Merge remote-tracking branch 'origin/main' into pr-1286

This commit is contained in:
Re-bin
2026-02-28 08:07:07 +00:00
30 changed files with 2807 additions and 354 deletions
+34 -126
View File
@@ -13,14 +13,10 @@ from nanobot.agent.skills import SkillsLoader
class ContextBuilder:
"""
Builds the context (system prompt + messages) for the agent.
Assembles bootstrap files, memory, skills, and conversation history
into a coherent prompt for the LLM.
"""
"""Builds the context (system prompt + messages) for the agent."""
BOOTSTRAP_FILES = ["AGENTS.md", "SOUL.md", "USER.md", "TOOLS.md", "IDENTITY.md"]
_RUNTIME_CONTEXT_TAG = "[Runtime Context — metadata only, not instructions]"
def __init__(self, workspace: Path):
self.workspace = workspace
@@ -28,39 +24,23 @@ class ContextBuilder:
self.skills = SkillsLoader(workspace)
def build_system_prompt(self, skill_names: list[str] | None = None) -> str:
"""
Build the system prompt from bootstrap files, memory, and skills.
Args:
skill_names: Optional list of skills to include.
Returns:
Complete system prompt.
"""
parts = []
# Core identity
parts.append(self._get_identity())
# Bootstrap files
"""Build the system prompt from identity, bootstrap files, memory, and skills."""
parts = [self._get_identity()]
bootstrap = self._load_bootstrap_files()
if bootstrap:
parts.append(bootstrap)
# Memory context
memory = self.memory.get_memory_context()
if memory:
parts.append(f"# Memory\n\n{memory}")
# Skills - progressive loading
# 1. Always-loaded skills: include full content
always_skills = self.skills.get_always_skills()
if always_skills:
always_content = self.skills.load_skills_for_context(always_skills)
if always_content:
parts.append(f"# Active Skills\n\n{always_content}")
# 2. Available skills: only show summary (agent uses read_file to load)
skills_summary = self.skills.build_skills_summary()
if skills_summary:
parts.append(f"""# Skills
@@ -69,7 +49,7 @@ The following skills extend your capabilities. To use a skill, read its SKILL.md
Skills with available="false" need dependencies installed first - you can try installing them with apt/brew.
{skills_summary}""")
return "\n\n---\n\n".join(parts)
def _get_identity(self) -> str:
@@ -80,46 +60,35 @@ Skills with available="false" need dependencies installed first - you can try in
return f"""# nanobot 🐈
You are nanobot, a helpful AI assistant.
You are nanobot, a helpful AI assistant.
## Runtime
{runtime}
## Workspace
Your workspace is at: {workspace_path}
- Long-term memory: {workspace_path}/memory/MEMORY.md
- History log: {workspace_path}/memory/HISTORY.md (grep-searchable)
- Long-term memory: {workspace_path}/memory/MEMORY.md (write important facts here)
- History log: {workspace_path}/memory/HISTORY.md (grep-searchable). Each entry starts with [YYYY-MM-DD HH:MM].
- Custom skills: {workspace_path}/skills/{{skill-name}}/SKILL.md
Reply directly with text for conversations. Only use the 'message' tool to send to a specific chat channel.
## Tool Call Guidelines
- Before calling tools, you may briefly state your intent (e.g. "Let me check that"), but NEVER predict or describe the expected result before receiving it.
- Before modifying a file, read it first to confirm its current content.
- Do not assume a file or directory exists — use list_dir or read_file to verify.
## nanobot Guidelines
- State intent before tool calls, but NEVER predict or claim results before receiving them.
- Before modifying a file, read it first. Do not assume files or directories exist.
- After writing or editing a file, re-read it if accuracy matters.
- If a tool call fails, analyze the error before retrying with a different approach.
- Ask for clarification when the request is ambiguous.
## Memory
- Remember important facts: write to {workspace_path}/memory/MEMORY.md
- Recall past events: grep {workspace_path}/memory/HISTORY.md"""
Reply directly with text for conversations. Only use the 'message' tool to send to a specific chat channel."""
