prompt_name = prompt_def.name
self._name = f"mcp_{server_name}_prompt_{prompt_def.name}"
@@ -266,9 +260,7 @@ class MCPPromptWrapper(Tool):
timeout=self._prompt_timeout,
)
except asyncio.TimeoutError:
logger.warning(
"MCP prompt '{}' timed out after {}s", self._name, self._prompt_timeout
)
logger.warning("MCP prompt '{}' timed out after {}s", self._name, self._prompt_timeout)
return f"(MCP prompt call timed out after {self._prompt_timeout}s)"
except asyncio.CancelledError:
task = asyncio.current_task()
@@ -279,13 +271,17 @@ class MCPPromptWrapper(Tool):
except McpError as exc:
logger.error(
"MCP prompt '{}' failed: code={} message={}",
self._name, exc.error.code, exc.error.message,
self._name,
exc.error.code,
exc.error.message,
)
return f"(MCP prompt call failed: {exc.error.message} [code {exc.error.code}])"
except Exception as exc:
logger.exception(
"MCP prompt '{}' failed: {}: {}",
self._name, type(exc).__name__, exc,
self._name,
type(exc).__name__,
exc,
)
return f"(MCP prompt call failed: {type(exc).__name__})"
@@ -307,35 +303,44 @@ class MCPPromptWrapper(Tool):
async def connect_mcp_servers(
mcp_servers: dict, registry: ToolRegistry, stack: AsyncExitStack
) -> None:
"""Connect to configured MCP servers and register their tools, resources, and prompts."""
mcp_servers: dict, registry: ToolRegistry
) -> dict[str, AsyncExitStack]:
"""Connect to configured MCP servers and register their tools, resources, prompts.
Returns a dict mapping server name -> its dedicated AsyncExitStack.
Each server gets its own stack and runs in its own task to prevent
cancel scope conflicts when multiple MCP servers are configured.
"""
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():
async def connect_single_server(name: str, cfg) -> tuple[str, AsyncExitStack | None]:
server_stack = AsyncExitStack()
await server_stack.__aenter__()
try:
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
await server_stack.aclose()
return name, None
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))
read, write = await server_stack.enter_async_context(stdio_client(params))
elif transport_type == "sse":
def httpx_client_factory(
headers: dict[str, str] | None = None,
timeout: httpx.Timeout | None = None,
@@ -353,27 +358,26 @@ async def connect_mcp_servers(
auth=auth,
)
read, write = await stack.enter_async_context(
read, write = await server_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(
http_client = await server_stack.enter_async_context(
httpx.AsyncClient(
headers=cfg.headers or None,
follow_redirects=True,
timeout=None,
)
)
read, write, _ = await stack.enter_async_context(
read, write, _ = await server_stack.enter_async_context(
streamable_http_client(cfg.url, http_client=http_client)
)
else:
logger.warning("MCP server '{}': unknown transport type '{}'", name, transport_type)
continue
await server_stack.aclose()
return name, None
session = await stack.enter_async_context(ClientSession(read, write))
session = await server_stack.enter_async_context(ClientSession(read, write))
await session.initialize()
tools = await session.list_tools()
@@ -418,7 +422,6 @@ async def connect_mcp_servers(
", ".join(available_wrapped_names) or "(none)",
)
# --- Register resources ---
try:
resources_result = await session.list_resources()
for resource in resources_result.resources:
@@ -433,7 +436,6 @@ async def connect_mcp_servers(
except Exception as e:
logger.debug("MCP server '{}': resources not supported or failed: {}", name, e)
# --- Register prompts ---
try:
prompts_result = await session.list_prompts()
for prompt in prompts_result.prompts:
@@ -442,14 +444,38 @@ async def connect_mcp_servers(
)
registry.register(wrapper)
registered_count += 1
logger.debug(
"MCP: registered prompt '{}' from server '{}'", wrapper.name, name
)
logger.debug("MCP: registered prompt '{}' from server '{}'", wrapper.name, name)
except Exception as e:
logger.debug("MCP server '{}': prompts not supported or failed: {}", name, e)
logger.info(
"MCP server '{}': connected, {} capabilities registered", name, registered_count
)
return name, server_stack
except Exception as e:
logger.error("MCP server '{}': failed to connect: {}", name, e)
try:
await server_stack.aclose()
except Exception:
pass
return name, None
server_stacks: dict[str, AsyncExitStack] = {}
tasks: list[asyncio.Task] = []
for name, cfg in mcp_servers.items():
task = asyncio.create_task(connect_single_server(name, cfg))
tasks.append(task)
results = await asyncio.gather(*tasks, return_exceptions=True)
for i, result in enumerate(results):
name = list(mcp_servers.keys())[i]
if isinstance(result, BaseException):
if not isinstance(result, asyncio.CancelledError):
logger.error("MCP server '{}' connection task failed: {}", name, result)
elif result is not None and result[1] is not None:
server_stacks[result[0]] = result[1]
return server_stacks
nanobot/agent/tools/notebook.py
+161
View File
@@ -0,0 +1,161 @@
"""NotebookEditTool — edit Jupyter .ipynb notebooks."""
from __future__ import annotations
import json
import uuid
from typing import Any
from nanobot.agent.tools.base import tool_parameters
from nanobot.agent.tools.schema import IntegerSchema, StringSchema, tool_parameters_schema
from nanobot.agent.tools.filesystem import _FsTool
def _new_cell(source: str, cell_type: str = "code", generate_id: bool = False) -> dict:
cell: dict[str, Any] = {
"cell_type": cell_type,
"source": source,
"metadata": {},
}
if cell_type == "code":
cell["outputs"] = []
cell["execution_count"] = None
if generate_id:
cell["id"] = uuid.uuid4().hex[:8]
return cell
def _make_empty_notebook() -> dict:
return {
"nbformat": 4,
"nbformat_minor": 5,
"metadata": {
"kernelspec": {"display_name": "Python 3", "language": "python", "name": "python3"},
"language_info": {"name": "python"},
},
"cells": [],
}
@tool_parameters(
tool_parameters_schema(
path=StringSchema("Path to the .ipynb notebook file"),
cell_index=IntegerSchema(0, description="0-based index of the cell to edit", minimum=0),
new_source=StringSchema("New source content for the cell"),
cell_type=StringSchema(
"Cell type: 'code' or 'markdown' (default: code)",
enum=["code", "markdown"],
),
edit_mode=StringSchema(
"Mode: 'replace' (default), 'insert' (after target), or 'delete'",
enum=["replace", "insert", "delete"],
),
required=["path", "cell_index"],
)
)
class NotebookEditTool(_FsTool):
"""Edit Jupyter notebook cells: replace, insert, or delete."""
_VALID_CELL_TYPES = frozenset({"code", "markdown"})
_VALID_EDIT_MODES = frozenset({"replace", "insert", "delete"})
@property
def name(self) -> str:
return "notebook_edit"
@property
def description(self) -> str:
return (
"Edit a Jupyter notebook (.ipynb) cell. "
"Modes: replace (default) replaces cell content, "
"insert adds a new cell after the target index, "
"delete removes the cell at the index. "
"cell_index is 0-based."
)
async def execute(
self,
path: str | None = None,
cell_index: int = 0,
new_source: str = "",
cell_type: str = "code",
edit_mode: str = "replace",
**kwargs: Any,
) -> str:
try:
if not path:
return "Error: path is required"
if not path.endswith(".ipynb"):
return "Error: notebook_edit only works on .ipynb files. Use edit_file for other files."
if edit_mode not in self._VALID_EDIT_MODES:
return (
f"Error: Invalid edit_mode '{edit_mode}'. "
"Use one of: replace, insert, delete."
)
if cell_type not in self._VALID_CELL_TYPES:
return (
f"Error: Invalid cell_type '{cell_type}'. "
"Use one of: code, markdown."
