Merge branch 'main' into pr-1751

Made-with: Cursor

# Conflicts:
#	nanobot/agent/loop.py
This commit is contained in:
Re-bin
2026-03-12 03:53:59 +00:00
55 changed files with 3774 additions and 860 deletions
+7 -9
View File
@@ -10,7 +10,7 @@ from typing import Any
from nanobot.agent.memory import MemoryStore
from nanobot.agent.skills import SkillsLoader
from nanobot.utils.helpers import detect_image_mime
from nanobot.utils.helpers import build_assistant_message, detect_image_mime
class ContextBuilder:
@@ -182,12 +182,10 @@ Reply directly with text for conversations. Only use the 'message' tool to send
thinking_blocks: list[dict] | None = None,
) -> list[dict[str, Any]]:
"""Add an assistant message to the message list."""
msg: dict[str, Any] = {"role": "assistant", "content": content}
if tool_calls:
msg["tool_calls"] = tool_calls
if reasoning_content is not None:
msg["reasoning_content"] = reasoning_content
if thinking_blocks:
msg["thinking_blocks"] = thinking_blocks
messages.append(msg)
messages.append(build_assistant_message(
content,
tool_calls=tool_calls,
reasoning_content=reasoning_content,
thinking_blocks=thinking_blocks,
))
return messages
+33 -72
View File
@@ -7,7 +7,6 @@ import json
import re
import os
import sys
import weakref
from contextlib import AsyncExitStack
from pathlib import Path
from typing import TYPE_CHECKING, Any, Awaitable, Callable
@@ -15,7 +14,7 @@ from typing import TYPE_CHECKING, Any, Awaitable, Callable
from loguru import logger
from nanobot.agent.context import ContextBuilder
from nanobot.agent.memory import MemoryStore
from nanobot.agent.memory import MemoryConsolidator
from nanobot.agent.subagent import SubagentManager
from nanobot.agent.tools.cron import CronTool
from nanobot.agent.tools.filesystem import EditFileTool, ListDirTool, ReadFileTool, WriteFileTool
@@ -46,7 +45,7 @@ class AgentLoop:
5. Sends responses back
"""
_TOOL_RESULT_MAX_CHARS = 500
_TOOL_RESULT_MAX_CHARS = 16_000
def __init__(
self,
@@ -55,10 +54,7 @@ class AgentLoop:
workspace: Path,
model: str | None = None,
max_iterations: int = 40,
temperature: float = 0.1,
max_tokens: int = 4096,
memory_window: int = 100,
reasoning_effort: str | None = None,
context_window_tokens: int = 65_536,
brave_api_key: str | None = None,
web_proxy: str | None = None,
exec_config: ExecToolConfig | None = None,
@@ -75,10 +71,7 @@ class AgentLoop:
self.workspace = workspace
self.model = model or provider.get_default_model()
self.max_iterations = max_iterations
self.temperature = temperature
self.max_tokens = max_tokens
self.memory_window = memory_window
self.reasoning_effort = reasoning_effort
self.context_window_tokens = context_window_tokens
self.brave_api_key = brave_api_key
self.web_proxy = web_proxy
self.exec_config = exec_config or ExecToolConfig()
@@ -93,9 +86,6 @@ class AgentLoop:
workspace=workspace,
bus=bus,
model=self.model,
temperature=self.temperature,
max_tokens=self.max_tokens,
reasoning_effort=reasoning_effort,
brave_api_key=brave_api_key,
web_proxy=web_proxy,
exec_config=self.exec_config,
@@ -107,11 +97,17 @@ class AgentLoop:
self._mcp_stack: AsyncExitStack | None = None
self._mcp_connected = False
self._mcp_connecting = False
self._consolidating: set[str] = set() # Session keys with consolidation in progress
self._consolidation_tasks: set[asyncio.Task] = set() # Strong refs to in-flight tasks
self._consolidation_locks: weakref.WeakValueDictionary[str, asyncio.Lock] = weakref.WeakValueDictionary()
self._active_tasks: dict[str, list[asyncio.Task]] = {} # session_key -> tasks
self._processing_lock = asyncio.Lock()
self.memory_consolidator = MemoryConsolidator(
workspace=workspace,
provider=provider,
model=self.model,
sessions=self.sessions,
context_window_tokens=context_window_tokens,
build_messages=self.context.build_messages,
get_tool_definitions=self.tools.get_definitions,
)
self._register_default_tools()
def _register_default_tools(self) -> None:
@@ -184,7 +180,7 @@ class AgentLoop:
initial_messages: list[dict],
on_progress: Callable[..., Awaitable[None]] | None = None,
) -> tuple[str | None, list[str], list[dict]]:
"""Run the agent iteration loop. Returns (final_content, tools_used, messages)."""