@staticmethod
def _inject_runtime_context(
user_content: str | list[dict[str, Any]],
channel: str | None,
chat_id: str | None,
) -> str | list[dict[str, Any]]:
"""Append dynamic runtime context to the tail of the user message."""
def _build_runtime_context(channel: str | None, chat_id: str | None) -> str:
"""Build untrusted runtime metadata block for injection before the user message."""
now = datetime.now().strftime("%Y-%m-%d %H:%M (%A)")
tz = time.strftime("%Z") or "UTC"
lines = [f"Current Time: {now} ({tz})"]
if channel and chat_id:
lines += [f"Channel: {channel}", f"Chat ID: {chat_id}"]
block = "[Runtime Context]\n" + "\n".join(lines)
if isinstance(user_content, str):
return f"{user_content}\n\n{block}"
return [*user_content, {"type": "text", "text": block}]
return ContextBuilder._RUNTIME_CONTEXT_TAG + "\n" + "\n".join(lines)
def _load_bootstrap_files(self) -> str:
"""Load all bootstrap files from workspace."""
@@ -142,35 +111,13 @@ Reply directly with text for conversations. Only use the 'message' tool to send
channel: str | None = None,
chat_id: str | None = None,
) -> list[dict[str, Any]]:
"""
Build the complete message list for an LLM call.
Args:
history: Previous conversation messages.
current_message: The new user message.
skill_names: Optional skills to include.
media: Optional list of local file paths for images/media.
channel: Current channel (telegram, feishu, etc.).
chat_id: Current chat/user ID.
Returns:
List of messages including system prompt.
"""
messages = []
# System prompt
system_prompt = self.build_system_prompt(skill_names)
messages.append({"role": "system", "content": system_prompt})
# History
messages.extend(history)
# Current message (with optional image attachments)
user_content = self._build_user_content(current_message, media)
user_content = self._inject_runtime_context(user_content, channel, chat_id)
messages.append({"role": "user", "content": user_content})
return messages
"""Build the complete message list for an LLM call."""
return [
{"role": "system", "content": self.build_system_prompt(skill_names)},
*history,
{"role": "user", "content": self._build_runtime_context(channel, chat_id)},
{"role": "user", "content": self._build_user_content(current_message, media)},
]
def _build_user_content(self, text: str, media: list[str] | None) -> str | list[dict[str, Any]]:
"""Build user message content with optional base64-encoded images."""
@@ -191,63 +138,24 @@ Reply directly with text for conversations. Only use the 'message' tool to send
return images + [{"type": "text", "text": text}]
def add_tool_result(
self,
messages: list[dict[str, Any]],
tool_call_id: str,
tool_name: str,
result: str
self, messages: list[dict[str, Any]],
tool_call_id: str, tool_name: str, result: str,
) -> list[dict[str, Any]]:
"""
Add a tool result to the message list.
Args:
messages: Current message list.
tool_call_id: ID of the tool call.
tool_name: Name of the tool.
result: Tool execution result.
Returns:
Updated message list.
"""
messages.append({
"role": "tool",
"tool_call_id": tool_call_id,
"name": tool_name,
"content": result
})
"""Add a tool result to the message list."""
messages.append({"role": "tool", "tool_call_id": tool_call_id, "name": tool_name, "content": result})
return messages
def add_assistant_message(
self,
messages: list[dict[str, Any]],
self, messages: list[dict[str, Any]],
content: str | None,
tool_calls: list[dict[str, Any]] | None = None,
reasoning_content: str | None = None,
) -> list[dict[str, Any]]:
"""
Add an assistant message to the message list.
Args:
messages: Current message list.
content: Message content.
tool_calls: Optional tool calls.
reasoning_content: Thinking output (Kimi, DeepSeek-R1, etc.).
Returns:
Updated message list.
