f9f6bc01fd
CI / test (push) Canceled after 0s
## Summary epic r04 - begin refactor ## Change Type - [x] Cowork feature - [ ] Bug fix - [ ] Core AI contribution - [ ] Test / hardening - [ ] Performance - [ ] Documentation ## Related Work Cowork Task: Core Repo: http://34.143.229.138/gitea-admin/fsg-ai-core-assets Core AI Issue: Core Task: Related PR: ## Scope What is intentionally included? What is intentionally NOT included? ## Validation - [ ] Unit tests - [ ] Integration tests - [ ] Manual verification - [ ] Regression check Commands / evidence: ## Security Impact Permission / credential / network / customer data impact: ## Compatibility - [ ] No breaking change - [ ] Breaking change documented ## Reviewer Notes Anything Cowork reviewers should pay attention to. --------- Co-authored-by: Anh Tran Nguyen Minh <anhtnm1@fpt.com> Co-authored-by: Huong Le Thi Thien <huongltt35@fpt.com> Co-authored-by: Nam Pham Dinh Thanh <nampdt@fpt.com> Co-authored-by: Vu Dam Tuan <vudt15@fpt.com> Co-authored-by: Hiep Ha Van <hiephv3@fpt.com> Co-authored-by: Lam Hoang Van <lamhv7@fpt.com> Reviewed-on: #7 Co-authored-by: Duy Le Huu <duylh19@fpt.com>
63 lines
2.2 KiB
Python
63 lines
2.2 KiB
Python
"""EPIC R05-T03/T04: ``core/code_agent.py::run_code`` used to gate tool calls
|
|
with ``if name in (WRITE_TOOLS | MS365_WRITE_TOOLS): gate.request(...)``. This
|
|
pins that the switch to ``ToolPolicyGateway`` still gates exactly the same
|
|
calls: ``write_file`` (a WRITE tool) consults the gate; ``list_dir``
|
|
(read-only) never does.
|
|
|
|
Runs the REAL engine (``run_code``) via :class:`FakeProvider`, same approach
|
|
``tests/characterization/test_run_cowork.py`` uses for the Cowork engine.
|
|
"""
|
|
from __future__ import annotations
|
|
|
|
from typing import Any, Dict, List
|
|
|
|
from cowork_local.core.code_agent import run_code
|
|
from cowork_local.core.tools import ToolContext
|
|
from tests.fakes import FakeProvider, ScriptedTurn
|
|
|
|
|
|
class _RecordingGate:
|
|
def __init__(self, approve: bool):
|
|
self.approve = approve
|
|
self.calls: List[Dict[str, Any]] = []
|
|
|
|
def request(self, payload: Dict[str, Any]) -> bool:
|
|
self.calls.append(payload)
|
|
return self.approve
|
|
|
|
|
|
def _run(tmp_path, provider, gate):
|
|
ctx = ToolContext(tmp_path)
|
|
events: List[Dict[str, Any]] = []
|
|
messages: List[Dict[str, Any]] = [{"role": "user", "content": "do it"}]
|
|
run_code(provider, messages, ctx, gate, events.append)
|
|
return events
|
|
|
|
|
|
def test_write_file_consults_the_gate_and_honors_rejection(tmp_path):
|
|
provider = FakeProvider([
|
|
ScriptedTurn(tool_calls=[("write_file", {"path": "a.txt", "content": "hi"})]),
|
|
ScriptedTurn(text="done"),
|
|
])
|
|
gate = _RecordingGate(approve=False)
|
|
events = _run(tmp_path, provider, gate)
|
|
|
|
assert len(gate.calls) == 1 and gate.calls[0]["name"] == "write_file"
|
|
results = [e for e in events if e.get("type") == "tool_result"]
|
|
assert results[0]["ok"] is False
|
|
assert not (tmp_path / "a.txt").exists() # rejected, never actually written
|
|
|
|
|
|
def test_read_only_tool_never_consults_the_gate(tmp_path):
|
|
(tmp_path / "existing.txt").write_text("x", encoding="utf-8")
|
|
provider = FakeProvider([
|
|
ScriptedTurn(tool_calls=[("list_dir", {})]),
|
|
ScriptedTurn(text="done"),
|
|
])
|
|
gate = _RecordingGate(approve=False) # would reject if ever asked
|
|
events = _run(tmp_path, provider, gate)
|
|
|
|
assert gate.calls == []
|
|
results = [e for e in events if e.get("type") == "tool_result"]
|
|
assert results[0]["ok"] is True
|