"""Run the agent iteration loop."""
messages = initial_messages
iteration = 0
final_content = None
@@ -193,13 +189,12 @@ class AgentLoop:
while iteration < self.max_iterations:
iteration += 1
response = await self.provider.chat(
tool_defs = self.tools.get_definitions()
response = await self.provider.chat_with_retry(
messages=messages,
tools=self.tools.get_definitions(),
tools=tool_defs,
model=self.model,
temperature=self.temperature,
max_tokens=self.max_tokens,
reasoning_effort=self.reasoning_effort,
)
if response.has_tool_calls:
@@ -210,14 +205,7 @@ class AgentLoop:
await on_progress(self._tool_hint(response.tool_calls), tool_hint=True)
tool_call_dicts = [
{
"id": tc.id,
"type": "function",
"function": {
"name": tc.name,
"arguments": json.dumps(tc.arguments, ensure_ascii=False)
}
}
tc.to_openai_tool_call()
for tc in response.tool_calls
]
messages = self.context.add_assistant_message(
@@ -343,8 +331,9 @@ class AgentLoop:
logger.info("Processing system message from {}", msg.sender_id)
key = f"{channel}:{chat_id}"
session = self.sessions.get_or_create(key)
await self.memory_consolidator.maybe_consolidate_by_tokens(session)
self._set_tool_context(channel, chat_id, msg.metadata.get("message_id"))
history = session.get_history(max_messages=self.memory_window)
history = session.get_history(max_messages=0)
messages = self.context.build_messages(
history=history,
current_message=msg.content, channel=channel, chat_id=chat_id,
@@ -352,6 +341,7 @@ class AgentLoop:
final_content, _, all_msgs = await self._run_agent_loop(messages)
self._save_turn(session, all_msgs, 1 + len(history))
self.sessions.save(session)
await self.memory_consolidator.maybe_consolidate_by_tokens(session)
return OutboundMessage(channel=channel, chat_id=chat_id,
content=final_content or "Background task completed.")
@@ -364,27 +354,20 @@ class AgentLoop:
# Slash commands
cmd = msg.content.strip().lower()
if cmd == "/new":
lock = self._consolidation_locks.setdefault(session.key, asyncio.Lock())
self._consolidating.add(session.key)
try:
async with lock:
snapshot = session.messages[session.last_consolidated:]
if snapshot:
temp = Session(key=session.key)
temp.messages = list(snapshot)
if not await self._consolidate_memory(temp, archive_all=True):
return OutboundMessage(
channel=msg.channel, chat_id=msg.chat_id,
content="Memory archival failed, session not cleared. Please try again.",
)
if not await self.memory_consolidator.archive_unconsolidated(session):
return OutboundMessage(
channel=msg.channel,
chat_id=msg.chat_id,
content="Memory archival failed, session not cleared. Please try again.",
)
except Exception:
logger.exception("/new archival failed for {}", session.key)
return OutboundMessage(
channel=msg.channel, chat_id=msg.chat_id,
channel=msg.channel,
chat_id=msg.chat_id,
content="Memory archival failed, session not cleared. Please try again.",
)
finally:
self._consolidating.discard(session.key)
session.clear()
self.sessions.save(session)
@@ -404,30 +387,14 @@ class AgentLoop:
asyncio.create_task(_r())
return None
unconsolidated = len(session.messages) - session.last_consolidated
if (unconsolidated >= self.memory_window and session.key not in self._consolidating):
self._consolidating.add(session.key)
lock = self._consolidation_locks.setdefault(session.key, asyncio.Lock())
async def _consolidate_and_unlock():
try:
async with lock:
await self._consolidate_memory(session)
finally:
self._consolidating.discard(session.key)
_task = asyncio.current_task()
if _task is not None:
self._consolidation_tasks.discard(_task)
_task = asyncio.create_task(_consolidate_and_unlock())
self._consolidation_tasks.add(_task)
await self.memory_consolidator.maybe_consolidate_by_tokens(session)
self._set_tool_context(msg.channel, msg.chat_id, msg.metadata.get("message_id"))
if message_tool := self.tools.get("message"):
if isinstance(message_tool, MessageTool):
message_tool.start_turn()
history = session.get_history(max_messages=self.memory_window)
history = session.get_history(max_messages=0)
initial_messages = self.context.build_messages(
history=history,
current_message=msg.content,
@@ -452,6 +419,7 @@ class AgentLoop:
self._save_turn(session, all_msgs, 1 + len(history))
self.sessions.save(session)
await self.memory_consolidator.maybe_consolidate_by_tokens(session)
if (mt := self.tools.get("message")) and isinstance(mt, MessageTool) and mt._sent_in_turn:
return None
@@ -498,13 +466,6 @@ class AgentLoop:
session.messages.append(entry)
session.updated_at = datetime.now()
async def _consolidate_memory(self, session, archive_all: bool = False) -> bool:
"""Delegate to MemoryStore.consolidate(). Returns True on success."""
