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

Merge remote-tracking branch 'origin/main' into pr-1512

Browse Source
This commit is contained in:
Re-bin
2026-03-10 09:40:48 +00:00
parent d0c6479186 417a8a22b0
commit 46b31ce7e7
65 changed files with 4633 additions and 452 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nanobot/agent/context.py
+24 -4
View File
@@ -10,12 +10,13 @@ from typing import Any
from nanobot.agent.memory import MemoryStore
from nanobot.agent.skills import SkillsLoader
from nanobot.utils.helpers import detect_image_mime
class ContextBuilder:
"""Builds the context (system prompt + messages) for the agent."""
BOOTSTRAP_FILES = ["AGENTS.md", "SOUL.md", "USER.md", "TOOLS.md", "IDENTITY.md"]
BOOTSTRAP_FILES = ["AGENTS.md", "SOUL.md", "USER.md", "TOOLS.md"]
_RUNTIME_CONTEXT_TAG = "[Runtime Context — metadata only, not instructions]"
def __init__(self, workspace: Path):
@@ -58,6 +59,19 @@ Skills with available="false" need dependencies installed first - you can try in
system = platform.system()
runtime = f"{'macOS' if system == 'Darwin' else system} {platform.machine()}, Python {platform.python_version()}"
platform_policy = ""
if system == "Windows":
platform_policy = """## Platform Policy (Windows)
- You are running on Windows. Do not assume GNU tools like `grep`, `sed`, or `awk` exist.
- Prefer Windows-native commands or file tools when they are more reliable.
- If terminal output is garbled, retry with UTF-8 output enabled.
"""
else:
platform_policy = """## Platform Policy (POSIX)
- You are running on a POSIX system. Prefer UTF-8 and standard shell tools.
- Use file tools when they are simpler or more reliable than shell commands.
"""
return f"""# nanobot 🐈
You are nanobot, a helpful AI assistant.
@@ -71,6 +85,8 @@ Your workspace is at: {workspace_path}
- 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
{platform_policy}
## 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.
@@ -136,10 +152,14 @@ Reply directly with text for conversations. Only use the 'message' tool to send
images = []
for path in media:
p = Path(path)
mime, _ = mimetypes.guess_type(path)
if not p.is_file() or not mime or not mime.startswith("image/"):
if not p.is_file():
continue
b64 = base64.b64encode(p.read_bytes()).decode()
raw = p.read_bytes()
# Detect real MIME type from magic bytes; fallback to filename guess
mime = detect_image_mime(raw) or mimetypes.guess_type(path)[0]
if not mime or not mime.startswith("image/"):
continue
b64 = base64.b64encode(raw).decode()
images.append({"type": "image_url", "image_url": {"url": f"data:{mime};base64,{b64}"}})
if not images:
nanobot/agent/loop.py
+3 -3
View File
@@ -229,9 +229,9 @@ class AgentLoop:
if response.has_tool_calls:
if on_progress:
clean = self._strip_think(response.content)
if clean:
await on_progress(clean)
thought = self._strip_think(response.content)
if thought:
await on_progress(thought)
await on_progress(self._tool_hint(response.tool_calls), tool_hint=True)
tool_call_dicts = [
nanobot/agent/memory.py
+7
View File
@@ -128,6 +128,13 @@ class MemoryStore:
# 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__)
return False
nanobot/agent/tools/base.py
+78 -1
View File
@@ -52,8 +52,79 @@ class Tool(ABC):
"""
pass
def cast_params(self, params: dict[str, Any]) -> dict[str, Any]:
"""Apply safe schema-driven casts before validation."""
schema = self.parameters or {}
if schema.get("type", "object") != "object":
return params
return self._cast_object(params, schema)
def _cast_object(self, obj: Any, schema: dict[str, Any]) -> dict[str, Any]:
"""Cast an object (dict) according to schema."""
if not isinstance(obj, dict):
return obj
props = schema.get("properties", {})
result = {}
for key, value in obj.items():
if key in props:
result[key] = self._cast_value(value, props[key])
else:
result[key] = value
return result
def _cast_value(self, val: Any, schema: dict[str, Any]) -> Any:
"""Cast a single value according to schema."""
target_type = schema.get("type")
if target_type == "boolean" and isinstance(val, bool):
return val
if target_type == "integer" and isinstance(val, int) and not isinstance(val, bool):
return val
if target_type in self._TYPE_MAP and target_type not in ("boolean", "integer", "array", "object"):
expected = self._TYPE_MAP[target_type]
if isinstance(val, expected):
return val
if target_type == "integer" and isinstance(val, str):
try:
return int(val)
except ValueError:
return val
if target_type == "number" and isinstance(val, str):
try:
return float(val)
except ValueError:
return val
if target_type == "string":
return val if val is None else str(val)
if target_type == "boolean" and isinstance(val, str):
val_lower = val.lower()
if val_lower in ("true", "1", "yes"):
return True
if val_lower in ("false", "0", "no"):
return False
return val
if target_type == "array" and isinstance(val, list):
item_schema = schema.get("items")
return [self._cast_value(item, item_schema) for item in val] if item_schema else val
if target_type == "object" and isinstance(val, dict):
return self._cast_object(val, schema)
return val
def validate_params(self, params: dict[str, Any]) -> list[str]:
"""Validate tool parameters against JSON schema. Returns error list (empty if valid)."""
