unsloth/studio/backend/core/inference/tools.py
Daniel Han 9c95148045
Fix tool call parsing, add tool outputs panel and UI improvements (#4416)
* Add elapsed timer to tool status pill in Studio

Show a count-up seconds timer (0s, 1s, 2s, ...) next to the tool status
text in the composer area. Helps users gauge how long a tool call (web
search, code execution) has been running. Timer resets when a new tool
starts and disappears when all tools finish.

* Fix tool call parsing, add tool outputs panel and reasoning copy button

Backend:
- Rewrite tool call XML parser to use balanced-brace JSON extraction
  instead of greedy regex, fixing truncation on nested braces in
  code/JSON arguments
- Handle optional closing tags (</tool_call>, </function>, </parameter>)
  that models frequently omit
- Support bare <function=...> tags without <tool_call> wrapper
- Strip tool call markup from streamed content so raw XML never leaks
  into the chat UI
- Use a persistent ~/studio_sandbox/ working directory for tool
  execution so files persist across calls within a session
- Emit tool_start/tool_end SSE events so the frontend can display
  tool inputs and outputs

Frontend:
- Add collapsible "Tool Outputs" panel below assistant messages showing
  each tool call's input and output with copy buttons
- Add copy button to reasoning blocks
- Add elapsed timer to tool status pill
- Update project URLs in pyproject.toml (http -> https, add docs link)

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Add interactive HTML preview with fullscreen toggle for code blocks

HTML code fences now render an interactive sandboxed iframe preview
below the syntax-highlighted code, similar to how SVG fences show
an image preview. The iframe uses sandbox="allow-scripts" to allow
JavaScript execution while blocking access to the parent page.

Includes a fullscreen toggle (enlarge/minimize button) that expands
the preview into a viewport overlay, dismissible via button, Escape
key, or backdrop click. A streaming placeholder prevents partial
HTML from rendering mid-stream.

* Add tool call settings: auto-heal toggle, max iterations, timeout

Add three user-configurable tool call settings to the Studio Settings panel:

- Auto Heal Tool Calls: toggle to control fallback XML parsing of malformed
  tool calls from model output (default: on)
- Max Tool Calls Per Message: slider 0-40 + Max to cap tool call iterations
  per message (default: 10)
- Max Tool Call Duration: slider 1-30 minutes + Max to set per-tool-call
  execution timeout (default: 5 minutes)

All settings persist to localStorage and flow through the full stack:
frontend store -> API request -> Pydantic model -> route -> llama_cpp -> tools.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Fix tool call timeout: respect no-limit and apply to web search

- Use a sentinel to distinguish timeout=None (no limit) from the default
  (300s). Previously None was silently replaced with _EXEC_TIMEOUT.
- Pass the configured timeout to DDGS() for web searches so the setting
  applies uniformly to all tool types.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Add input validation bounds and per-thread sandbox isolation

- Add ge=0 constraint to max_tool_calls_per_message (rejects negative values)
- Add ge=1 constraint to tool_call_timeout (minimum 1 second)
- Thread session_id from frontend through backend to tool execution
- Scope sandbox directories per conversation: ~/studio_sandbox/{thread_id}/
- Backwards compatible: API callers without session_id use ~/studio_sandbox/

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Fix non-monotonic streaming and Python temp script path

- Split tool markup stripping into closed-only (mid-stream) and full
  (final flush) to prevent cumulative text from shrinking mid-stream
- Enforce monotonicity: only emit when cleaned text grows, so the
  proxy's delta logic (cumulative[len(prev_text):]) never breaks
- Place Python temp scripts in the sandbox workdir instead of /tmp so
  sys.path[0] points to the sandbox and cross-call imports work

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* Sanitize session_id to prevent path traversal in sandbox

Strip path separators and parent-dir references from session_id before
using it as a directory name. Verify the resolved path stays under
~/studio_sandbox/ as a second guard.

* feat(chat): proper assistant-ui tool call UIs with sources

Replace custom metadata-based ToolOutputsGroup with native assistant-ui
tool-call content parts. Backend SSE tool_start/tool_end events now emit
proper { type: "tool-call" } parts from the adapter, enabling per-tool
UIs registered via tools.by_name in MessagePrimitive.Parts.