return await MemoryStore(self.workspace).consolidate(
session, self.provider, self.model,
archive_all=archive_all, memory_window=self.memory_window,
)
async def process_direct(
self,
content: str,
+182 -55
View File
@@ -2,17 +2,19 @@
from __future__ import annotations
import asyncio
import json
import weakref
from pathlib import Path
from typing import TYPE_CHECKING
from typing import TYPE_CHECKING, Any, Callable
from loguru import logger
from nanobot.utils.helpers import ensure_dir
from nanobot.utils.helpers import ensure_dir, estimate_message_tokens, estimate_prompt_tokens_chain
if TYPE_CHECKING:
from nanobot.providers.base import LLMProvider
from nanobot.session.manager import Session
from nanobot.session.manager import Session, SessionManager
_SAVE_MEMORY_TOOL = [
@@ -26,7 +28,7 @@ _SAVE_MEMORY_TOOL = [
"properties": {
"history_entry": {
"type": "string",
"description": "A paragraph (2-5 sentences) summarizing key events/decisions/topics. "
"description": "A paragraph summarizing key events/decisions/topics. "
"Start with [YYYY-MM-DD HH:MM]. Include detail useful for grep search.",
},
"memory_update": {
@@ -42,6 +44,19 @@ _SAVE_MEMORY_TOOL = [
]
def _ensure_text(value: Any) -> str:
"""Normalize tool-call payload values to text for file storage."""
return value if isinstance(value, str) else json.dumps(value, ensure_ascii=False)
def _normalize_save_memory_args(args: Any) -> dict[str, Any] | None:
"""Normalize provider tool-call arguments to the expected dict shape."""
if isinstance(args, str):
args = json.loads(args)
if isinstance(args, list):
return args[0] if args and isinstance(args[0], dict) else None
return args if isinstance(args, dict) else None
class MemoryStore:
"""Two-layer memory: MEMORY.md (long-term facts) + HISTORY.md (grep-searchable log)."""
@@ -66,40 +81,27 @@ class MemoryStore:
long_term = self.read_long_term()
return f"## Long-term Memory\n{long_term}" if long_term else ""
@staticmethod
def _format_messages(messages: list[dict]) -> str:
lines = []
for message in messages:
if not message.get("content"):
continue
tools = f" [tools: {', '.join(message['tools_used'])}]" if message.get("tools_used") else ""
lines.append(
f"[{message.get('timestamp', '?')[:16]}] {message['role'].upper()}{tools}: {message['content']}"
)
return "\n".join(lines)
async def consolidate(
self,
session: Session,
messages: list[dict],
provider: LLMProvider,
model: str,
*,
archive_all: bool = False,
memory_window: int = 50,
) -> bool:
"""Consolidate old messages into MEMORY.md + HISTORY.md via LLM tool call.
Returns True on success (including no-op), False on failure.
"""
if archive_all:
old_messages = session.messages
keep_count = 0
logger.info("Memory consolidation (archive_all): {} messages", len(session.messages))
else:
keep_count = memory_window // 2
if len(session.messages) <= keep_count:
return True
if len(session.messages) - session.last_consolidated <= 0:
return True
old_messages = session.messages[session.last_consolidated:-keep_count]
if not old_messages:
return True
logger.info("Memory consolidation: {} to consolidate, {} keep", len(old_messages), keep_count)
lines = []
for m in old_messages:
if not m.get("content"):
continue
tools = f" [tools: {', '.join(m['tools_used'])}]" if m.get("tools_used") else ""
lines.append(f"[{m.get('timestamp', '?')[:16]}] {m['role'].upper()}{tools}: {m['content']}")
"""Consolidate the provided message chunk into MEMORY.md + HISTORY.md."""
if not messages:
return True
current_memory = self.read_long_term()
prompt = f"""Process this conversation and call the save_memory tool with your consolidation.