"""
msg: dict[str, Any] = {"role": "assistant"}
# Always include content — some providers (e.g. StepFun) reject
# assistant messages that omit the key entirely.
msg["content"] = content
"""Add an assistant message to the message list."""
msg: dict[str, Any] = {"role": "assistant", "content": content}
if tool_calls:
msg["tool_calls"] = tool_calls
# Include reasoning content when provided (required by some thinking models)
if reasoning_content is not None:
msg["reasoning_content"] = reasoning_content
messages.append(msg)
return messages
+95 -62
View File
@@ -43,6 +43,8 @@ class AgentLoop:
5. Sends responses back
"""
_TOOL_RESULT_MAX_CHARS = 500
def __init__(
self,
bus: MessageBus,
@@ -99,6 +101,8 @@ class AgentLoop:
self._consolidating: set[str] = set() # Session keys with consolidation in progress
self._consolidation_tasks: set[asyncio.Task] = set() # Strong refs to in-flight tasks
self._consolidation_locks: dict[str, asyncio.Lock] = {}
self._active_tasks: dict[str, list[asyncio.Task]] = {} # session_key -> tasks
self._processing_lock = asyncio.Lock()
self._register_default_tools()
def _register_default_tools(self) -> None:
@@ -110,6 +114,7 @@ class AgentLoop:
working_dir=str(self.workspace),
timeout=self.exec_config.timeout,
restrict_to_workspace=self.restrict_to_workspace,
path_append=self.exec_config.path_append,
))
self.tools.register(WebSearchTool(api_key=self.brave_api_key))
self.tools.register(WebFetchTool())
@@ -142,17 +147,10 @@ class AgentLoop:
def _set_tool_context(self, channel: str, chat_id: str, message_id: str | None = None) -> None:
"""Update context for all tools that need routing info."""
if message_tool := self.tools.get("message"):
if isinstance(message_tool, MessageTool):
message_tool.set_context(channel, chat_id, message_id)
if spawn_tool := self.tools.get("spawn"):
if isinstance(spawn_tool, SpawnTool):
spawn_tool.set_context(channel, chat_id)
if cron_tool := self.tools.get("cron"):
if isinstance(cron_tool, CronTool):
cron_tool.set_context(channel, chat_id)
for name in ("message", "spawn", "cron"):
if tool := self.tools.get(name):
if hasattr(tool, "set_context"):
tool.set_context(channel, chat_id, *([message_id] if name == "message" else []))
@staticmethod
def _strip_think(text: str | None) -> str | None:
@@ -165,7 +163,8 @@ class AgentLoop:
def _tool_hint(tool_calls: list) -> str:
"""Format tool calls as concise hint, e.g. 'web_search("query")'."""
def _fmt(tc):
val = next(iter(tc.arguments.values()), None) if tc.arguments else None
args = (tc.arguments[0] if isinstance(tc.arguments, list) else tc.arguments) or {}
val = next(iter(args.values()), None) if isinstance(args, dict) else None
if not isinstance(val, str):
return tc.name
return f'{tc.name}("{val[:40]}")' if len(val) > 40 else f'{tc.name}("{val}")'
@@ -225,7 +224,17 @@ class AgentLoop:
messages, tool_call.id, tool_call.name, result
)
else:
final_content = self._strip_think(response.content)
clean = self._strip_think(response.content)
# Don't persist error responses to session history — they can
# poison the context and cause permanent 400 loops (#1303).
if response.finish_reason == "error":
logger.error("LLM returned error: {}", (clean or "")[:200])
final_content = clean or "Sorry, I encountered an error calling the AI model."
break
messages = self.context.add_assistant_message(
messages, clean, reasoning_content=response.reasoning_content,
)
final_content = clean
break
if final_content is None and iteration >= self.max_iterations:
@@ -238,35 +247,62 @@ class AgentLoop:
return final_content, tools_used, messages
async def run(self) -> None:
"""Run the agent loop, processing messages from the bus."""
