Files
cowork-local/tests/unit/test_tool_registry_and_policy.py
f9f6bc01fd
CI / test (push) Canceled after 0s
Feature/delta team/epic r04 (#7)
## 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>
2026-08-31 05:15:13 +00:00

108 lines
4.6 KiB
Python

"""Unit tests for EPIC R05: the tool descriptor/registry (R05-T01), the split
built-in handlers (R05-T02), and the policy gateway (R05-T03).
The gateway tests assert the SAME capability set each engine used to hard-code
as a name tuple still gets gated after the switch to capability lookup — that
equivalence is the whole point of R05-T03, not an incidental detail.
"""
from __future__ import annotations
from typing import Any, Dict
import pytest
from cowork_local.application.conversations import ToolPolicyGateway
from cowork_local.core.tools import TOOL_SPECS, ToolContext, execute_tool
from cowork_local.domain.tools import ToolCapability, ToolDescriptor, default_registry
# --------------------------------------------------------------------------- #
# R05-T01 - ToolDescriptor / ToolRegistry
# --------------------------------------------------------------------------- #
def test_capability_flags_compose():
install = ToolDescriptor("install_package", "", {}, ToolCapability.WRITE | ToolCapability.EXECUTE)
assert install.has(ToolCapability.WRITE)
assert install.has(ToolCapability.EXECUTE)
assert not install.has(ToolCapability.NETWORK)
def test_default_registry_matches_todays_hardcoded_gating_sets():
"""The two literal sets this EPIC replaces:
``core/tools.py::WRITE_TOOLS`` and ``core/chat_agent.py``'s
``("run_command", "install_package")`` tuple. The registry must agree
with both, or the capability switch silently changes who gets gated."""
registry = default_registry(TOOL_SPECS)
execute_gated = {d.name for d in registry.all() if d.has(ToolCapability.EXECUTE)}
assert execute_gated == {"run_command", "install_package"}
write_gated = {d.name for d in registry.all() if d.has(ToolCapability.WRITE)}
assert write_gated == {"write_file", "edit_file", "install_package"}
def test_unregistered_tool_has_no_capabilities():
registry = default_registry(TOOL_SPECS)
assert registry.capabilities_for("no_such_tool") is ToolCapability.NONE
# --------------------------------------------------------------------------- #
# R05-T02 - core/tools.py dispatch, now built from the split infra modules
# --------------------------------------------------------------------------- #
def test_execute_tool_still_dispatches_every_built_in(tmp_path):
ctx = ToolContext(tmp_path)
written = execute_tool(ctx, "write_file", {"path": "a.txt", "content": "hi"})
assert written["ok"] is True
read = execute_tool(ctx, "read_file", {"path": "a.txt"})
assert read == {"ok": True, "output": "hi"}
edited = execute_tool(ctx, "edit_file", {"path": "a.txt", "old_string": "hi", "new_string": "bye"})
assert edited["ok"] is True
assert execute_tool(ctx, "read_file", {"path": "a.txt"})["output"] == "bye"
listing = execute_tool(ctx, "list_dir", {})
assert listing["ok"] is True and "a.txt" in listing["output"]
def test_execute_tool_reports_unknown_name(tmp_path):
ctx = ToolContext(tmp_path)
result = execute_tool(ctx, "not_a_real_tool", {})
assert result == {"ok": False, "output": "Tool not found: not_a_real_tool"}
# --------------------------------------------------------------------------- #
# R05-T03 - ToolPolicyGateway
# --------------------------------------------------------------------------- #
class _RecordingGate:
def __init__(self, approve: bool):
self.approve = approve
self.calls: list = []
def request(self, payload: Dict[str, Any]) -> bool:
self.calls.append(payload)
return self.approve
@pytest.fixture
def cowork_policy() -> ToolPolicyGateway:
"""Same construction as ``core/chat_agent.py``'s module-level
``_COWORK_TOOL_POLICY`` - EXECUTE is exactly what Cowork used to gate via
the literal ``("run_command", "install_package")`` tuple."""
return ToolPolicyGateway(default_registry(TOOL_SPECS), ToolCapability.EXECUTE)
def test_no_gate_means_auto_run(cowork_policy):
assert cowork_policy.allow("run_command", None, {}) is True
def test_read_only_tool_never_asks_the_gate(cowork_policy):
gate = _RecordingGate(approve=False) # would reject if asked
assert cowork_policy.allow("write_file", gate, {}) is True
assert gate.calls == [] # never consulted - write_file isn't EXECUTE
def test_gated_capability_consults_the_gate_and_honors_its_answer(cowork_policy):
approving = _RecordingGate(approve=True)
assert cowork_policy.allow("run_command", approving, {"name": "run_command"}) is True
assert approving.calls == [{"name": "run_command"}]
rejecting = _RecordingGate(approve=False)
assert cowork_policy.allow("install_package", rejecting, {}) is False