)
fp = self._resolve(path)
# Create new notebook if file doesn't exist and mode is insert
if not fp.exists():
if edit_mode != "insert":
return f"Error: File not found: {path}"
nb = _make_empty_notebook()
cell = _new_cell(new_source, cell_type, generate_id=True)
nb["cells"].append(cell)
fp.parent.mkdir(parents=True, exist_ok=True)
fp.write_text(json.dumps(nb, indent=1, ensure_ascii=False), encoding="utf-8")
return f"Successfully created {fp} with 1 cell"
try:
nb = json.loads(fp.read_text(encoding="utf-8"))
except (json.JSONDecodeError, UnicodeDecodeError) as e:
return f"Error: Failed to parse notebook: {e}"
cells = nb.get("cells", [])
nbformat_minor = nb.get("nbformat_minor", 0)
generate_id = nb.get("nbformat", 0) >= 4 and nbformat_minor >= 5
if edit_mode == "delete":
if cell_index < 0 or cell_index >= len(cells):
return f"Error: cell_index {cell_index} out of range (notebook has {len(cells)} cells)"
cells.pop(cell_index)
nb["cells"] = cells
fp.write_text(json.dumps(nb, indent=1, ensure_ascii=False), encoding="utf-8")
return f"Successfully deleted cell {cell_index} from {fp}"
if edit_mode == "insert":
insert_at = min(cell_index + 1, len(cells))
cell = _new_cell(new_source, cell_type, generate_id=generate_id)
cells.insert(insert_at, cell)
nb["cells"] = cells
fp.write_text(json.dumps(nb, indent=1, ensure_ascii=False), encoding="utf-8")
return f"Successfully inserted cell at index {insert_at} in {fp}"
# Default: replace
if cell_index < 0 or cell_index >= len(cells):
return f"Error: cell_index {cell_index} out of range (notebook has {len(cells)} cells)"
cells[cell_index]["source"] = new_source
if cell_type and cells[cell_index].get("cell_type") != cell_type:
cells[cell_index]["cell_type"] = cell_type
if cell_type == "code":
cells[cell_index].setdefault("outputs", [])
cells[cell_index].setdefault("execution_count", None)
elif "outputs" in cells[cell_index]:
del cells[cell_index]["outputs"]
cells[cell_index].pop("execution_count", None)
nb["cells"] = cells
fp.write_text(json.dumps(nb, indent=1, ensure_ascii=False), encoding="utf-8")
return f"Successfully edited cell {cell_index} in {fp}"
except PermissionError as e:
return f"Error: {e}"
except Exception as e:
return f"Error editing notebook: {e}"
nanobot/agent/tools/shell.py
+14 -2
View File
@@ -46,6 +46,7 @@ class ExecTool(Tool):
restrict_to_workspace: bool = False,
sandbox: str = "",
path_append: str = "",
allowed_env_keys: list[str] | None = None,
):
self.timeout = timeout
self.working_dir = working_dir
@@ -64,6 +65,7 @@ class ExecTool(Tool):
self.allow_patterns = allow_patterns or []
self.restrict_to_workspace = restrict_to_workspace
self.path_append = path_append
self.allowed_env_keys = allowed_env_keys or []
@property
def name(self) -> str:
@@ -208,7 +210,7 @@ class ExecTool(Tool):
"""
if _IS_WINDOWS:
sr = os.environ.get("SYSTEMROOT", r"C:\Windows")
return {
env = {
"SYSTEMROOT": sr,
"COMSPEC": os.environ.get("COMSPEC", f"{sr}\\system32\\cmd.exe"),
"USERPROFILE": os.environ.get("USERPROFILE", ""),
@@ -225,12 +227,22 @@ class ExecTool(Tool):
"ProgramFiles(x86)": os.environ.get("ProgramFiles(x86)", ""),
"ProgramW6432": os.environ.get("ProgramW6432", ""),
}
for key in self.allowed_env_keys:
val = os.environ.get(key)
if val is not None:
env[key] = val
return env
home = os.environ.get("HOME", "/tmp")
return {
env = {
"HOME": home,
"LANG": os.environ.get("LANG", "C.UTF-8"),
"TERM": os.environ.get("TERM", "dumb"),
}
for key in self.allowed_env_keys:
val = os.environ.get(key)
if val is not None:
env[key] = val
return env
def _guard_command(self, command: str, cwd: str) -> str | None:
"""Best-effort safety guard for potentially destructive commands."""
nanobot/agent/tools/web.py
+25
View File
@@ -114,6 +114,8 @@ class WebSearchTool(Tool):
return await self._search_jina(query, n)
elif provider == "brave":
return await self._search_brave(query, n)
elif provider == "kagi":
return await self._search_kagi(query, n)
else:
return f"Error: unknown search provider '{provider}'"
@@ -204,6 +206,29 @@ class WebSearchTool(Tool):
logger.warning("Jina search failed ({}), falling back to DuckDuckGo", e)
return await self._search_duckduckgo(query, n)
async def _search_kagi(self, query: str, n: int) -> str:
api_key = self.config.api_key or os.environ.get("KAGI_API_KEY", "")
if not api_key:
logger.warning("KAGI_API_KEY not set, falling back to DuckDuckGo")
return await self._search_duckduckgo(query, n)
try:
async with httpx.AsyncClient(proxy=self.proxy) as client:
r = await client.get(
"https://kagi.com/api/v0/search",
params={"q": query, "limit": n},
headers={"Authorization": f"Bot {api_key}"},
timeout=10.0,
)
r.raise_for_status()
# t=0 items are search results; other values are related searches, etc.
items = [
{"title": d.get("title", ""), "url": d.get("url", ""), "content": d.get("snippet", "")}
for d in r.json().get("data", []) if d.get("t") == 0
]
return _format_results(query, items, n)
except Exception as e:
return f"Error: {e}"
async def _search_duckduckgo(self, query: str, n: int) -> str:
try:
# Note: duckduckgo_search is synchronous and does its own requests
nanobot/channels/discord.py
+54 -9
View File
@@ -22,6 +22,7 @@ from nanobot.utils.helpers import safe_filename, split_message
DISCORD_AVAILABLE = importlib.util.find_spec("discord") is not None
if TYPE_CHECKING:
import aiohttp
import discord
from discord import app_commands
from discord.abc import Messageable
@@ -58,6 +59,9 @@ class DiscordConfig(Base):
working_emoji: str = "🔧"
working_emoji_delay: float = 2.0
streaming: bool = True
proxy: str | None = None
proxy_username: str | None = None
proxy_password: str | None = None
if DISCORD_AVAILABLE:
@@ -65,8 +69,15 @@ if DISCORD_AVAILABLE:
class DiscordBotClient(discord.Client):
"""discord.py client that forwards events to the channel."""
def __init__(self, channel: DiscordChannel, *, intents: discord.Intents) -> None:
super().__init__(intents=intents)
def __init__(
self,
channel: DiscordChannel,
*,
intents: discord.Intents,
proxy: str | None = None,
proxy_auth: aiohttp.BasicAuth | None = None,
) -> None:
super().__init__(intents=intents, proxy=proxy, proxy_auth=proxy_auth)
self._channel = channel
self.tree = app_commands.CommandTree(self)
self._register_app_commands()
@@ -130,6 +141,7 @@ if DISCORD_AVAILABLE:
)
for name, description, command_text in commands:
@self.tree.command(name=name, description=description)
async def command_handler(
interaction: discord.Interaction,
@@ -186,7 +198,9 @@ if DISCORD_AVAILABLE:
else:
failed_media.append(Path(media_path).name)
for index, chunk in enumerate(self._build_chunks(msg.content or "", failed_media, sent_media)):
for index, chunk in enumerate(
self._build_chunks(msg.content or "", failed_media, sent_media)
):
kwargs: dict[str, Any] = {"content": chunk}
if index == 0 and reference is not None and not sent_media:
kwargs["reference"] = reference
@@ -292,7 +306,29 @@ class DiscordChannel(BaseChannel):
try:
intents = discord.Intents.none()
intents.value = self.config.intents
self._client = DiscordBotClient(self, intents=intents)
proxy_auth = None
has_user = bool(self.config.proxy_username)
has_pass = bool(self.config.proxy_password)
if has_user and has_pass:
import aiohttp
proxy_auth = aiohttp.BasicAuth(
login=self.config.proxy_username,
password=self.config.proxy_password,
)
elif has_user != has_pass:
logger.warning(
"Discord proxy auth incomplete: both proxy_username and "
"proxy_password must be set; ignoring partial credentials",
)
self._client = DiscordBotClient(
self,
intents=intents,
proxy=self.config.proxy,
proxy_auth=proxy_auth,
)
except Exception as e:
logger.error("Failed to initialize Discord client: {}", e)
self._client = None
@@ -335,7 +371,9 @@ class DiscordChannel(BaseChannel):
await self._stop_typing(msg.chat_id)
await self._clear_reactions(msg.chat_id)
async def send_delta(self, chat_id: str, delta: str, metadata: dict[str, Any] | None = None) -> None:
async def send_delta(
self, chat_id: str, delta: str, metadata: dict[str, Any] | None = None
) -> None:
"""Progressive Discord delivery: send once, then edit until the stream ends."""