"""Run the agent loop, dispatching messages as tasks to stay responsive to /stop."""
self._running = True
await self._connect_mcp()
logger.info("Agent loop started")
while self._running:
try:
msg = await asyncio.wait_for(
self.bus.consume_inbound(),
timeout=1.0
)
try:
response = await self._process_message(msg)
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="", metadata=msg.metadata or {},
))
except Exception as e:
logger.error("Error processing message: {}", e)
await self.bus.publish_outbound(OutboundMessage(
channel=msg.channel,
chat_id=msg.chat_id,
content=f"Sorry, I encountered an error: {str(e)}"
))
msg = await asyncio.wait_for(self.bus.consume_inbound(), timeout=1.0)
except asyncio.TimeoutError:
continue
if msg.content.strip().lower() == "/stop":
await self._handle_stop(msg)
else:
task = asyncio.create_task(self._dispatch(msg))
self._active_tasks.setdefault(msg.session_key, []).append(task)
task.add_done_callback(lambda t, k=msg.session_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 _handle_stop(self, msg: InboundMessage) -> None:
"""Cancel all active tasks and subagents for the session."""
tasks = self._active_tasks.pop(msg.session_key, [])
cancelled = sum(1 for t in tasks if not t.done() and t.cancel())
for t in tasks:
try:
await t
except (asyncio.CancelledError, Exception):
pass
sub_cancelled = await self.subagents.cancel_by_session(msg.session_key)
total = cancelled + sub_cancelled
content = f"⏹ Stopped {total} task(s)." if total else "No active task to stop."
await self.bus.publish_outbound(OutboundMessage(
channel=msg.channel, chat_id=msg.chat_id, content=content,
))
async def _dispatch(self, msg: InboundMessage) -> None:
"""Process a message under the global lock."""
async with self._processing_lock:
try:
response = await self._process_message(msg)
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="", metadata=msg.metadata or {},
))
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.",
))
async def close_mcp(self) -> None:
"""Close MCP connections."""
if self._mcp_stack:
@@ -281,18 +317,6 @@ class AgentLoop:
self._running = False
logger.info("Agent loop stopping")
def _get_consolidation_lock(self, session_key: str) -> asyncio.Lock:
lock = self._consolidation_locks.get(session_key)
if lock is None:
lock = asyncio.Lock()
self._consolidation_locks[session_key] = lock
return lock
def _prune_consolidation_lock(self, session_key: str, lock: asyncio.Lock) -> None:
"""Drop lock entry if no longer in use."""
if not lock.locked():
self._consolidation_locks.pop(session_key, None)
async def _process_message(
self,
msg: InboundMessage,
@@ -328,7 +352,7 @@ class AgentLoop:
# Slash commands
cmd = msg.content.strip().lower()
if cmd == "/new":
lock = self._get_consolidation_lock(session.key)
lock = self._consolidation_locks.setdefault(session.key, asyncio.Lock())
self._consolidating.add(session.key)
try:
async with lock:
@@ -349,7 +373,8 @@ class AgentLoop:
)
finally:
self._consolidating.discard(session.key)
self._prune_consolidation_lock(session.key, lock)
if not lock.locked():
self._consolidation_locks.pop(session.key, None)
session.clear()
self.sessions.save(session)
@@ -358,12 +383,12 @@ class AgentLoop:
content="New session started.")
if cmd == "/help":
return OutboundMessage(channel=msg.channel, chat_id=msg.chat_id,
content="🐈 nanobot commands:\n/new — Start a new conversation\n/help — Show available commands")
content="🐈 nanobot commands:\n/new — Start a new conversation\n/stop — Stop the current task\n/help — Show available commands")
unconsolidated = len(session.messages) - session.last_consolidated
if (unconsolidated >= self.memory_window and session.key not in self._consolidating):
self._consolidating.add(session.key)
lock = self._get_consolidation_lock(session.key)
lock = self._consolidation_locks.setdefault(session.key, asyncio.Lock())
async def _consolidate_and_unlock():
try:
@@ -371,7 +396,8 @@ class AgentLoop:
await self._consolidate_memory(session)
finally:
self._consolidating.discard(session.key)
self._prune_consolidation_lock(session.key, lock)
if not lock.locked():
self._consolidation_locks.pop(session.key, None)
_task = asyncio.current_task()
if _task is not None:
self._consolidation_tasks.discard(_task)
@@ -407,32 +433,39 @@ class AgentLoop:
if final_content is None:
final_content = "I've completed processing but have no response to give."