@@ -108,50 +110,175 @@ class MemoryStore:
{current_memory or "(empty)"}
## Conversation to Process
{chr(10).join(lines)}"""
{self._format_messages(messages)}"""
try:
response = await provider.chat(
response = await provider.chat_with_retry(
messages=[
{"role": "system", "content": "You are a memory consolidation agent. Call the save_memory tool with your consolidation of the conversation."},
{"role": "user", "content": prompt},
],
tools=_SAVE_MEMORY_TOOL,
model=model,
tool_choice="required",
)
if not response.has_tool_calls:
logger.warning("Memory consolidation: LLM did not call save_memory, skipping")
return False
args = response.tool_calls[0].arguments
# Some providers return arguments as a JSON string instead of dict
if isinstance(args, str):
args = json.loads(args)
# Some providers return arguments as a list (handle edge case)
if isinstance(args, list):
if args and isinstance(args[0], dict):
args = args[0]
else:
logger.warning("Memory consolidation: unexpected arguments as empty or non-dict list")
return False
if not isinstance(args, dict):
logger.warning("Memory consolidation: unexpected arguments type {}", type(args).__name__)
args = _normalize_save_memory_args(response.tool_calls[0].arguments)
if args is None:
logger.warning("Memory consolidation: unexpected save_memory arguments")
return False
if entry := args.get("history_entry"):
if not isinstance(entry, str):
entry = json.dumps(entry, ensure_ascii=False)
self.append_history(entry)
self.append_history(_ensure_text(entry))
if update := args.get("memory_update"):
if not isinstance(update, str):
update = json.dumps(update, ensure_ascii=False)
update = _ensure_text(update)
if update != current_memory:
self.write_long_term(update)
session.last_consolidated = 0 if archive_all else len(session.messages) - keep_count
logger.info("Memory consolidation done: {} messages, last_consolidated={}", len(session.messages), session.last_consolidated)
logger.info("Memory consolidation done for {} messages", len(messages))
return True
except Exception:
logger.exception("Memory consolidation failed")
return False
class MemoryConsolidator:
"""Owns consolidation policy, locking, and session offset updates."""
_MAX_CONSOLIDATION_ROUNDS = 5
def __init__(
self,
workspace: Path,
provider: LLMProvider,
model: str,
sessions: SessionManager,
context_window_tokens: int,
build_messages: Callable[..., list[dict[str, Any]]],
get_tool_definitions: Callable[[], list[dict[str, Any]]],
):
self.store = MemoryStore(workspace)
self.provider = provider
self.model = model
self.sessions = sessions
self.context_window_tokens = context_window_tokens
self._build_messages = build_messages
self._get_tool_definitions = get_tool_definitions
self._locks: weakref.WeakValueDictionary[str, asyncio.Lock] = weakref.WeakValueDictionary()
def get_lock(self, session_key: str) -> asyncio.Lock:
"""Return the shared consolidation lock for one session."""
return self._locks.setdefault(session_key, asyncio.Lock())
async def consolidate_messages(self, messages: list[dict[str, object]]) -> bool:
"""Archive a selected message chunk into persistent memory."""
return await self.store.consolidate(messages, self.provider, self.model)
def pick_consolidation_boundary(
self,
session: Session,
tokens_to_remove: int,
) -> tuple[int, int] | None:
"""Pick a user-turn boundary that removes enough old prompt tokens."""
start = session.last_consolidated
if start >= len(session.messages) or tokens_to_remove <= 0:
return None
removed_tokens = 0
last_boundary: tuple[int, int] | None = None
for idx in range(start, len(session.messages)):
message = session.messages[idx]
if idx > start and message.get("role") == "user":
last_boundary = (idx, removed_tokens)
if removed_tokens >= tokens_to_remove:
return last_boundary
removed_tokens += estimate_message_tokens(message)
return last_boundary
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)
channel, chat_id = (session.key.split(":", 1) if ":" in session.key else (None, None))
probe_messages = self._build_messages(
history=history,
current_message="[token-probe]",
channel=channel,
chat_id=chat_id,
)
return estimate_prompt_tokens_chain(
self.provider,
self.model,
probe_messages,
self._get_tool_definitions(),
)
async def archive_unconsolidated(self, session: Session) -> bool:
"""Archive the full unconsolidated tail for /new-style session rollover."""
lock = self.get_lock(session.key)
async with lock:
snapshot = session.messages[session.last_consolidated:]
if not snapshot:
return True
return await self.consolidate_messages(snapshot)
async def maybe_consolidate_by_tokens(self, session: Session) -> None:
"""Loop: archive old messages until prompt fits within half the context window."""