client = self._client
if client is None or not client.is_ready():
@@ -355,7 +393,9 @@ class DiscordChannel(BaseChannel):
return
buf = self._stream_bufs.get(chat_id)
if buf is None or (stream_id is not None and buf.stream_id is not None and buf.stream_id != stream_id):
if buf is None or (
stream_id is not None and buf.stream_id is not None and buf.stream_id != stream_id
):
buf = _StreamBuf(stream_id=stream_id)
self._stream_bufs[chat_id] = buf
elif buf.stream_id is None:
@@ -534,7 +574,11 @@ class DiscordChannel(BaseChannel):
@staticmethod
def _build_inbound_metadata(message: discord.Message) -> dict[str, str | None]:
"""Build metadata for inbound Discord messages."""
reply_to = str(message.reference.message_id) if message.reference and message.reference.message_id else None
reply_to = (
str(message.reference.message_id)
if message.reference and message.reference.message_id
else None
)
return {
"message_id": str(message.id),
"guild_id": str(message.guild.id) if message.guild else None,
@@ -549,7 +593,9 @@ class DiscordChannel(BaseChannel):
if self.config.group_policy == "mention":
bot_user_id = self._bot_user_id
if bot_user_id is None:
logger.debug("Discord message in {} ignored (bot identity unavailable)", message.channel.id)
logger.debug(
"Discord message in {} ignored (bot identity unavailable)", message.channel.id
)
return False
if any(str(user.id) == bot_user_id for user in message.mentions):
@@ -591,7 +637,6 @@ class DiscordChannel(BaseChannel):
except asyncio.CancelledError:
pass
async def _clear_reactions(self, chat_id: str) -> None:
"""Remove all pending reactions after bot replies."""
# Cancel delayed working emoji if it hasn't fired yet
nanobot/channels/feishu.py
+76 -16
View File
@@ -22,6 +22,8 @@ from nanobot.channels.base import BaseChannel
from nanobot.config.paths import get_media_dir
from nanobot.config.schema import Base
from lark_oapi.core.const import FEISHU_DOMAIN, LARK_DOMAIN
FEISHU_AVAILABLE = importlib.util.find_spec("lark_oapi") is not None
# Message type display mapping
@@ -250,9 +252,12 @@ class FeishuConfig(Base):
verification_token: str = ""
allow_from: list[str] = Field(default_factory=list)
react_emoji: str = "THUMBSUP"
done_emoji: str | None = None # Emoji to show when task is completed (e.g., "DONE", "OK")
tool_hint_prefix: str = "\U0001f527" # Prefix for inline tool hints (default: 🔧)
group_policy: Literal["open", "mention"] = "mention"
reply_to_message: bool = False # If True, bot replies quote the user's original message
streaming: bool = True
domain: Literal["feishu", "lark"] = "feishu" # Set to "lark" for international Lark
_STREAM_ELEMENT_ID = "streaming_md"
@@ -326,10 +331,12 @@ class FeishuChannel(BaseChannel):
self._loop = asyncio.get_running_loop()
# Create Lark client for sending messages
domain = LARK_DOMAIN if self.config.domain == "lark" else FEISHU_DOMAIN
self._client = (
lark.Client.builder()
.app_id(self.config.app_id)
.app_secret(self.config.app_secret)
.domain(domain)
.log_level(lark.LogLevel.INFO)
.build()
)
@@ -357,6 +364,7 @@ class FeishuChannel(BaseChannel):
self._ws_client = lark.ws.Client(
self.config.app_id,
self.config.app_secret,
domain=domain,
event_handler=event_handler,
log_level=lark.LogLevel.INFO,
)
@@ -1012,14 +1020,29 @@ class FeishuChannel(BaseChannel):
elif msg_type in ("audio", "file", "media"):
file_key = content_json.get("file_key")
if file_key and message_id:
data, filename = await loop.run_in_executor(
None, self._download_file_sync, message_id, file_key, msg_type
)
if not filename:
filename = file_key[:16]
if msg_type == "audio" and not filename.endswith(".opus"):
filename = f"{filename}.opus"
if not file_key:
logger.warning("Feishu {} message missing file_key: {}", msg_type, content_json)
return None, f"[{msg_type}: missing file_key]"
if not message_id:
logger.warning("Feishu {} message missing message_id", msg_type)
return None, f"[{msg_type}: missing message_id]"
data, filename = await loop.run_in_executor(
None, self._download_file_sync, message_id, file_key, msg_type
)
if not data:
logger.warning("Feishu {} download failed: file_key={}", msg_type, file_key)
return None, f"[{msg_type}: download failed]"
if not filename:
filename = file_key[:16]
# Feishu voice messages are opus in OGG container.
# Use .ogg extension for better Whisper compatibility.
if msg_type == "audio":
if not any(filename.endswith(ext) for ext in (".opus", ".ogg", ".oga")):
filename = f"{filename}.ogg"
if data and filename:
file_path = media_dir / filename
@@ -1263,7 +1286,15 @@ class FeishuChannel(BaseChannel):
async def send_delta(
self, chat_id: str, delta: str, metadata: dict[str, Any] | None = None
) -> None:
"""Progressive streaming via CardKit: create card on first delta, stream-update on subsequent."""
"""Progressive streaming via CardKit: create card on first delta, stream-update on subsequent.
Supported metadata keys:
_stream_end: Finalize the streaming card.
_resuming: Mid-turn pause – flush but keep the buffer alive.
_tool_hint: Delta is a formatted tool hint (for display only).
message_id: Original message id (used with _stream_end for reaction cleanup).
reaction_id: Reaction id to remove on stream end.
"""
if not self._client:
return
meta = metadata or {}
@@ -1274,6 +1305,22 @@ class FeishuChannel(BaseChannel):
if meta.get("_stream_end"):
if (message_id := meta.get("message_id")) and (reaction_id := meta.get("reaction_id")):
await self._remove_reaction(message_id, reaction_id)
# Add completion emoji if configured
if self.config.done_emoji and message_id:
await self._add_reaction(message_id, self.config.done_emoji)
resuming = meta.get("_resuming", False)
if resuming:
# Mid-turn pause (e.g. tool call between streaming segments).
# Flush current text to card but keep the buffer alive so the
# next segment appends to the same card.
buf = self._stream_bufs.get(chat_id)
if buf and buf.card_id and buf.text:
buf.sequence += 1
await loop.run_in_executor(
None, self._stream_update_text_sync, buf.card_id, buf.text, buf.sequence,
)
return
buf = self._stream_bufs.pop(chat_id, None)
if not buf or not buf.text:
@@ -1346,13 +1393,26 @@ class FeishuChannel(BaseChannel):
receive_id_type = "chat_id" if msg.chat_id.startswith("oc_") else "open_id"
loop = asyncio.get_running_loop()
# Handle tool hint messages as code blocks in interactive cards.
# These are progress-only messages and should bypass normal reply routing.
# Handle tool hint messages. When a streaming card is active for
# this chat, inline the hint into the card instead of sending a
# separate message so the user experience stays cohesive.
if msg.metadata.get("_tool_hint"):
if msg.content and msg.content.strip():
await self._send_tool_hint_card(
receive_id_type, msg.chat_id, msg.content.strip()
)
hint = (msg.content or "").strip()
if not hint:
return
buf = self._stream_bufs.get(msg.chat_id)
if buf and buf.card_id:
# Delegate to send_delta so tool hints get the same
# throttling (and card creation) as regular text deltas.
lines = self.__class__._format_tool_hint_lines(hint).split("\n")
delta = "\n\n" + "\n".join(
f"{self.config.tool_hint_prefix} {ln}" for ln in lines if ln.strip()
) + "\n\n"
await self.send_delta(msg.chat_id, delta)
return
await self._send_tool_hint_card(
receive_id_type, msg.chat_id, hint
)
return
# Determine whether the first message should quote the user's message.
@@ -1661,7 +1721,7 @@ class FeishuChannel(BaseChannel):
loop = asyncio.get_running_loop()
# Put each top-level tool call on its own line without altering commas inside arguments.
formatted_code = self._format_tool_hint_lines(tool_hint)
formatted_code = self.__class__._format_tool_hint_lines(tool_hint)
card = {
"config": {"wide_screen_mode": True},
nanobot/channels/qq.py
+112 -82
View File
@@ -242,43 +242,46 @@ class QQChannel(BaseChannel):
async def send(self, msg: OutboundMessage) -> None:
"""Send attachments first, then text."""