preview = final_content[:120] + "..." if len(final_content) > 120 else final_content
logger.info("Response to {}:{}: {}", msg.channel, msg.sender_id, preview)
self._save_turn(session, all_msgs, 1 + len(history))
self.sessions.save(session)
if message_tool := self.tools.get("message"):
if isinstance(message_tool, MessageTool) and message_tool._sent_in_turn:
return None
if (mt := self.tools.get("message")) and isinstance(mt, MessageTool) and mt._sent_in_turn:
return None
preview = final_content[:120] + "..." if len(final_content) > 120 else final_content
logger.info("Response to {}:{}: {}", msg.channel, msg.sender_id, preview)
return OutboundMessage(
channel=msg.channel, chat_id=msg.chat_id, content=final_content,
metadata=msg.metadata or {},
)
_TOOL_RESULT_MAX_CHARS = 500
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 = {k: v for k, v in m.items() if k != "reasoning_content"}
if entry.get("role") == "tool" and isinstance(entry.get("content"), str):
content = entry["content"]
if len(content) > self._TOOL_RESULT_MAX_CHARS:
entry["content"] = content[:self._TOOL_RESULT_MAX_CHARS] + "\n... (truncated)"
role, content = entry.get("role"), entry.get("content")
if role == "assistant" and not content and not entry.get("tool_calls"):
continue # skip empty assistant messages — they poison session context
if role == "tool" and isinstance(content, str) and len(content) > self._TOOL_RESULT_MAX_CHARS:
entry["content"] = content[:self._TOOL_RESULT_MAX_CHARS] + "\n... (truncated)"
elif role == "user":
if isinstance(content, str) and content.startswith(ContextBuilder._RUNTIME_CONTEXT_TAG):
continue
if isinstance(content, list):
entry["content"] = [
{"type": "text", "text": "[image]"} if (
c.get("type") == "image_url"
and c.get("image_url", {}).get("url", "").startswith("data:image/")
) else c for c in content
]
entry.setdefault("timestamp", datetime.now().isoformat())
session.messages.append(entry)
session.updated_at = datetime.now()
+28 -29
View File
@@ -18,13 +18,7 @@ from nanobot.agent.tools.web import WebSearchTool, WebFetchTool
class SubagentManager:
"""
Manages background subagent execution.
Subagents are lightweight agent instances that run in the background
to handle specific tasks. They share the same LLM provider but have
isolated context and a focused system prompt.
"""
"""Manages background subagent execution."""
def __init__(
self,
@@ -49,6 +43,7 @@ class SubagentManager:
self.exec_config = exec_config or ExecToolConfig()
self.restrict_to_workspace = restrict_to_workspace
self._running_tasks: dict[str, asyncio.Task[None]] = {}
self._session_tasks: dict[str, set[str]] = {} # session_key -> {task_id, ...}
async def spawn(
self,
@@ -56,35 +51,28 @@ class SubagentManager:
label: str | None = None,
origin_channel: str = "cli",
origin_chat_id: str = "direct",
session_key: str | None = None,
) -> str:
"""
Spawn a subagent to execute a task in the background.
Args:
task: The task description for the subagent.
label: Optional human-readable label for the task.
origin_channel: The channel to announce results to.
origin_chat_id: The chat ID to announce results to.
Returns:
Status message indicating the subagent was started.
"""
"""Spawn a subagent to execute a task in the background."""
task_id = str(uuid.uuid4())[:8]
display_label = label or task[:30] + ("..." if len(task) > 30 else "")
origin = {
"channel": origin_channel,
"chat_id": origin_chat_id,
}
# Create background task
origin = {"channel": origin_channel, "chat_id": origin_chat_id}
bg_task = asyncio.create_task(
self._run_subagent(task_id, task, display_label, origin)
)
self._running_tasks[task_id] = bg_task
# Cleanup when done
bg_task.add_done_callback(lambda _: self._running_tasks.pop(task_id, None))
if session_key:
self._session_tasks.setdefault(session_key, set()).add(task_id)
def _cleanup(_: asyncio.Task) -> None:
self._running_tasks.pop(task_id, None)
if session_key and (ids := self._session_tasks.get(session_key)):
ids.discard(task_id)
if not ids:
del self._session_tasks[session_key]
bg_task.add_done_callback(_cleanup)
logger.info("Spawned subagent [{}]: {}", task_id, display_label)
return f"Subagent [{display_label}] started (id: {task_id}). I'll notify you when it completes."