if not session.messages or self.context_window_tokens <= 0:
return
lock = self.get_lock(session.key)
async with lock:
target = self.context_window_tokens // 2
estimated, source = self.estimate_session_prompt_tokens(session)
if estimated <= 0:
return
if estimated < self.context_window_tokens:
logger.debug(
"Token consolidation idle {}: {}/{} via {}",
session.key,
estimated,
self.context_window_tokens,
source,
)
return
for round_num in range(self._MAX_CONSOLIDATION_ROUNDS):
if estimated <= target:
return
boundary = self.pick_consolidation_boundary(session, max(1, estimated - target))
if boundary is None:
logger.debug(
"Token consolidation: no safe boundary for {} (round {})",
session.key,
round_num,
)
return
end_idx = boundary[0]
chunk = session.messages[session.last_consolidated:end_idx]
if not chunk:
return
logger.info(
"Token consolidation round {} for {}: {}/{} via {}, chunk={} msgs",
round_num,
session.key,
estimated,
self.context_window_tokens,
source,
len(chunk),
)
if not await self.consolidate_messages(chunk):
return
session.last_consolidated = end_idx
self.sessions.save(session)
estimated, source = self.estimate_session_prompt_tokens(session)
if estimated <= 0:
return
+10 -25
View File
@@ -16,6 +16,7 @@ from nanobot.bus.events import InboundMessage
from nanobot.bus.queue import MessageBus
from nanobot.config.schema import ExecToolConfig
from nanobot.providers.base import LLMProvider
from nanobot.utils.helpers import build_assistant_message
class SubagentManager:
@@ -27,9 +28,6 @@ class SubagentManager:
workspace: Path,
bus: MessageBus,
model: str | None = None,
temperature: float = 0.7,
max_tokens: int = 4096,
reasoning_effort: str | None = None,
brave_api_key: str | None = None,
web_proxy: str | None = None,
exec_config: "ExecToolConfig | None" = None,
@@ -40,9 +38,6 @@ class SubagentManager:
self.workspace = workspace
self.bus = bus
self.model = model or provider.get_default_model()
self.temperature = temperature
self.max_tokens = max_tokens
self.reasoning_effort = reasoning_effort
self.brave_api_key = brave_api_key
self.web_proxy = web_proxy
self.exec_config = exec_config or ExecToolConfig()
@@ -123,33 +118,23 @@ class SubagentManager:
while iteration < max_iterations:
iteration += 1
response = await self.provider.chat(
response = await self.provider.chat_with_retry(
messages=messages,
tools=tools.get_definitions(),
model=self.model,
temperature=self.temperature,
max_tokens=self.max_tokens,
reasoning_effort=self.reasoning_effort,
)
if response.has_tool_calls:
# Add assistant message with tool calls
tool_call_dicts = [
{
"id": tc.id,
"type": "function",
"function": {
"name": tc.name,
"arguments": json.dumps(tc.arguments, ensure_ascii=False),
},
}
tc.to_openai_tool_call()
for tc in response.tool_calls
]
messages.append({
"role": "assistant",
"content": response.content or "",
"tool_calls": tool_call_dicts,
})
messages.append(build_assistant_message(
response.content or "",
tool_calls=tool_call_dicts,
reasoning_content=response.reasoning_content,
thinking_blocks=response.thinking_blocks,
))
# Execute tools
for tool_call in response.tool_calls:
@@ -230,7 +215,7 @@ Stay focused on the assigned task. Your final response will be reported back to
parts.append(f"## Skills\n\nRead SKILL.md with read_file to use a skill.\n\n{skills_summary}")
return "\n\n".join(parts)
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, [])
+213 -86
View File
@@ -1,4 +1,4 @@
"""File system tools: read, write, edit."""
"""File system tools: read, write, edit, list."""
import difflib
from pathlib import Path
@@ -23,62 +23,108 @@ def _resolve_path(
return resolved
class ReadFileTool(Tool):
"""Tool to read file contents."""
_MAX_CHARS = 128_000 # ~128 KB — prevents OOM from reading huge files into LLM context
class _FsTool(Tool):
"""Shared base for filesystem tools — common init and path resolution."""
def __init__(self, workspace: Path | None = None, allowed_dir: Path | None = None):
self._workspace = workspace
self._allowed_dir = allowed_dir
def _resolve(self, path: str) -> Path:
return _resolve_path(path, self._workspace, self._allowed_dir)
# ---------------------------------------------------------------------------
# read_file
# ---------------------------------------------------------------------------
class ReadFileTool(_FsTool):
"""Read file contents with optional line-based pagination."""
_MAX_CHARS = 128_000
_DEFAULT_LIMIT = 2000
@property
def name(self) -> str:
return "read_file"
@property
def description(self) -> str:
return "Read the contents of a file at the given path."
return (
"Read the contents of a file. Returns numbered lines. "
"Use offset and limit to paginate through large files."
