claude-dev-env 8.2.0 → 8.4.0

package/hooks/observability/test_test_failure_recorder.py

@@ -1,173 +0,0 @@
-"""Behavior tests for the test_failure_recorder PostToolUse hook.
-
-Drives the hook's main through real stdin payloads shaped like a genuine
-Bash PostToolUse call, then reads the shared content-hash store back to
-confirm what -- if anything -- it recorded. The store's real state file
-under the OS temp directory is read directly, the same way
-test_content_hash_store.py and test_tdd_enforcer.py already do, rather than
-mocking tempfile.gettempdir. ``hooks/conftest.py`` already puts the hooks
-and blocking directories on sys.path for test collection, so this file needs
-no bootstrap of its own before importing content_hash_store.
-"""
-
-import contextlib
-import importlib.util
-import io
-import json
-from pathlib import Path
-from unittest import mock
-
-from tdd_enforcer_parts import content_hash_store
-
-_HOOK_DIRECTORY = Path(__file__).parent
-_hook_spec = importlib.util.spec_from_file_location(
-    "test_failure_recorder_under_test", _HOOK_DIRECTORY / "test_failure_recorder.py"
-)
-assert _hook_spec is not None
-assert _hook_spec.loader is not None
-_hook_module = importlib.util.module_from_spec(_hook_spec)
-_hook_spec.loader.exec_module(_hook_module)
-
-
-def _run_hook_with_payload(payload: dict) -> None:
-    with (
-        mock.patch("sys.stdin", io.StringIO(json.dumps(payload))),
-        contextlib.suppress(SystemExit),
-    ):
-        _hook_module.main()
-
-
-def _recorded_failure_entry(test_file: Path, session_id: str, repository_root: str) -> dict | None:
-    state_file = content_hash_store._state_file_path(session_id, repository_root)
-    if not state_file.exists():
-        return None
-    state = json.loads(state_file.read_text())
-    return state.get(content_hash_store._state_key_for(test_file))
-
-
-def _bash_payload(command: str, tool_response: object, cwd: Path, session_id: str) -> dict:
-    return {
-        "session_id": session_id,
-        "cwd": str(cwd),
-        "tool_name": "Bash",
-        "tool_input": {"command": command},
-        "tool_response": tool_response,
-    }
-
-
-_FAILING_OUTPUT = (
-    "Error: Exit code 1\n"
-    "F                                                                    [100%]\n"
-    "=================================== FAILURES ===================================\n"
-    "FAILED test_orders.py::test_fulfill - AssertionError\n"
-    "1 failed in 0.02s"
-)
-_PASSING_OUTPUT = {"stdout": "1 passed in 0.02s", "stderr": "", "interrupted": False}
-
-
-def test_records_a_failure_for_a_bare_pytest_command_naming_a_real_file(
-    tmp_path: Path,
-) -> None:
-    test_file = tmp_path / "test_orders.py"
-    test_file.write_text("def test_fulfill(): assert False\n")
-    session_id = "recorder-session-1"
-
-    _run_hook_with_payload(
-        _bash_payload("pytest test_orders.py", _FAILING_OUTPUT, tmp_path, session_id)
-    )
-
-    entry = _recorded_failure_entry(test_file, session_id, str(tmp_path))
-    assert entry is not None
-    assert entry[content_hash_store.STORED_FAILURE_EXIT_STATUS_KEY] == 1
-    assert entry[content_hash_store.STORED_FAILURE_COMMAND_KEY] == "pytest test_orders.py"
-
-
-def test_does_not_record_for_a_passing_command(tmp_path: Path) -> None:
-    test_file = tmp_path / "test_orders.py"
-    test_file.write_text("def test_fulfill(): pass\n")
-    session_id = "recorder-session-2"
-
-    _run_hook_with_payload(
-        _bash_payload("pytest test_orders.py", _PASSING_OUTPUT, tmp_path, session_id)
-    )
-
-    assert _recorded_failure_entry(test_file, session_id, str(tmp_path)) is None
-
-
-def test_does_not_record_for_a_non_pytest_command(tmp_path: Path) -> None:
-    test_file = tmp_path / "test_orders.py"