if not self._client:
logger.warning("QQ client not initialized")
return
try:
if not self._client:
logger.warning("QQ client not initialized")
return
msg_id = msg.metadata.get("message_id")
chat_type = self._chat_type_cache.get(msg.chat_id, "c2c")
is_group = chat_type == "group"
msg_id = msg.metadata.get("message_id")
chat_type = self._chat_type_cache.get(msg.chat_id, "c2c")
is_group = chat_type == "group"
# 1) Send media
for media_ref in msg.media or []:
ok = await self._send_media(
chat_id=msg.chat_id,
media_ref=media_ref,
msg_id=msg_id,
is_group=is_group,
)
if not ok:
filename = (
os.path.basename(urlparse(media_ref).path)
or os.path.basename(media_ref)
or "file"
# 1) Send media
for media_ref in msg.media or []:
ok = await self._send_media(
chat_id=msg.chat_id,
media_ref=media_ref,
msg_id=msg_id,
is_group=is_group,
)
if not ok:
filename = (
os.path.basename(urlparse(media_ref).path)
or os.path.basename(media_ref)
or "file"
)
await self._send_text_only(
chat_id=msg.chat_id,
is_group=is_group,
msg_id=msg_id,
content=f"[Attachment send failed: {filename}]",
)
# 2) Send text
if msg.content and msg.content.strip():
await self._send_text_only(
chat_id=msg.chat_id,
is_group=is_group,
msg_id=msg_id,
content=f"[Attachment send failed: {filename}]",
content=msg.content.strip(),
)
# 2) Send text
if msg.content and msg.content.strip():
await self._send_text_only(
chat_id=msg.chat_id,
is_group=is_group,
msg_id=msg_id,
content=msg.content.strip(),
)
except Exception:
logger.exception("Error sending QQ message to chat_id={}", msg.chat_id)
async def _send_text_only(
self,
@@ -438,15 +441,26 @@ class QQChannel(BaseChannel):
endpoint = "/v2/users/{openid}/files"
id_key = "openid"
payload = {
payload: dict[str, Any] = {
id_key: chat_id,
"file_type": file_type,
"file_data": file_data,
"file_name": file_name,
"srv_send_msg": srv_send_msg,
}
# Only pass file_name for non-image types (file_type=4).
# Passing file_name for images causes QQ client to render them as
# file attachments instead of inline images.
if file_type != QQ_FILE_TYPE_IMAGE and file_name:
payload["file_name"] = file_name
route = Route("POST", endpoint, **{id_key: chat_id})
return await self._client.api._http.request(route, json=payload)
result = await self._client.api._http.request(route, json=payload)
# Extract only the file_info field to avoid extra fields (file_uuid, ttl, etc.)
# that may confuse QQ client when sending the media object.
if isinstance(result, dict) and "file_info" in result:
return {"file_info": result["file_info"]}
return result
# ---------------------------
# Inbound (receive)
@@ -454,58 +468,68 @@ class QQChannel(BaseChannel):
async def _on_message(self, data: C2CMessage | GroupMessage, is_group: bool = False) -> None:
"""Parse inbound message, download attachments, and publish to the bus."""
if data.id in self._processed_ids:
return
self._processed_ids.append(data.id)
try:
if data.id in self._processed_ids:
return
self._processed_ids.append(data.id)
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"
content = (data.content or "").strip()
# the data used by tests don't contain attachments property
# so we use getattr with a default of [] to avoid AttributeError in tests
attachments = getattr(data, "attachments", None) or []
media_paths, recv_lines, att_meta = await self._handle_attachments(attachments)
# Compose content that always contains actionable saved paths
if recv_lines:
tag = "[Image]" if any(_is_image_name(Path(p).name) for p in media_paths) else "[File]"
file_block = "Received files:\n" + "\n".join(recv_lines)
content = f"{content}\n\n{file_block}".strip() if content else f"{tag}\n{file_block}"
if not content and not media_paths:
return
if self.config.ack_message:
try:
await self._send_text_only(
chat_id=chat_id,
is_group=is_group,
msg_id=data.id,
content=self.config.ack_message,
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")
)
except Exception:
logger.debug("QQ ack message failed for chat_id={}", chat_id)
user_id = chat_id
self._chat_type_cache[chat_id] = "c2c"
await self._handle_message(
sender_id=user_id,
chat_id=chat_id,
content=content,
media=media_paths if media_paths else None,
metadata={
"message_id": data.id,
"attachments": att_meta,
},
)
content = (data.content or "").strip()
# the data used by tests don't contain attachments property
# so we use getattr with a default of [] to avoid AttributeError in tests
attachments = getattr(data, "attachments", None) or []
media_paths, recv_lines, att_meta = await self._handle_attachments(attachments)
# Compose content that always contains actionable saved paths
if recv_lines:
tag = (
"[Image]"
if any(_is_image_name(Path(p).name) for p in media_paths)
else "[File]"
)
file_block = "Received files:\n" + "\n".join(recv_lines)
content = (
f"{content}\n\n{file_block}".strip() if content else f"{tag}\n{file_block}"
)
if not content and not media_paths:
return
if self.config.ack_message:
try:
await self._send_text_only(
chat_id=chat_id,
is_group=is_group,
msg_id=data.id,
content=self.config.ack_message,
)
except Exception:
logger.debug("QQ ack message failed for chat_id={}", chat_id)
await self._handle_message(
sender_id=user_id,
chat_id=chat_id,
content=content,
media=media_paths if media_paths else None,
metadata={
"message_id": data.id,
"attachments": att_meta,
},
)
except Exception:
logger.exception("Error handling QQ inbound message id={}", getattr(data, "id", "?"))
async def _handle_attachments(
self,
@@ -520,7 +544,9 @@ class QQChannel(BaseChannel):
return media_paths, recv_lines, att_meta
for att in attachments:
url, filename, ctype = att.url, att.filename, att.content_type
url = getattr(att, "url", None) or ""
filename = getattr(att, "filename", None) or ""
ctype = getattr(att, "content_type", None) or ""
logger.info("Downloading file from QQ: {}", filename or url)
local_path = await self._download_to_media_dir_chunked(url, filename_hint=filename)
@@ -555,6 +581,10 @@ class QQChannel(BaseChannel):
Enforces a max download size and writes to a .part temp file
that is atomically renamed on success.
"""
# Handle protocol-relative URLs (e.g. "//multimedia.nt.qq.com/...")
if url.startswith("//"):
url = f"https:{url}"
if not self._http:
self._http = aiohttp.ClientSession(timeout=aiohttp.ClientTimeout(total=120))
nanobot/channels/websocket.py
+457
View File
@@ -0,0 +1,457 @@
"""WebSocket server channel: nanobot acts as a WebSocket server and serves connected clients."""
from __future__ import annotations
import asyncio
import email.utils
import hmac
import http
import json
import secrets
import ssl
import time
import uuid
from typing import Any, Self
from urllib.parse import parse_qs, urlparse
from loguru import logger
from pydantic import Field, field_validator, model_validator
from websockets.asyncio.server import ServerConnection, serve
from websockets.datastructures import Headers
from websockets.exceptions import ConnectionClosed
from websockets.http11 import Request as WsRequest, Response
from nanobot.bus.events import OutboundMessage
from nanobot.bus.queue import MessageBus
from nanobot.channels.base import BaseChannel
from nanobot.config.schema import Base
def _strip_trailing_slash(path: str) -> str:
if len(path) > 1 and path.endswith("/"):
return path.rstrip("/")
return path or "/"
def _normalize_config_path(path: str) -> str:
return _strip_trailing_slash(path)
class WebSocketConfig(Base):
"""WebSocket server channel configuration.