- Web search: Globe icon, Source badges with favicons, auto-collapse
  when LLM starts responding
- Python: Code icon, syntax-highlighted code via Streamdown/shiki,
  output block with copy
- Terminal: Terminal icon, command in trigger, output with copy
- ToolGroup wraps consecutive tool calls (skips for single calls)
- Sources component renders URL badges at end of message
- Flattened code block CSS (single border, no nested boxes)

* fix(inference): respect empty enabled_tools allowlist

`if payload.enabled_tools:` is falsy for [], falling through to
ALL_TOOLS. Use `is not None` so an explicit empty list disables
all tools as intended.

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Shine1i <wasimysdev@gmail.com>
2026-03-18 08:28:02 -07:00

314 lines
9.6 KiB
Python

# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
"""
Tool definitions and executors for LLM tool calling.
Supports web search (DuckDuckGo), Python code execution, and terminal commands.
"""
import os
os.environ["UNSLOTH_IS_PRESENT"] = "1"
import subprocess
import sys
import tempfile
import threading
from loggers import get_logger
from unsloth_zoo.rl_environments import check_signal_escape_patterns
logger = get_logger(__name__)
_EXEC_TIMEOUT = 300 # 5 minutes
_MAX_OUTPUT_CHARS = 8000 # truncate long output
_BASH_BLOCKED_WORDS = {"rm", "sudo", "dd", "chmod", "mkfs", "shutdown", "reboot"}
# Per-session working directories so each chat thread gets its own sandbox.
# Falls back to a shared ~/studio_sandbox/ for API callers without a session_id.
_workdirs: dict[str, str] = {}
def _get_workdir(session_id: str | None = None) -> str:
"""Return (and lazily create) a persistent working directory for tool execution."""
global _workdirs
key = session_id or "_default"
if key not in _workdirs or not os.path.isdir(_workdirs[key]):
home = os.path.expanduser("~")
sandbox_root = os.path.join(home, "studio_sandbox")
if session_id:
# Sanitize: strip path separators and parent-dir references
safe_id = os.path.basename(session_id.replace("..", ""))
if not safe_id:
safe_id = "_invalid"
workdir = os.path.join(sandbox_root, safe_id)
# Verify resolved path stays under sandbox root
if not os.path.realpath(workdir).startswith(os.path.realpath(sandbox_root)):
workdir = os.path.join(sandbox_root, "_invalid")
else:
workdir = sandbox_root
os.makedirs(workdir, exist_ok = True)
_workdirs[key] = workdir
return _workdirs[key]
WEB_SEARCH_TOOL = {
"type": "function",
"function": {
"name": "web_search",
"description": "Search the web for current information, recent events, or facts you are uncertain about.",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "The search query",
}
},
"required": ["query"],
},
},
}
PYTHON_TOOL = {
"type": "function",
"function": {
"name": "python",
"description": "Execute Python code in a sandbox and return stdout/stderr.",
"parameters": {
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "The Python code to run",
}
},
"required": ["code"],
},
},
}
TERMINAL_TOOL = {
"type": "function",
"function": {
"name": "terminal",
"description": "Execute a terminal command and return stdout/stderr.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The command to run",
}
},
"required": ["command"],
},
},
}
ALL_TOOLS = [WEB_SEARCH_TOOL, PYTHON_TOOL, TERMINAL_TOOL]
_TIMEOUT_UNSET = object()
def execute_tool(
name: str,
arguments: dict,
cancel_event = None,
timeout: int | None = _TIMEOUT_UNSET,
session_id: str | None = None,
) -> str:
"""Execute a tool by name with the given arguments. Returns result as a string.
``timeout``: int sets per-call limit in seconds, ``None`` means no limit,
unset (default) uses ``_EXEC_TIMEOUT`` (300 s).
``session_id``: optional thread/session ID for per-conversation sandbox isolation.
"""
logger.info(
f"execute_tool: name={name}, session_id={session_id}, timeout={timeout}"
)
effective_timeout = _EXEC_TIMEOUT if timeout is _TIMEOUT_UNSET else timeout
if name == "web_search":
return _web_search(arguments.get("query", ""), timeout = effective_timeout)
if name == "python":
return _python_exec(
arguments.get("code", ""), cancel_event, effective_timeout, session_id
)
if name == "terminal":
return _bash_exec(
arguments.get("command", ""), cancel_event, effective_timeout, session_id