)
@property
def parameters(self) -> dict[str, Any]:
return {
"type": "object",
"properties": {"path": {"type": "string", "description": "The file path to read"}},
"properties": {
"path": {"type": "string", "description": "The file path to read"},
"offset": {
"type": "integer",
"description": "Line number to start reading from (1-indexed, default 1)",
"minimum": 1,
},
"limit": {
"type": "integer",
"description": "Maximum number of lines to read (default 2000)",
"minimum": 1,
},
},
"required": ["path"],
}
async def execute(self, path: str, **kwargs: Any) -> str:
async def execute(self, path: str, offset: int = 1, limit: int | None = None, **kwargs: Any) -> str:
try:
file_path = _resolve_path(path, self._workspace, self._allowed_dir)
if not file_path.exists():
fp = self._resolve(path)
if not fp.exists():
return f"Error: File not found: {path}"
if not file_path.is_file():
if not fp.is_file():
return f"Error: Not a file: {path}"
size = file_path.stat().st_size
if size > self._MAX_CHARS * 4: # rough upper bound (UTF-8 chars ≤ 4 bytes)
return (
f"Error: File too large ({size:,} bytes). "
f"Use exec tool with head/tail/grep to read portions."
)
all_lines = fp.read_text(encoding="utf-8").splitlines()
total = len(all_lines)
content = file_path.read_text(encoding="utf-8")
if len(content) > self._MAX_CHARS:
return content[: self._MAX_CHARS] + f"\n\n... (truncated — file is {len(content):,} chars, limit {self._MAX_CHARS:,})"
return content
if offset < 1:
offset = 1
if total == 0:
return f"(Empty file: {path})"
if offset > total:
return f"Error: offset {offset} is beyond end of file ({total} lines)"
start = offset - 1
end = min(start + (limit or self._DEFAULT_LIMIT), total)
numbered = [f"{start + i + 1}| {line}" for i, line in enumerate(all_lines[start:end])]
result = "\n".join(numbered)
if len(result) > self._MAX_CHARS:
trimmed, chars = [], 0
for line in numbered:
chars += len(line) + 1
if chars > self._MAX_CHARS:
break
trimmed.append(line)
end = start + len(trimmed)
result = "\n".join(trimmed)
if end < total:
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)"
return result
except PermissionError as e:
return f"Error: {e}"
except Exception as e:
return f"Error reading file: {str(e)}"
return f"Error reading file: {e}"
class WriteFileTool(Tool):
"""Tool to write content to a file."""
# ---------------------------------------------------------------------------
# write_file
# ---------------------------------------------------------------------------
def __init__(self, workspace: Path | None = None, allowed_dir: Path | None = None):
self._workspace = workspace
self._allowed_dir = allowed_dir
class WriteFileTool(_FsTool):
"""Write content to a file."""
@property
def name(self) -> str:
@@ -101,22 +147,48 @@ class WriteFileTool(Tool):
async def execute(self, path: str, content: str, **kwargs: Any) -> str:
try:
file_path = _resolve_path(path, self._workspace, self._allowed_dir)
file_path.parent.mkdir(parents=True, exist_ok=True)
file_path.write_text(content, encoding="utf-8")
return f"Successfully wrote {len(content)} bytes to {file_path}"
fp = self._resolve(path)
fp.parent.mkdir(parents=True, exist_ok=True)
fp.write_text(content, encoding="utf-8")
return f"Successfully wrote {len(content)} bytes to {fp}"
except PermissionError as e:
return f"Error: {e}"
except Exception as e:
return f"Error writing file: {str(e)}"
return f"Error writing file: {e}"
class EditFileTool(Tool):
"""Tool to edit a file by replacing text."""
# ---------------------------------------------------------------------------
# edit_file
# ---------------------------------------------------------------------------
def __init__(self, workspace: Path | None = None, allowed_dir: Path | None = None):
self._workspace = workspace
self._allowed_dir = allowed_dir
def _find_match(content: str, old_text: str) -> tuple[str | None, int]:
"""Locate old_text in content: exact first, then line-trimmed sliding window.
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:
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
class EditFileTool(_FsTool):
"""Edit a file by replacing text with fallback matching."""
@property
def name(self) -> str:
@@ -124,7 +196,11 @@ class EditFileTool(Tool):
@property
def description(self) -> str:
return "Edit a file by replacing old_text with new_text. The old_text must exist exactly in the file."
return (
"Edit a file by replacing old_text with new_text. "
"Supports minor whitespace/line-ending differences. "
"Set replace_all=true to replace every occurrence."
