Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Python agentaichatgptdeepseekfine-tuninggemmaimage-generationllamallmllmsopenaipythonqwenreinforcement-learningself-hostedstable-diffusiontext-to-speechttsuiunsloth
# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team. All rights reserved. See /studio/LICENSE.AGPL-3.0
"""Each decision is resolved right after tool_start, since the slot already exists by then."""
import pytest
from core.inference.safetensors_agentic import run_safetensors_tool_loop
from state import tool_approvals
from state.tool_approvals import TOOL_REJECTED_MESSAGE, resolve_tool_decision
_SESSION = "loop-session"
@pytest.fixture(autouse = True)
def _clear_pending():
with tool_approvals._lock:
tool_approvals._pending.clear()
yield
with tool_approvals._lock:
tool_approvals._pending.clear()
class _FakeExecuteTool:
def __init__(self):
self.calls = []
def __call__(
self,
name,
arguments,
*,
cancel_event = None,
timeout = None,
session_id = None,
thread_id = None,
rag_scope = None,
disable_sandbox = False,
):
self.calls.append((name, arguments))
return f"RESULT[{name}]"
def _tool_call(name, args_json):
return f'<tool_call>{{"name": "{name}", "arguments": {args_json}}}</tool_call>'
def _multi_turn(turns):
"""A single_turn generator that yields one full snapshot per turn."""
turn_iter = iter(turns)
def _gen(_messages):
try:
yield next(turn_iter)
except StopIteration:
return
return _gen
_DEFAULT_TOOLS = [
{"type": "function", "function": {"name": "python"}},
{"type": "function", "function": {"name": "web_search"}},
]
def _drive(
turns,
decisions,
*,
tools = None,
):
"""Omitting a tool from the advertised tools list makes calls to it disabled, so no prompt."""
decision_iter = iter(decisions)
exec_fn = _FakeExecuteTool()
gen = run_safetensors_tool_loop(
single_turn = _multi_turn(turns),
messages = [{"role": "user", "content": "hi"}],
tools = _DEFAULT_TOOLS if tools is None else tools,
execute_tool = exec_fn,
session_id = _SESSION,
confirm_tool_calls = True,
# Confirm-gate mechanics need every call to prompt; "auto" only gates high-risk calls.
permission_mode = "ask",
)
events = []
for ev in gen:
events.append(ev)
if ev["type"] == "tool_start" and ev.get("awaiting_confirmation"):
# The slot is registered before this yield, so the decision lands before the wait.
resolve_tool_decision(ev["approval_id"], next(decision_iter), session_id = _SESSION)
return events, exec_fn.calls
def _tool_starts(events):
return [e for e in events if e["type"] == "tool_start"]
def _tool_ends(events):
return [e for e in events if e["type"] == "tool_end"]
def test_allow_executes_the_tool_once():
events, calls = _drive(
[_tool_call("python", '{"code": "print(1)"}'), "final answer"],
["allow"],
)
starts = _tool_starts(events)
assert len(starts) == 1
assert starts[0]["awaiting_confirmation"] is True
assert starts[0]["approval_id"]
assert calls == [("python", {"code": "print(1)"})]
assert _tool_ends(events)[0]["result"] == "RESULT[python]"
def test_deny_skips_execution_and_feeds_rejection():
events, calls = _drive(
[_tool_call("python", '{"code": "print(1)"}'), "final answer"],
["deny"],
)
assert calls == []
assert _tool_ends(events)[0]["result"] == TOOL_REJECTED_MESSAGE
def test_disabled_tool_is_not_prompted():
events, calls = _drive(
[_tool_call("python", '{"code": "print(1)"}'), "final answer"],
[],
tools = [{"type": "function", "function": {"name": "web_search"}}],
)
assert _tool_starts(events) == []
assert _tool_ends(events) == []
assert calls == []
def test_duplicate_call_is_not_prompted():
same = _tool_call("python", '{"code": "print(1)"}')
events, calls = _drive([same, same, "final answer"], ["allow"])
starts = _tool_starts(events)
assert len(starts) == 1
assert starts[0]["awaiting_confirmation"] is True
assert calls == [("python", {"code": "print(1)"})]
assert len(_tool_ends(events)) == 1
def test_denied_call_can_be_reissued_and_approved():
# Denied calls are not in duplicate history, so a re-issued identical call must run.
same = _tool_call("python", '{"code": "print(1)"}')
events, calls = _drive([same, same, "final answer"], ["deny", "allow"])
starts = _tool_starts(events)
assert len(starts) == 2
assert starts[0]["awaiting_confirmation"] is True
assert starts[1]["awaiting_confirmation"] is True
assert calls == [("python", {"code": "print(1)"})]
ends = _tool_ends(events)
assert ends[0]["result"] == TOOL_REJECTED_MESSAGE
assert ends[1]["result"] == "RESULT[python]"