Files
turnstone/tests/test_sandbox.py
Patrick Buckley 9be155b97a Quality overhaul: code tooling, CI/CD, architecture diagrams, UI rede… (#1)
* Quality overhaul: code tooling, CI/CD, architecture diagrams, UI redesign, and legacy cleanup

- Add ruff (lint+format) and mypy (strict) with zero errors across 37 source files
- Add GitHub Actions CI (lint, typecheck, test matrix 3.11/3.12/3.13) and PyPI publish workflow
- Create 12 PlantUML architecture diagrams with PNG renders covering all subsystems
- Refresh README and docs with badges, diagram links, and current descriptions
- Refactor test_server_live.py with mock streaming helpers for deterministic CI testing
- Update dependencies to current versions (openai>=2.24, httpx>=0.28, redis>=7.2)

Console dashboard:
- Move state indicators from top cards to fixed bottom status bar with cluster metrics
- Replace flat 50-node list with hostname-prefix grouped nodes (expand/collapse, up to 1000)
- Apply "Instrument Panel" visual redesign: IBM Plex Mono + Outfit fonts, warm amber accent,
  LED glow state indicators, deep charcoal surfaces, WCAG AA contrast compliance
- Add render cache, stale indicator, active filter highlight, loading states

Server web UI:
- Apply matching Instrument Panel aesthetic for visual consistency with console
- Fix branding (pcode → turnstone), extract inline styles to CSS classes
- Rename pcode localStorage keys and history state to turnstone

Legacy cleanup:
- Remove persona-model-specific --persona flag and /persona slash command
- Remove model_identity from chat_template_kwargs (vLLM-specific mechanism)
- Refactor plan agent to use standard developer message instead of model_identity
- Remove dead code (unused date/has_tools variables, noqa suppressions)

* Fix CI typecheck: add mypy overrides for optional sympy/numpy imports

The math sandbox optionally imports sympy and numpy at runtime (try/except
ImportError). In CI these packages are not installed, so mypy raises
import-not-found rather than import-untyped. Add mypy overrides to
ignore missing imports for these optional dependencies.

* Fix Copilot review findings: ARIA role, status bar cache, and pulse opacity

- Change #node-table from role="tree" to role="list" and group elements
  from role="treeitem" to role="listitem" (proper ARIA semantics)
- Include currentView and currentFilter.state in renderStatusBar cache key
  so active pill highlight updates when switching views
- Align pulse animation to 0.35 opacity (already applied in CSS)
2026-03-02 16:55:12 -08:00

100 lines
3.1 KiB
Python

"""Tests for turnstone.core.sandbox — validate_math_code and auto_print_wrap."""
from turnstone.core.sandbox import auto_print_wrap, validate_math_code
class TestValidateMathCode:
def test_safe_code_no_errors(self):
assert validate_math_code("x = 1 + 2\nprint(x)") == []
def test_safe_math_import(self):
assert validate_math_code("import math\nprint(math.pi)") == []
def test_blocked_import_os(self):
errors = validate_math_code("import os")
assert len(errors) == 1
assert "os" in errors[0]
def test_blocked_import_sys(self):
errors = validate_math_code("import sys")
assert len(errors) == 1
assert "sys" in errors[0]
def test_blocked_import_subprocess(self):
errors = validate_math_code("import subprocess")
assert len(errors) == 1
assert "subprocess" in errors[0]
def test_blocked_from_import(self):
errors = validate_math_code("from os.path import join")
assert len(errors) == 1
assert "os" in errors[0]
def test_blocked_builtin_exec(self):
errors = validate_math_code("exec('print(1)')")
assert len(errors) == 1
assert "exec" in errors[0]
def test_blocked_builtin_eval(self):
errors = validate_math_code("eval('1+1')")
assert len(errors) == 1
assert "eval" in errors[0]
def test_blocked_builtin_open(self):
errors = validate_math_code("open('file.txt')")
assert len(errors) == 1
assert "open" in errors[0]
def test_blocked_dunder_access(self):
errors = validate_math_code("x.__dict__")
assert len(errors) == 1
assert "__dict__" in errors[0]
def test_allowed_dunder_name(self):
# __name__, __doc__, __class__ are allowed
assert validate_math_code("print(int.__name__)") == []
def test_syntax_error_caught(self):
errors = validate_math_code("def f(\n")
assert len(errors) == 1
assert "Syntax error" in errors[0]
def test_multiple_violations(self):
code = "import os\nimport sys\nexec('x')"
errors = validate_math_code(code)
assert len(errors) == 3
class TestAutoPrintWrap:
def test_bare_expression_wrapped(self):
result = auto_print_wrap("1 + 2")
assert "print(" in result
assert "1 + 2" in result
def test_assignment_not_wrapped(self):
code = "x = 1 + 2"
assert auto_print_wrap(code) == code
def test_code_with_print_not_wrapped(self):
code = "x = 1\nprint(x)"
assert auto_print_wrap(code) == code
def test_code_with_result_assignment_not_wrapped(self):
code = "result = 42"
assert auto_print_wrap(code) == code
def test_multiline_with_bare_expression_last(self):
code = "x = 2\ny = 3\nx + y"
result = auto_print_wrap(code)
assert "print(" in result
# The assignments should still be there
assert "x = 2" in result
assert "y = 3" in result
def test_empty_code(self):
assert auto_print_wrap("") == ""
def test_syntax_error_returns_original(self):
code = "def f(\n"
assert auto_print_wrap(code) == code