)
@property
def parameters(self) -> dict[str, Any]:
@@ -132,40 +208,52 @@ class EditFileTool(Tool):
"type": "object",
"properties": {
"path": {"type": "string", "description": "The file path to edit"},
"old_text": {"type": "string", "description": "The exact text to find and replace"},
"old_text": {"type": "string", "description": "The text to find and replace"},
"new_text": {"type": "string", "description": "The text to replace with"},
"replace_all": {
"type": "boolean",
"description": "Replace all occurrences (default false)",
},
},
"required": ["path", "old_text", "new_text"],
}
async def execute(self, path: str, old_text: str, new_text: str, **kwargs: Any) -> str:
async def execute(
self, path: str, old_text: str, new_text: str,
replace_all: bool = False, **kwargs: Any,
) -> str:
try:
file_path = _resolve_path(path, self._workspace, self._allowed_dir)
if not file_path.exists():
fp = self._resolve(path)
if not fp.exists():
return f"Error: File not found: {path}"
content = file_path.read_text(encoding="utf-8")
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"))
if old_text not in content:
return self._not_found_message(old_text, content, path)
if match is None:
return self._not_found_msg(old_text, content, path)
if count > 1 and not replace_all:
return (
f"Warning: old_text appears {count} times. "
"Provide more context to make it unique, or set replace_all=true."
)
# Count occurrences
count = content.count(old_text)
if count > 1:
return f"Warning: old_text appears {count} times. Please provide more context to make it unique."
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)
if uses_crlf:
new_content = new_content.replace("\n", "\r\n")
new_content = content.replace(old_text, new_text, 1)
file_path.write_text(new_content, encoding="utf-8")
return f"Successfully edited {file_path}"
fp.write_bytes(new_content.encode("utf-8"))
return f"Successfully edited {fp}"
except PermissionError as e:
return f"Error: {e}"
except Exception as e:
return f"Error editing file: {str(e)}"
return f"Error editing file: {e}"
@staticmethod
def _not_found_message(old_text: str, content: str, path: str) -> str:
"""Build a helpful error when old_text is not found."""
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)
@@ -177,27 +265,29 @@ class EditFileTool(Tool):
best_ratio, best_start = ratio, i
if best_ratio > 0.5:
diff = "\n".join(
difflib.unified_diff(
old_lines,
lines[best_start : best_start + window],
fromfile="old_text (provided)",
tofile=f"{path} (actual, line {best_start + 1})",
lineterm="",
)
)
diff = "\n".join(difflib.unified_diff(
old_lines, lines[best_start : best_start + window],
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}"
return (
f"Error: old_text not found in {path}. No similar text found. Verify the file content."
)
return f"Error: old_text not found in {path}. No similar text found. Verify the file content."
class ListDirTool(Tool):
"""Tool to list directory contents."""
# ---------------------------------------------------------------------------
# list_dir
# ---------------------------------------------------------------------------
def __init__(self, workspace: Path | None = None, allowed_dir: Path | None = None):
self._workspace = workspace
self._allowed_dir = allowed_dir
class ListDirTool(_FsTool):
"""List directory contents with optional recursion."""
_DEFAULT_MAX = 200
_IGNORE_DIRS = {
".git", "node_modules", "__pycache__", ".venv", "venv",
"dist", "build", ".tox", ".mypy_cache", ".pytest_cache",
".ruff_cache", ".coverage", "htmlcov",
}
@property
def name(self) -> str:
@@ -205,34 +295,71 @@ class ListDirTool(Tool):
@property
def description(self) -> str:
return "List the contents of a directory."
return (
"List the contents of a directory. "
"Set recursive=true to explore nested structure. "
"Common noise directories (.git, node_modules, __pycache__, etc.) are auto-ignored."
)
@property
def parameters(self) -> dict[str, Any]:
return {
"type": "object",
"properties": {"path": {"type": "string", "description": "The directory path to list"}},
"properties": {
"path": {"type": "string", "description": "The directory path to list"},
"recursive": {
"type": "boolean",
"description": "Recursively list all files (default false)",
},
"max_entries": {
"type": "integer",
"description": "Maximum entries to return (default 200)",
"minimum": 1,
},
},
"required": ["path"],
}
async def execute(self, path: str, **kwargs: Any) -> str:
async def execute(
self, path: str, recursive: bool = False,
max_entries: int | None = None, **kwargs: Any,
) -> str:
try:
dir_path = _resolve_path(path, self._workspace, self._allowed_dir)
if not dir_path.exists():
dp = self._resolve(path)
if not dp.exists():
return f"Error: Directory not found: {path}"
if not dir_path.is_dir():
if not dp.is_dir():
return f"Error: Not a directory: {path}"
items = []
for item in sorted(dir_path.iterdir()):
prefix = "📁 " if item.is_dir() else "📄 "
items.append(f"{prefix}{item.name}")
cap = max_entries or self._DEFAULT_MAX
items: list[str] = []
total = 0
if not items:
if recursive:
for item in sorted(dp.rglob("*")):
if any(p in self._IGNORE_DIRS for p in item.parts):
continue
total += 1
if len(items) < cap:
rel = item.relative_to(dp)
items.append(f"{rel}/" if item.is_dir() else str(rel))
else:
for item in sorted(dp.iterdir()):
if item.name in self._IGNORE_DIRS:
continue
total += 1
if len(items) < cap:
pfx = "📁 " if item.is_dir() else "📄 "
items.append(f"{pfx}{item.name}")
if not items and total == 0:
return f"Directory {path} is empty"
return "\n".join(items)
result = "\n".join(items)
if total > cap:
result += f"\n\n(truncated, showing first {cap} of {total} entries)"
return result
except PermissionError as e:
return f"Error: {e}"
except Exception as e:
return f"Error listing directory: {str(e)}"
return f"Error listing directory: {e}"
+49 -28
View File
@@ -42,6 +42,9 @@ class ExecTool(Tool):
def name(self) -> str:
return "exec"
_MAX_TIMEOUT = 600
_MAX_OUTPUT = 10_000
@property
def description(self) -> str:
return "Execute a shell command and return its output. Use with caution."