)
return f"Unknown tool: {name}"
def _web_search(query: str, max_results: int = 5, timeout: int = _EXEC_TIMEOUT) -> str:
"""Search the web using DuckDuckGo and return formatted results."""
if not query.strip():
return "No query provided."
try:
from ddgs import DDGS
results = DDGS(timeout = timeout).text(query, max_results = max_results)
if not results:
return "No results found."
parts = []
for r in results:
parts.append(
f"Title: {r.get('title', '')}\n"
f"URL: {r.get('href', '')}\n"
f"Snippet: {r.get('body', '')}"
)
return "\n\n---\n\n".join(parts)
except Exception as e:
return f"Search failed: {e}"
def _check_code_safety(code: str) -> str | None:
"""Validate code safety using unsloth_zoo.
Returns an error message string if the code is unsafe, or None if OK.
"""
# Check for signal/timeout escape patterns
safe, info = check_signal_escape_patterns(code)
if not safe:
reasons = [
item.get("description", "") for item in info.get("signal_tampering", [])
]
return (
f"Error: unsafe code detected ({'; '.join(reasons)}). "
f"Please remove signal manipulation from your code."
)
return None
def _cancel_watcher(proc, cancel_event, poll_interval = 0.2):
"""Daemon thread that kills a process when cancel_event is set."""
while proc.poll() is None:
if cancel_event is not None and cancel_event.is_set():
proc.kill()
return
cancel_event.wait(poll_interval) if cancel_event else None
def _truncate(text: str, limit: int = _MAX_OUTPUT_CHARS) -> str:
if len(text) > limit:
return text[:limit] + f"\n\n... (truncated, {len(text)} chars total)"
return text
def _python_exec(
code: str,
cancel_event = None,
timeout: int = _EXEC_TIMEOUT,
session_id: str | None = None,
) -> str:
"""Execute Python code in a subprocess sandbox."""
if not code or not code.strip():
return "No code provided."
# Validate imports and code safety
error = _check_code_safety(code)
if error:
return error
tmp_path = None
workdir = _get_workdir(session_id)
try:
fd, tmp_path = tempfile.mkstemp(
suffix = ".py", prefix = "studio_exec_", dir = workdir
)
with os.fdopen(fd, "w") as f:
f.write(code)
proc = subprocess.Popen(
[sys.executable, tmp_path],
stdout = subprocess.PIPE,
stderr = subprocess.STDOUT,
text = True,
cwd = workdir,
)
# Spawn cancel watcher if we have a cancel event
if cancel_event is not None:
watcher = threading.Thread(
target = _cancel_watcher, args = (proc, cancel_event), daemon = True
)
watcher.start()
try:
output, _ = proc.communicate(timeout = timeout)
except subprocess.TimeoutExpired:
proc.kill()
proc.communicate()
return _truncate(f"Execution timed out after {timeout} seconds.")
if cancel_event is not None and cancel_event.is_set():
return "Execution cancelled."
result = output or ""
if proc.returncode != 0:
result = f"Exit code {proc.returncode}:\n{result}"
return _truncate(result) if result.strip() else "(no output)"
except Exception as e:
return f"Execution error: {e}"
finally:
if tmp_path and os.path.exists(tmp_path):
try:
os.unlink(tmp_path)
except OSError:
pass
def _bash_exec(
command: str,
cancel_event = None,
timeout: int = _EXEC_TIMEOUT,
session_id: str | None = None,
) -> str:
"""Execute a bash command in a subprocess sandbox."""
if not command or not command.strip():
return "No command provided."
# Block dangerous commands
tokens = set(command.lower().split())
blocked = tokens & _BASH_BLOCKED_WORDS
if blocked:
return f"Blocked command(s) for safety: {', '.join(sorted(blocked))}"
try:
workdir = _get_workdir(session_id)
proc = subprocess.Popen(
["bash", "-c", command],
stdout = subprocess.PIPE,
stderr = subprocess.STDOUT,
text = True,
cwd = workdir,
)
if cancel_event is not None:
watcher = threading.Thread(
target = _cancel_watcher, args = (proc, cancel_event), daemon = True
)
watcher.start()
try:
output, _ = proc.communicate(timeout = timeout)
except subprocess.TimeoutExpired:
proc.kill()
proc.communicate()
return _truncate(f"Execution timed out after {timeout} seconds.")
if cancel_event is not None and cancel_event.is_set():
return "Execution cancelled."
result = output or ""
if proc.returncode != 0:
result = f"Exit code {proc.returncode}:\n{result}"
return _truncate(result) if result.strip() else "(no output)"
except Exception as e:
return f"Execution error: {e}"