-    test_file.write_text("def test_fulfill(): assert False\n")
-    session_id = "recorder-session-3"
-
-    _run_hook_with_payload(
-        _bash_payload("npm test", "Error: Exit code 1\n1 failing", tmp_path, session_id)
-    )
-
-    assert _recorded_failure_entry(test_file, session_id, str(tmp_path)) is None
-
-
-def test_does_not_record_for_a_chained_command(tmp_path: Path) -> None:
-    test_file = tmp_path / "test_orders.py"
-    test_file.write_text("def test_fulfill(): assert False\n")
-    session_id = "recorder-session-4"
-
-    _run_hook_with_payload(
-        _bash_payload("cd /repo && pytest test_orders.py", _FAILING_OUTPUT, tmp_path, session_id)
-    )
-
-    assert _recorded_failure_entry(test_file, session_id, str(tmp_path)) is None
-
-
-def test_does_not_record_for_a_bare_pytest_run_with_no_path_argument(
-    tmp_path: Path,
-) -> None:
-    test_file = tmp_path / "test_orders.py"
-    test_file.write_text("def test_fulfill(): assert False\n")
-    session_id = "recorder-session-5"
-
-    _run_hook_with_payload(_bash_payload("pytest -q", _FAILING_OUTPUT, tmp_path, session_id))
-
-    assert _recorded_failure_entry(test_file, session_id, str(tmp_path)) is None
-
-
-def test_records_only_the_named_file_not_an_option_or_expression_token(
-    tmp_path: Path,
-) -> None:
-    test_file = tmp_path / "test_orders.py"
-    test_file.write_text("def test_fulfill(): assert False\n")
-    session_id = "recorder-session-6"
-
-    _run_hook_with_payload(
-        _bash_payload("pytest test_orders.py -k fulfill", _FAILING_OUTPUT, tmp_path, session_id)
-    )
-
-    entry = _recorded_failure_entry(test_file, session_id, str(tmp_path))
-    assert entry is not None
-    state_file = content_hash_store._state_file_path(session_id, str(tmp_path))
-    state = json.loads(state_file.read_text())
-    assert len(state) == 1
-
-
-def test_ignores_a_tool_other_than_bash(tmp_path: Path) -> None:
-    test_file = tmp_path / "test_orders.py"
-    test_file.write_text("def test_fulfill(): assert False\n")
-    session_id = "recorder-session-7"
-    payload = _bash_payload("pytest test_orders.py", _FAILING_OUTPUT, tmp_path, session_id)
-    payload["tool_name"] = "Write"
-
-    _run_hook_with_payload(payload)
-
-    assert _recorded_failure_entry(test_file, session_id, str(tmp_path)) is None
-
-
-def test_does_not_record_when_the_named_file_does_not_exist_on_disk(
-    tmp_path: Path,
-) -> None:
-    session_id = "recorder-session-8"
-    missing_file = tmp_path / "test_missing.py"
-
-    _run_hook_with_payload(
-        _bash_payload("pytest test_missing.py", _FAILING_OUTPUT, tmp_path, session_id)
-    )
-
-    assert _recorded_failure_entry(missing_file, session_id, str(tmp_path)) is None

package/hooks/validators/VALIDATION_REPORT.md

@@ -1,287 +0,0 @@
-# Test Safety Checks Validator - Comprehensive Validation Report
-
-## Executive Summary
-
-**Critical Gaps Found: 2**
-**Minor Issues: 1**
-**Tests Passed: 14/17**
-
----
-
-## Check 1: No Skip Decorators
-
-### Test Results
-
-| Test Case | Expected | Result | Status |
-|-----------|----------|--------|--------|
-| `@skip` | CAUGHT | CAUGHT | PASS |
-| `@pytest.mark.skipif(...)` | CAUGHT | CAUGHT | PASS |
-| `@unittest.skipIf(...)` | CAUGHT | CAUGHT | PASS |
-| `@skip()` with parentheses | CAUGHT | CAUGHT | PASS |
-| `@pytest.mark.xfail` | ALLOWED | ALLOWED | PASS |
-| `@skip_on_windows` custom | ALLOWED | ALLOWED | PASS |
-| `@Skip` (capital S) | CAUGHT | **ALLOWED** | **FAIL** |
-| `@unittest.skipUnless(...)` | CAUGHT | CAUGHT | PASS |
-| `@pytest.mark.skip` (no args) | CAUGHT | CAUGHT | PASS |
-
-### GAP #1: Case-Sensitive Decorator Matching
-
-**Severity: MEDIUM**
-
-**Issue:** The validator uses case-sensitive matching, so `@Skip` (capital S) is NOT caught.