@@ -53,22 +56,36 @@ class ExecTool(Tool):
"properties": {
"command": {
"type": "string",
"description": "The shell command to execute"
"description": "The shell command to execute",
},
"working_dir": {
"type": "string",
"description": "Optional working directory for the command"
}
"description": "Optional working directory for the command",
},
"timeout": {
"type": "integer",
"description": (
"Timeout in seconds. Increase for long-running commands "
"like compilation or installation (default 60, max 600)."
),
"minimum": 1,
"maximum": 600,
},
},
"required": ["command"]
"required": ["command"],
}
async def execute(self, command: str, working_dir: str | None = None, **kwargs: Any) -> str:
async def execute(
self, command: str, working_dir: str | None = None,
timeout: int | None = None, **kwargs: Any,
) -> str:
cwd = working_dir or self.working_dir or os.getcwd()
guard_error = self._guard_command(command, cwd)
if guard_error:
return guard_error
effective_timeout = min(timeout or self.timeout, self._MAX_TIMEOUT)
env = os.environ.copy()
if self.path_append:
env["PATH"] = env.get("PATH", "") + os.pathsep + self.path_append
@@ -81,44 +98,46 @@ class ExecTool(Tool):
cwd=cwd,
env=env,
)
try:
stdout, stderr = await asyncio.wait_for(
process.communicate(),
timeout=self.timeout
timeout=effective_timeout,
)
except asyncio.TimeoutError:
process.kill()
# Wait for the process to fully terminate so pipes are
# drained and file descriptors are released.
try:
await asyncio.wait_for(process.wait(), timeout=5.0)
except asyncio.TimeoutError:
pass
return f"Error: Command timed out after {self.timeout} seconds"
return f"Error: Command timed out after {effective_timeout} seconds"
output_parts = []
if stdout:
output_parts.append(stdout.decode("utf-8", errors="replace"))
if stderr:
stderr_text = stderr.decode("utf-8", errors="replace")
if stderr_text.strip():
output_parts.append(f"STDERR:\n{stderr_text}")
if process.returncode != 0:
output_parts.append(f"\nExit code: {process.returncode}")
output_parts.append(f"\nExit code: {process.returncode}")
result = "\n".join(output_parts) if output_parts else "(no output)"
# Truncate very long output
max_len = 10000
# Head + tail truncation to preserve both start and end of output
max_len = self._MAX_OUTPUT
if len(result) > max_len:
result = result[:max_len] + f"\n... (truncated, {len(result) - max_len} more chars)"
half = max_len // 2
result = (
result[:half]
+ f"\n\n... ({len(result) - max_len:,} chars truncated) ...\n\n"
+ result[-half:]
)
return result
except Exception as e:
return f"Error executing command: {str(e)}"
@@ -143,7 +162,8 @@ class ExecTool(Tool):
for raw in self._extract_absolute_paths(cmd):
try:
p = Path(raw.strip()).resolve()
expanded = os.path.expandvars(raw.strip())
p = Path(expanded).expanduser().resolve()
except Exception:
continue
if p.is_absolute() and cwd_path not in p.parents and p != cwd_path:
@@ -154,5 +174,6 @@ class ExecTool(Tool):
@staticmethod
def _extract_absolute_paths(command: str) -> list[str]:
win_paths = re.findall(r"[A-Za-z]:\\[^\s\"'|><;]+", command) # Windows: C:\...
posix_paths = re.findall(r"(?:^|[\s|>])(/[^\s\"'>]+)", command) # POSIX: /absolute only
return win_paths + posix_paths
posix_paths = re.findall(r"(?:^|[\s|>'\"])(/[^\s\"'>;|<]+)", command) # POSIX: /absolute only
home_paths = re.findall(r"(?:^|[\s|>'\"])(~[^\s\"'>;|<]*)", command) # POSIX/Windows home shortcut: ~
return win_paths + posix_paths + home_paths