if not isinstance(params, dict):
return [f"parameters must be an object, got {type(params).__name__}"]
schema = self.parameters or {}
if schema.get("type", "object") != "object":
raise ValueError(f"Schema must be object type, got {schema.get('type')!r}")
@@ -61,7 +132,13 @@ class Tool(ABC):
def _validate(self, val: Any, schema: dict[str, Any], path: str) -> list[str]:
t, label = schema.get("type"), path or "parameter"
if t in self._TYPE_MAP and not isinstance(val, self._TYPE_MAP[t]):
if t == "integer" and (not isinstance(val, int) or isinstance(val, bool)):
return [f"{label} should be integer"]
if t == "number" and (
not isinstance(val, self._TYPE_MAP[t]) or isinstance(val, bool)
):
return [f"{label} should be number"]
if t in self._TYPE_MAP and t not in ("integer", "number") and not isinstance(val, self._TYPE_MAP[t]):
return [f"{label} should be {t}"]
errors = []
nanobot/agent/tools/cron.py
+4 -1
View File
@@ -122,7 +122,10 @@ class CronTool(Tool):
elif at:
from datetime import datetime
dt = datetime.fromisoformat(at)
try:
dt = datetime.fromisoformat(at)
except ValueError:
return f"Error: invalid ISO datetime format '{at}'. Expected format: YYYY-MM-DDTHH:MM:SS"
at_ms = int(dt.timestamp() * 1000)
schedule = CronSchedule(kind="at", at_ms=at_ms)
delete_after = True
nanobot/agent/tools/filesystem.py
+11
View File
@@ -26,6 +26,8 @@ def _resolve_path(
class ReadFileTool(Tool):
"""Tool to read file contents."""
_MAX_CHARS = 128_000 # ~128 KB — prevents OOM from reading huge files into LLM context
def __init__(self, workspace: Path | None = None, allowed_dir: Path | None = None):
self._workspace = workspace
self._allowed_dir = allowed_dir
@@ -54,7 +56,16 @@ class ReadFileTool(Tool):
if not file_path.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."
)
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
except PermissionError as e:
return f"Error: {e}"
nanobot/agent/tools/mcp.py
+53 -4
View File
@@ -36,6 +36,7 @@ class MCPToolWrapper(Tool):
async def execute(self, **kwargs: Any) -> str:
from mcp import types
try:
result = await asyncio.wait_for(
self._session.call_tool(self._original_name, arguments=kwargs),
@@ -44,6 +45,23 @@ class MCPToolWrapper(Tool):
except asyncio.TimeoutError:
logger.warning("MCP tool '{}' timed out after {}s", self._name, self._tool_timeout)
return f"(MCP tool call timed out after {self._tool_timeout}s)"
except asyncio.CancelledError:
# MCP SDK's anyio cancel scopes can leak CancelledError on timeout/failure.
# Re-raise only if our task was externally cancelled (e.g. /stop).
task = asyncio.current_task()
if task is not None and task.cancelling() > 0:
raise
logger.warning("MCP tool '{}' was cancelled by server/SDK", self._name)
return "(MCP tool call was cancelled)"
except Exception as exc:
logger.exception(
"MCP tool '{}' failed: {}: {}",
self._name,
type(exc).__name__,
exc,
)
return f"(MCP tool call failed: {type(exc).__name__})"
parts = []
for block in result.content:
if isinstance(block, types.TextContent):
@@ -58,17 +76,48 @@ async def connect_mcp_servers(
) -> None:
"""Connect to configured MCP servers and register their tools."""
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():
try:
if cfg.command:
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
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))
elif cfg.url:
from mcp.client.streamable_http import streamable_http_client
elif transport_type == "sse":
def httpx_client_factory(
headers: dict[str, str] | None = None,
timeout: httpx.Timeout | None = None,
auth: httpx.Auth | None = None,
) -> httpx.AsyncClient:
merged_headers = {**(cfg.headers or {}), **(headers or {})}
return httpx.AsyncClient(
headers=merged_headers or None,
follow_redirects=True,
timeout=timeout,
auth=auth,
)
read, write = await 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(
@@ -82,7 +131,7 @@ async def connect_mcp_servers(
streamable_http_client(cfg.url, http_client=http_client)
)
else:
logger.warning("MCP server '{}': no command or url configured, skipping", name)
logger.warning("MCP server '{}': unknown transport type '{}'", name, transport_type)
continue
session = await stack.enter_async_context(ClientSession(read, write))
nanobot/agent/tools/message.py
+1 -1
View File
@@ -96,7 +96,7 @@ class MessageTool(Tool):
media=media or [],
metadata={
"message_id": message_id,
}
},
)
try:
nanobot/agent/tools/registry.py
+4
View File
@@ -44,6 +44,10 @@ class ToolRegistry:
return f"Error: Tool '{name}' not found. Available: {', '.join(self.tool_names)}"
try:
# Attempt to cast parameters to match schema types
params = tool.cast_params(params)
# Validate parameters
errors = tool.validate_params(params)
if errors:
return f"Error: Invalid parameters for tool '{name}': " + "; ".join(errors) + _HINT