Clients connect with URLs like ``ws://{host}:{port}{path}?client_id=...&token=...``.
- ``client_id``: Used for ``allow_from`` authorization; if omitted, a value is generated and logged.
- ``token``: If non-empty, the ``token`` query param may match this static secret; short-lived tokens
from ``token_issue_path`` are also accepted.
- ``token_issue_path``: If non-empty, **GET** (HTTP/1.1) to this path returns JSON
``{"token": "...", "expires_in": <seconds>}``; use ``?token=...`` when opening the WebSocket.
Must differ from ``path`` (the WS upgrade path). If the client runs in the **same process** as
nanobot and shares the asyncio loop, use a thread or async HTTP client for GET—do not call
blocking ``urllib`` or synchronous ``httpx`` from inside a coroutine.
- ``token_issue_secret``: If non-empty, token requests must send ``Authorization: Bearer <secret>`` or
``X-Nanobot-Auth: <secret>``.
- ``websocket_requires_token``: If True, the handshake must include a valid token (static or issued and not expired).
- Each connection has its own session: a unique ``chat_id`` maps to the agent session internally.
- ``media`` field in outbound messages contains local filesystem paths; remote clients need a
shared filesystem or an HTTP file server to access these files.
"""
enabled: bool = False
host: str = "127.0.0.1"
port: int = 8765
path: str = "/"
token: str = ""
token_issue_path: str = ""
token_issue_secret: str = ""
token_ttl_s: int = Field(default=300, ge=30, le=86_400)
websocket_requires_token: bool = True
allow_from: list[str] = Field(default_factory=lambda: ["*"])
streaming: bool = True
max_message_bytes: int = Field(default=1_048_576, ge=1024, le=16_777_216)
ping_interval_s: float = Field(default=20.0, ge=5.0, le=300.0)
ping_timeout_s: float = Field(default=20.0, ge=5.0, le=300.0)
ssl_certfile: str = ""
ssl_keyfile: str = ""
@field_validator("path")
@classmethod
def path_must_start_with_slash(cls, value: str) -> str:
if not value.startswith("/"):
raise ValueError('path must start with "/"')
return _normalize_config_path(value)
@field_validator("token_issue_path")
@classmethod
def token_issue_path_format(cls, value: str) -> str:
value = value.strip()
if not value:
return ""
if not value.startswith("/"):
raise ValueError('token_issue_path must start with "/"')
return _normalize_config_path(value)
@model_validator(mode="after")
def token_issue_path_differs_from_ws_path(self) -> Self:
if not self.token_issue_path:
return self
if _normalize_config_path(self.token_issue_path) == _normalize_config_path(self.path):
raise ValueError("token_issue_path must differ from path (the WebSocket upgrade path)")
return self
def _http_json_response(data: dict[str, Any], *, status: int = 200) -> Response:
body = json.dumps(data, ensure_ascii=False).encode("utf-8")
headers = Headers(
[
("Date", email.utils.formatdate(usegmt=True)),
("Connection", "close"),
("Content-Length", str(len(body))),
("Content-Type", "application/json; charset=utf-8"),
]
)
reason = http.HTTPStatus(status).phrase
return Response(status, reason, headers, body)
def _parse_request_path(path_with_query: str) -> tuple[str, dict[str, list[str]]]:
"""Parse normalized path and query parameters in one pass."""
parsed = urlparse("ws://x" + path_with_query)
path = _strip_trailing_slash(parsed.path or "/")
return path, parse_qs(parsed.query)
def _normalize_http_path(path_with_query: str) -> str:
"""Return the path component (no query string), with trailing slash normalized (root stays ``/``)."""
return _parse_request_path(path_with_query)[0]
def _parse_query(path_with_query: str) -> dict[str, list[str]]:
return _parse_request_path(path_with_query)[1]
def _query_first(query: dict[str, list[str]], key: str) -> str | None:
"""Return the first value for *key*, or None."""
values = query.get(key)
return values[0] if values else None
def _parse_inbound_payload(raw: str) -> str | None:
"""Parse a client frame into text; return None for empty or unrecognized content."""
text = raw.strip()
if not text:
return None
if text.startswith("{"):
try:
data = json.loads(text)
except json.JSONDecodeError:
return text
if isinstance(data, dict):
for key in ("content", "text", "message"):
value = data.get(key)
if isinstance(value, str) and value.strip():
return value
return None
return None
return text
def _issue_route_secret_matches(headers: Any, configured_secret: str) -> bool:
"""Return True if the token-issue HTTP request carries credentials matching ``token_issue_secret``."""
if not configured_secret:
return True
authorization = headers.get("Authorization") or headers.get("authorization")
if authorization and authorization.lower().startswith("bearer "):
supplied = authorization[7:].strip()
return hmac.compare_digest(supplied, configured_secret)
header_token = headers.get("X-Nanobot-Auth") or headers.get("x-nanobot-auth")
if not header_token:
return False
return hmac.compare_digest(header_token.strip(), configured_secret)
class WebSocketChannel(BaseChannel):
"""Run a local WebSocket server; forward text/JSON messages to the message bus."""
name = "websocket"
display_name = "WebSocket"
def __init__(self, config: Any, bus: MessageBus):
if isinstance(config, dict):
config = WebSocketConfig.model_validate(config)
super().__init__(config, bus)
self.config: WebSocketConfig = config
self._connections: dict[str, Any] = {}
self._issued_tokens: dict[str, float] = {}
self._stop_event: asyncio.Event | None = None
self._server_task: asyncio.Task[None] | None = None
@classmethod
def default_config(cls) -> dict[str, Any]:
return WebSocketConfig().model_dump(by_alias=True)
def _expected_path(self) -> str:
return _normalize_config_path(self.config.path)
def _build_ssl_context(self) -> ssl.SSLContext | None:
cert = self.config.ssl_certfile.strip()
key = self.config.ssl_keyfile.strip()
if not cert and not key:
return None
if not cert or not key:
raise ValueError(
"websocket: ssl_certfile and ssl_keyfile must both be set for WSS, or both left empty"
)
ctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
ctx.minimum_version = ssl.TLSVersion.TLSv1_2
ctx.load_cert_chain(certfile=cert, keyfile=key)
return ctx
_MAX_ISSUED_TOKENS = 10_000
def _purge_expired_issued_tokens(self) -> None:
now = time.monotonic()
for token_key, expiry in list(self._issued_tokens.items()):
if now > expiry:
self._issued_tokens.pop(token_key, None)
def _take_issued_token_if_valid(self, token_value: str | None) -> bool:
"""Validate and consume one issued token (single use per connection attempt).
Uses single-step pop to minimize the window between lookup and removal;
safe under asyncio's single-threaded cooperative model.
"""
if not token_value:
return False
self._purge_expired_issued_tokens()
expiry = self._issued_tokens.pop(token_value, None)
if expiry is None:
return False
if time.monotonic() > expiry:
return False
return True
def _handle_token_issue_http(self, connection: Any, request: Any) -> Any:
secret = self.config.token_issue_secret.strip()
if secret:
if not _issue_route_secret_matches(request.headers, secret):
return connection.respond(401, "Unauthorized")
else:
logger.warning(
"websocket: token_issue_path is set but token_issue_secret is empty; "
"any client can obtain connection tokens — set token_issue_secret for production."