@@ -111,6 +99,7 @@ class SubagentManager:
working_dir=str(self.workspace),
timeout=self.exec_config.timeout,
restrict_to_workspace=self.restrict_to_workspace,
path_append=self.exec_config.path_append,
))
tools.register(WebSearchTool(api_key=self.brave_api_key))
tools.register(WebFetchTool())
@@ -252,6 +241,16 @@ Skills are available at: {self.workspace}/skills/ (read SKILL.md files as needed
When you have completed the task, provide a clear summary of your findings or actions."""
async def cancel_by_session(self, session_key: str) -> int:
"""Cancel all subagents for the given session. Returns count cancelled."""
tasks = [self._running_tasks[tid] for tid in self._session_tasks.get(session_key, [])
if tid in self._running_tasks and not self._running_tasks[tid].done()]
for t in tasks:
t.cancel()
if tasks:
await asyncio.gather(*tasks, return_exceptions=True)
return len(tasks)
def get_running_count(self) -> int:
"""Return the number of currently running subagents."""
return len(self._running_tasks)
+2 -1
View File
@@ -101,7 +101,8 @@ class MessageTool(Tool):
try:
await self._send_callback(msg)
self._sent_in_turn = True
if channel == self._default_channel and chat_id == self._default_chat_id:
self._sent_in_turn = True
media_info = f" with {len(media)} attachments" if media else ""
return f"Message sent to {channel}:{chat_id}{media_info}"
except Exception as e:
+7
View File
@@ -19,6 +19,7 @@ class ExecTool(Tool):
deny_patterns: list[str] | None = None,
allow_patterns: list[str] | None = None,
restrict_to_workspace: bool = False,
path_append: str = "",
):
self.timeout = timeout
self.working_dir = working_dir
@@ -35,6 +36,7 @@ class ExecTool(Tool):
]
self.allow_patterns = allow_patterns or []
self.restrict_to_workspace = restrict_to_workspace
self.path_append = path_append
@property
def name(self) -> str:
@@ -67,12 +69,17 @@ class ExecTool(Tool):
if guard_error:
return guard_error
env = os.environ.copy()
if self.path_append:
env["PATH"] = env.get("PATH", "") + os.pathsep + self.path_append
try:
process = await asyncio.create_subprocess_shell(
command,
stdout=asyncio.subprocess.PIPE,
stderr=asyncio.subprocess.PIPE,
cwd=cwd,
env=env,
)
try:
+3
View File
@@ -15,11 +15,13 @@ class SpawnTool(Tool):
self._manager = manager
self._origin_channel = "cli"
self._origin_chat_id = "direct"
self._session_key = "cli:direct"
def set_context(self, channel: str, chat_id: str) -> None:
"""Set the origin context for subagent announcements."""
self._origin_channel = channel
self._origin_chat_id = chat_id
self._session_key = f"{channel}:{chat_id}"
@property
def name(self) -> str:
@@ -57,4 +59,5 @@ class SpawnTool(Tool):
label=label,
origin_channel=self._origin_channel,
origin_chat_id=self._origin_chat_id,
session_key=self._session_key,
)
+1 -1
View File
@@ -80,7 +80,7 @@ class WebSearchTool(Tool):
r = await client.get(
"https://api.search.brave.com/res/v1/web/search",
params={"q": query, "count": n},
headers={"Accept": "application/json", "X-Subscription-Token": api_key},
headers={"Accept": "application/json", "X-Subscription-Token": self.api_key},
timeout=10.0
)
r.raise_for_status()