)
self._purge_expired_issued_tokens()
if len(self._issued_tokens) >= self._MAX_ISSUED_TOKENS:
logger.error(
"websocket: too many outstanding issued tokens ({}), rejecting issuance",
len(self._issued_tokens),
)
return _http_json_response({"error": "too many outstanding tokens"}, status=429)
token_value = f"nbwt_{secrets.token_urlsafe(32)}"
self._issued_tokens[token_value] = time.monotonic() + float(self.config.token_ttl_s)
return _http_json_response(
{"token": token_value, "expires_in": self.config.token_ttl_s}
)
def _authorize_websocket_handshake(self, connection: Any, query: dict[str, list[str]]) -> Any:
supplied = _query_first(query, "token")
static_token = self.config.token.strip()
if static_token:
if supplied and hmac.compare_digest(supplied, static_token):
return None
if supplied and self._take_issued_token_if_valid(supplied):
return None
return connection.respond(401, "Unauthorized")
if self.config.websocket_requires_token:
if supplied and self._take_issued_token_if_valid(supplied):
return None
return connection.respond(401, "Unauthorized")
if supplied:
self._take_issued_token_if_valid(supplied)
return None
async def start(self) -> None:
self._running = True
self._stop_event = asyncio.Event()
ssl_context = self._build_ssl_context()
scheme = "wss" if ssl_context else "ws"
async def process_request(
connection: ServerConnection,
request: WsRequest,
) -> Any:
got, _ = _parse_request_path(request.path)
if self.config.token_issue_path:
issue_expected = _normalize_config_path(self.config.token_issue_path)
if got == issue_expected:
return self._handle_token_issue_http(connection, request)
expected_ws = self._expected_path()
if got != expected_ws:
return connection.respond(404, "Not Found")
# Early reject before WebSocket upgrade to avoid unnecessary overhead;
# _handle_message() performs a second check as defense-in-depth.
query = _parse_query(request.path)
client_id = _query_first(query, "client_id") or ""
if len(client_id) > 128:
client_id = client_id[:128]
if not self.is_allowed(client_id):
return connection.respond(403, "Forbidden")
return self._authorize_websocket_handshake(connection, query)
async def handler(connection: ServerConnection) -> None:
await self._connection_loop(connection)
logger.info(
"WebSocket server listening on {}://{}:{}{}",
scheme,
self.config.host,
self.config.port,
self.config.path,
)
if self.config.token_issue_path:
logger.info(
"WebSocket token issue route: {}://{}:{}{}",
scheme,
self.config.host,
self.config.port,
_normalize_config_path(self.config.token_issue_path),
)
async def runner() -> None:
async with serve(
handler,
self.config.host,
self.config.port,
process_request=process_request,
max_size=self.config.max_message_bytes,
ping_interval=self.config.ping_interval_s,
ping_timeout=self.config.ping_timeout_s,
ssl=ssl_context,
):
assert self._stop_event is not None
await self._stop_event.wait()
self._server_task = asyncio.create_task(runner())
await self._server_task
async def _connection_loop(self, connection: Any) -> None:
request = connection.request
path_part = request.path if request else "/"
_, query = _parse_request_path(path_part)
client_id_raw = _query_first(query, "client_id")
client_id = client_id_raw.strip() if client_id_raw else ""
if not client_id:
client_id = f"anon-{uuid.uuid4().hex[:12]}"
elif len(client_id) > 128:
logger.warning("websocket: client_id too long ({} chars), truncating", len(client_id))
client_id = client_id[:128]
chat_id = str(uuid.uuid4())
try:
await connection.send(
json.dumps(
{
"event": "ready",
"chat_id": chat_id,
"client_id": client_id,
},
ensure_ascii=False,
)
)
# Register only after ready is successfully sent to avoid out-of-order sends
self._connections[chat_id] = connection
async for raw in connection:
if isinstance(raw, bytes):
try:
raw = raw.decode("utf-8")
except UnicodeDecodeError:
logger.warning("websocket: ignoring non-utf8 binary frame")
continue
content = _parse_inbound_payload(raw)
if content is None:
continue
await self._handle_message(
sender_id=client_id,
chat_id=chat_id,
content=content,
metadata={"remote": getattr(connection, "remote_address", None)},
)
except Exception as e:
logger.debug("websocket connection ended: {}", e)
finally:
self._connections.pop(chat_id, None)
async def stop(self) -> None:
if not self._running:
return
self._running = False
if self._stop_event:
self._stop_event.set()
if self._server_task:
try:
await self._server_task
except Exception as e:
logger.warning("websocket: server task error during shutdown: {}", e)
self._server_task = None
self._connections.clear()
self._issued_tokens.clear()
async def _safe_send(self, chat_id: str, raw: str, *, label: str = "") -> None:
"""Send a raw frame, cleaning up dead connections on ConnectionClosed."""
connection = self._connections.get(chat_id)
if connection is None:
return
try:
await connection.send(raw)
except ConnectionClosed:
self._connections.pop(chat_id, None)
logger.warning("websocket{}connection gone for chat_id={}", label, chat_id)
except Exception as e:
logger.error("websocket{}send failed: {}", label, e)
raise
async def send(self, msg: OutboundMessage) -> None:
connection = self._connections.get(msg.chat_id)
if connection is None:
logger.warning("websocket: no active connection for chat_id={}", msg.chat_id)
return
payload: dict[str, Any] = {
"event": "message",
"text": msg.content,
}
if msg.media:
payload["media"] = msg.media
if msg.reply_to:
payload["reply_to"] = msg.reply_to
raw = json.dumps(payload, ensure_ascii=False)
await self._safe_send(msg.chat_id, raw, label=" ")
async def send_delta(
self,
chat_id: str,
delta: str,
metadata: dict[str, Any] | None = None,
) -> None:
if self._connections.get(chat_id) is None:
return
meta = metadata or {}
if meta.get("_stream_end"):
body: dict[str, Any] = {"event": "stream_end"}
else:
body = {
"event": "delta",
"text": delta,
}
if meta.get("_stream_id") is not None:
body["stream_id"] = meta["_stream_id"]
raw = json.dumps(body, ensure_ascii=False)
await self._safe_send(chat_id, raw, label=" stream ")
nanobot/channels/wecom.py
+195 -26
View File
@@ -1,9 +1,13 @@
"""WeCom (Enterprise WeChat) channel implementation using wecom_aibot_sdk."""
import asyncio
import base64
import hashlib
import importlib.util
import os
import re
from collections import OrderedDict
from pathlib import Path
from typing import Any
from loguru import logger
@@ -17,6 +21,37 @@ from pydantic import Field
WECOM_AVAILABLE = importlib.util.find_spec("wecom_aibot_sdk") is not None
# Upload safety limits (matching QQ channel defaults)
WECOM_UPLOAD_MAX_BYTES = 1024 * 1024 * 200 # 200MB
# Replace unsafe characters with "_", keep Chinese and common safe punctuation.
_SAFE_NAME_RE = re.compile(r"[^\w.\-()\[\]（）【】\u4e00-\u9fff]+", re.UNICODE)
def _sanitize_filename(name: str) -> str:
"""Sanitize filename to avoid traversal and problematic chars."""
name = (name or "").strip()
name = Path(name).name
name = _SAFE_NAME_RE.sub("_", name).strip("._ ")
return name
_IMAGE_EXTS = {".jpg", ".jpeg", ".png", ".gif", ".webp", ".bmp"}
_VIDEO_EXTS = {".mp4", ".avi", ".mov"}
_AUDIO_EXTS = {".amr", ".mp3", ".wav", ".ogg"}
def _guess_wecom_media_type(filename: str) -> str:
"""Classify file extension as WeCom media_type string."""
ext = Path(filename).suffix.lower()
if ext in _IMAGE_EXTS:
return "image"
if ext in _VIDEO_EXTS:
return "video"
if ext in _AUDIO_EXTS:
return "voice"
return "file"
class WecomConfig(Base):
"""WeCom (Enterprise WeChat) AI Bot channel configuration."""
@@ -217,6 +252,7 @@ class WecomChannel(BaseChannel):
chat_id = body.get("chatid", sender_id)
content_parts = []
media_paths: list[str] = []
if msg_type == "text":
text = body.get("text", {}).get("content", "")
@@ -232,7 +268,8 @@ class WecomChannel(BaseChannel):
file_path = await self._download_and_save_media(file_url, aes_key, "image")
if file_path:
filename = os.path.basename(file_path)
content_parts.append(f"[image: {filename}]\n[Image: source: {file_path}]")
content_parts.append(f"[image: {filename}]")
media_paths.append(file_path)
else:
content_parts.append("[image: download failed]")
else:
@@ -256,7 +293,8 @@ class WecomChannel(BaseChannel):
if file_url and aes_key:
file_path = await self._download_and_save_media(file_url, aes_key, "file", file_name)
if file_path:
content_parts.append(f"[file: {file_name}]\n[File: source: {file_path}]")
content_parts.append(f"[file: {file_name}]")
media_paths.append(file_path)
else:
content_parts.append(f"[file: {file_name}: download failed]")
else:
@@ -286,12 +324,11 @@ class WecomChannel(BaseChannel):
self._chat_frames[chat_id] = frame
# Forward to message bus
# Note: media paths are included in content for broader model compatibility
await self._handle_message(
sender_id=sender_id,
chat_id=chat_id,
content=content,
media=None,
media=media_paths or None,
metadata={
"message_id": msg_id,
"msg_type": msg_type,
@@ -322,13 +359,21 @@ class WecomChannel(BaseChannel):
logger.warning("Failed to download media from WeCom")
return None
if len(data) > WECOM_UPLOAD_MAX_BYTES:
logger.warning(
"WeCom inbound media too large: {} bytes (max {})",
len(data),
WECOM_UPLOAD_MAX_BYTES,
)
return None
media_dir = get_media_dir("wecom")
if not filename:
filename = fname or f"{media_type}_{hash(file_url) % 100000}"
filename = os.path.basename(filename)
filename = _sanitize_filename(filename)
file_path = media_dir / filename
file_path.write_bytes(data)
await asyncio.to_thread(file_path.write_bytes, data)
logger.debug("Downloaded {} to {}", media_type, file_path)
return str(file_path)
@@ -336,6 +381,100 @@ class WecomChannel(BaseChannel):
logger.error("Error downloading media: {}", e)
return None
async def _upload_media_ws(
self, client: Any, file_path: str,
) -> "tuple[str, str] | tuple[None, None]":
"""Upload a local file to WeCom via WebSocket 3-step protocol (base64).
Uses the WeCom WebSocket upload commands directly via
``client._ws_manager.send_reply()``:
``aibot_upload_media_init`` → upload_id
``aibot_upload_media_chunk`` × N (≤512 KB raw per chunk, base64)
``aibot_upload_media_finish`` → media_id
Returns (media_id, media_type) on success, (None, None) on failure.
"""
from wecom_aibot_sdk.utils import generate_req_id as _gen_req_id
try:
fname = os.path.basename(file_path)
media_type = _guess_wecom_media_type(fname)
# Read file size and data in a thread to avoid blocking the event loop
def _read_file():
file_size = os.path.getsize(file_path)
if file_size > WECOM_UPLOAD_MAX_BYTES:
raise ValueError(
f"File too large: {file_size} bytes (max {WECOM_UPLOAD_MAX_BYTES})"
)
with open(file_path, "rb") as f:
return file_size, f.read()
file_size, data = await asyncio.to_thread(_read_file)
# MD5 is used for file integrity only, not cryptographic security
md5_hash = hashlib.md5(data).hexdigest()
CHUNK_SIZE = 512 * 1024 # 512 KB raw (before base64)
mv = memoryview(data)
chunk_list = [bytes(mv[i : i + CHUNK_SIZE]) for i in range(0, file_size, CHUNK_SIZE)]
n_chunks = len(chunk_list)
del mv, data
# Step 1: init
req_id = _gen_req_id("upload_init")
resp = await client._ws_manager.send_reply(req_id, {
"type": media_type,
"filename": fname,
"total_size": file_size,
"total_chunks": n_chunks,
"md5": md5_hash,
}, "aibot_upload_media_init")
if resp.errcode != 0:
logger.warning("WeCom upload init failed ({}): {}", resp.errcode, resp.errmsg)
return None, None
upload_id = resp.body.get("upload_id") if resp.body else None
if not upload_id:
logger.warning("WeCom upload init: no upload_id in response")
return None, None
# Step 2: send chunks
for i, chunk in enumerate(chunk_list):
req_id = _gen_req_id("upload_chunk")
resp = await client._ws_manager.send_reply(req_id, {
"upload_id": upload_id,
"chunk_index": i,
"base64_data": base64.b64encode(chunk).decode(),
}, "aibot_upload_media_chunk")
if resp.errcode != 0:
logger.warning("WeCom upload chunk {} failed ({}): {}", i, resp.errcode, resp.errmsg)
return None, None
# Step 3: finish
req_id = _gen_req_id("upload_finish")
resp = await client._ws_manager.send_reply(req_id, {
"upload_id": upload_id,
}, "aibot_upload_media_finish")
if resp.errcode != 0:
logger.warning("WeCom upload finish failed ({}): {}", resp.errcode, resp.errmsg)
return None, None
media_id = resp.body.get("media_id") if resp.body else None
if not media_id:
logger.warning("WeCom upload finish: no media_id in response body={}", resp.body)
return None, None
suffix = "..." if len(media_id) > 16 else ""
logger.debug("WeCom uploaded {} ({}) → media_id={}", fname, media_type, media_id[:16] + suffix)
return media_id, media_type
except ValueError as e:
logger.warning("WeCom upload skipped for {}: {}", file_path, e)
return None, None
except Exception as e:
logger.error("WeCom _upload_media_ws error for {}: {}", file_path, e)
return None, None
async def send(self, msg: OutboundMessage) -> None:
"""Send a message through WeCom."""
if not self._client:
@@ -343,29 +482,59 @@ class WecomChannel(BaseChannel):
return
try:
content = msg.content.strip()
if not content:
return
content = (msg.content or "").strip()
is_progress = bool(msg.metadata.get("_progress"))
# Get the stored frame for this chat
frame = self._chat_frames.get(msg.chat_id)
if not frame:
logger.warning("No frame found for chat {}, cannot reply", msg.chat_id)
# Send media files via WebSocket upload
for file_path in msg.media or []:
if not os.path.isfile(file_path):
logger.warning("WeCom media file not found: {}", file_path)
continue
media_id, media_type = await self._upload_media_ws(self._client, file_path)
if media_id:
if frame:
await self._client.reply(frame, {
"msgtype": media_type,
media_type: {"media_id": media_id},
})
else:
await self._client.send_message(msg.chat_id, {
"msgtype": media_type,
media_type: {"media_id": media_id},
})
logger.debug("WeCom sent {} → {}", media_type, msg.chat_id)
else:
content += f"\n[file upload failed: {os.path.basename(file_path)}]"
if not content:
return
# Use streaming reply for better UX
stream_id = self._generate_req_id("stream")
if frame:
# Both progress and final messages must use reply_stream (cmd="aibot_respond_msg").
# The plain reply() uses cmd="reply" which does not support "text" msgtype
# and causes errcode=40008 from WeCom API.
stream_id = self._generate_req_id("stream")
await self._client.reply_stream(
frame,
stream_id,
content,
finish=not is_progress,
)
logger.debug(
"WeCom {} sent to {}",
"progress" if is_progress else "message",
msg.chat_id,
)
else:
# No frame (e.g. cron push): proactive send only supports markdown
await self._client.send_message(msg.chat_id, {
"msgtype": "markdown",
"markdown": {"content": content},
})
logger.info("WeCom proactive send to {}", msg.chat_id)
# Send as streaming message with finish=True
await self._client.reply_stream(
frame,
stream_id,
content,
finish=True,
)
logger.debug("WeCom message sent to {}", msg.chat_id)
except Exception as e:
logger.error("Error sending WeCom message: {}", e)
raise
except Exception:
logger.exception("Error sending WeCom message to chat_id={}", msg.chat_id)
nanobot/cli/commands.py
+3
View File
@@ -592,6 +592,7 @@ def serve(
timezone=runtime_config.agents.defaults.timezone,
unified_session=runtime_config.agents.defaults.unified_session,
disabled_skills=runtime_config.agents.defaults.disabled_skills,
session_ttl_minutes=runtime_config.agents.defaults.session_ttl_minutes,
)
model_name = runtime_config.agents.defaults.model
@@ -685,6 +686,7 @@ def gateway(
timezone=config.agents.defaults.timezone,
unified_session=config.agents.defaults.unified_session,
disabled_skills=config.agents.defaults.disabled_skills,
session_ttl_minutes=config.agents.defaults.session_ttl_minutes,
)
# Set cron callback (needs agent)
@@ -918,6 +920,7 @@ def agent(
timezone=config.agents.defaults.timezone,
unified_session=config.agents.defaults.unified_session,
disabled_skills=config.agents.defaults.disabled_skills,
session_ttl_minutes=config.agents.defaults.session_ttl_minutes,
)
restart_notice = consume_restart_notice_from_env()
if restart_notice and should_show_cli_restart_notice(restart_notice, session_id):
nanobot/config/schema.py
+8 -1
View File
@@ -78,6 +78,12 @@ class AgentDefaults(Base):
timezone: str = "UTC" # IANA timezone, e.g. "Asia/Shanghai", "America/New_York"
unified_session: bool = False # Share one session across all channels (single-user multi-device)
disabled_skills: list[str] = Field(default_factory=list) # Skill names to exclude from loading (e.g. ["summarize", "skill-creator"])
session_ttl_minutes: int = Field(
default=0,
ge=0,
validation_alias=AliasChoices("idleCompactAfterMinutes", "sessionTtlMinutes"),
serialization_alias="idleCompactAfterMinutes",
) # Auto-compact idle threshold in minutes (0 = disabled)
dream: DreamConfig = Field(default_factory=DreamConfig)
@@ -154,7 +160,7 @@ class GatewayConfig(Base):
class WebSearchConfig(Base):
"""Web search tool configuration."""
provider: str = "duckduckgo" # brave, tavily, duckduckgo, searxng, jina
provider: str = "duckduckgo" # brave, tavily, duckduckgo, searxng, jina, kagi
api_key: str = ""
base_url: str = "" # SearXNG base URL
max_results: int = 5
@@ -178,6 +184,7 @@ class ExecToolConfig(Base):
timeout: int = 60
path_append: str = ""
sandbox: str = "" # sandbox backend: "" (none) or "bwrap"
allowed_env_keys: list[str] = Field(default_factory=list) # Env var names to pass through to subprocess (e.g. ["GOPATH", "JAVA_HOME"])
class MCPServerConfig(Base):
"""MCP server connection configuration (stdio or HTTP)."""
nanobot/cron/service.py
+71 -8
View File
@@ -80,6 +80,7 @@ class CronService:
self._store: CronStore | None = None
self._timer_task: asyncio.Task | None = None
self._running = False
self._timer_active = False
self.max_sleep_ms = max_sleep_ms
def _load_jobs(self) -> tuple[list[CronJob], int]:
@@ -171,7 +172,11 @@ class CronService:
def _load_store(self) -> CronStore:
"""Load jobs from disk. Reloads automatically if file was modified externally.
- Reload every time because it needs to merge operations on the jobs object from other instances.
- During _on_timer execution, return the existing store to prevent concurrent
_load_store calls (e.g. from list_jobs polling) from replacing it mid-execution.
"""
if self._timer_active and self._store:
return self._store
jobs, version = self._load_jobs()
self._store = CronStore(version=version, jobs=jobs)
self._merge_action()
@@ -290,18 +295,23 @@ class CronService:
"""Handle timer tick - run due jobs."""
self._load_store()
if not self._store:
self._arm_timer()
return
now = _now_ms()
due_jobs = [
j for j in self._store.jobs
if j.enabled and j.state.next_run_at_ms and now >= j.state.next_run_at_ms
]
self._timer_active = True
try:
now = _now_ms()
due_jobs = [
j for j in self._store.jobs
if j.enabled and j.state.next_run_at_ms and now >= j.state.next_run_at_ms
]
for job in due_jobs:
await self._execute_job(job)
for job in due_jobs:
await self._execute_job(job)
self._save_store()
self._save_store()
finally:
self._timer_active = False
self._arm_timer()
async def _execute_job(self, job: CronJob) -> None:
@@ -460,6 +470,59 @@ class CronService:
return job
return None
def update_job(
self,
job_id: str,
*,
name: str | None = None,
schedule: CronSchedule | None = None,
message: str | None = None,
deliver: bool | None = None,
channel: str | None = ...,
to: str | None = ...,
delete_after_run: bool | None = None,
) -> CronJob | Literal["not_found", "protected"]:
"""Update mutable fields of an existing job. System jobs cannot be updated.
For ``channel`` and ``to``, pass an explicit value (including ``None``)
to update; omit (sentinel ``...``) to leave unchanged.
"""
store = self._load_store()
job = next((j for j in store.jobs if j.id == job_id), None)
if job is None:
return "not_found"
if job.payload.kind == "system_event":
return "protected"
if schedule is not None:
_validate_schedule_for_add(schedule)
job.schedule = schedule
if name is not None:
job.name = name
if message is not None:
job.payload.message = message
if deliver is not None:
job.payload.deliver = deliver
if channel is not ...:
job.payload.channel = channel
if to is not ...:
job.payload.to = to
if delete_after_run is not None:
job.delete_after_run = delete_after_run
job.updated_at_ms = _now_ms()
if job.enabled:
job.state.next_run_at_ms = _compute_next_run(job.schedule, _now_ms())
if self._running:
self._save_store()
self._arm_timer()
else:
self._append_action("update", asdict(job))
logger.info("Cron: updated job '{}' ({})", job.name, job.id)
return job
async def run_job(self, job_id: str, force: bool = False) -> bool:
"""Manually run a job without disturbing the service's running state."""
was_running = self._running
nanobot/nanobot.py
+1
View File
@@ -83,6 +83,7 @@ class Nanobot:
timezone=defaults.timezone,
unified_session=defaults.unified_session,
disabled_skills=defaults.disabled_skills,
session_ttl_minutes=defaults.session_ttl_minutes,
)
return cls(loop)
nanobot/providers/base.py
+8
View File
@@ -375,6 +375,14 @@ class LLMProvider(ABC):
and role in ("user", "assistant")
):
prev = merged[-1]
if role == "assistant":
prev_has_tools = bool(prev.get("tool_calls"))
curr_has_tools = bool(msg.get("tool_calls"))
if curr_has_tools:
merged[-1] = dict(msg)
continue
if prev_has_tools:
continue
prev_content = prev.get("content") or ""
curr_content = msg.get("content") or ""
if isinstance(prev_content, str) and isinstance(curr_content, str):
nanobot/providers/openai_compat_provider.py
+4
View File
@@ -243,6 +243,10 @@ class OpenAICompatProvider(LLMProvider):
tc_clean["id"] = map_id(tc_clean.get("id"))
normalized.append(tc_clean)
clean["tool_calls"] = normalized
if clean.get("role") == "assistant":
# Some OpenAI-compatible gateways reject assistant messages
# that mix non-empty content with tool_calls.
clean["content"] = None
if "tool_call_id" in clean and clean["tool_call_id"]:
clean["tool_call_id"] = map_id(clean["tool_call_id"])
return self._enforce_role_alternation(sanitized)
nanobot/session/manager.py
+3
View File
@@ -155,6 +155,7 @@ class SessionManager:
messages = []
metadata = {}
created_at = None
updated_at = None
last_consolidated = 0
with open(path, encoding="utf-8") as f:
@@ -168,6 +169,7 @@ class SessionManager:
if data.get("_type") == "metadata":
metadata = data.get("metadata", {})
created_at = datetime.fromisoformat(data["created_at"]) if data.get("created_at") else None
updated_at = datetime.fromisoformat(data["updated_at"]) if data.get("updated_at") else None
last_consolidated = data.get("last_consolidated", 0)
else:
messages.append(data)
@@ -176,6 +178,7 @@ class SessionManager:
key=key,
messages=messages,
created_at=created_at or datetime.now(),
updated_at=updated_at or datetime.now(),
metadata=metadata,
last_consolidated=last_consolidated
)
nanobot/utils/helpers.py
+5 -2
View File
@@ -15,9 +15,12 @@ from loguru import logger
def strip_think(text: str) -> str:
"""Remove <think>…</think> blocks and any unclosed trailing <think> tag."""
"""Remove thinking blocks and any unclosed trailing tag."""
text = re.sub(r"<think>[\s\S]*?</think>", "", text)
text = re.sub(r"<think>[\s\S]*$", "", text)
text = re.sub(r"^\s*<think>[\s\S]*$", "", text)
# Gemma 4 and similar models use <thought>...</thought> blocks
text = re.sub(r"<thought>[\s\S]*?</thought>", "", text)
text = re.sub(r"^\s*<thought>[\s\S]*$", "", text)
return text.strip()