-
-**Current Code (lines 16-22):**
-```python
-SKIP_DECORATOR_NAMES = frozenset([
-    "skip",
-    "skipif",
-    "skipunless",
-    "skipIf",
-    "skipUnless",
-])
-```
-
-**Problem:** This misses decorators with different capitalization like `@Skip`, `@SkipIf`, `@SKIP`, etc.
-
-**Recommended Fix:**
-```python
-def _get_decorator_name(decorator: ast.expr) -> str:
-    """Extract the name from a decorator node (lowercase for comparison)."""
-    # ... existing logic ...
-    return name.lower()  # Convert to lowercase for case-insensitive matching
-```
-
-Then update the frozenset to all lowercase:
-```python
-SKIP_DECORATOR_NAMES = frozenset([
-    "skip",
-    "skipif",
-    "skipunless",
-])
-```
-
-**Impact:** Currently allows `@Skip`, `@SkipIf`, `@SkipUnless` to slip through.
-
----
-
-## Check 2: DEBUG Guard in Management Commands
-
-### Test Results
-
-| Test Case | Expected | Result | Status |
-|-----------|----------|--------|--------|
-| No DEBUG check | CAUGHT | CAUGHT | PASS |
-| `if not settings.DEBUG: raise` | ALLOWED | ALLOWED | PASS |
-| `if not settings.DEBUG: return` | ALLOWED | ALLOWED | PASS |
-| Using imported `DEBUG` variable | CAUGHT | CAUGHT | PASS |
-| DEBUG check in helper function | CAUGHT | CAUGHT | PASS |
-| DEBUG check after 5 statements | CAUGHT | CAUGHT | PASS |
-| `if settings.DEBUG: ... else: raise` | ALLOWED | **CAUGHT** | **FAIL** |
-| `if not settings.DEBUG and X:` | DEBATABLE | CAUGHT | WARN |
-| File not in `management/commands/` | IGNORED | IGNORED | PASS |
-
-### GAP #2: Positive DEBUG Check Pattern Rejected
-
-**Severity: HIGH**
-
-**Issue:** The validator incorrectly rejects the pattern `if settings.DEBUG: ... else: raise`.
-
-**Test File:** `cmd_07_positive_debug_check.py`
-```python
-def handle(self, *args, **options):
-    if settings.DEBUG:
-        print("Running in DEBUG mode")
-    else:
-        raise CommandError("This command can only be run in DEBUG mode")
-```
-
-**Expected:** ALLOWED (this is a valid DEBUG guard)
-**Actual:** CAUGHT (flagged as violation)
-
-**Root Cause (lines 186-187):**
-```python
-if _is_debug_check(test) and stmt.orelse:
-    return False  # This returns False when it should return True!
-```
-
-**The Logic Flaw:**
-- Line 186: Detects `if settings.DEBUG:` and checks if there's an `else` clause
-- Line 187: Returns `False` (no DEBUG guard found)
-- **BUG:** This should return `True` because the pattern IS a valid guard!
-
-**Recommended Fix:**
-```python
-def _has_debug_guard(func: ast.FunctionDef) -> bool:
-    """Check if a function has a settings.DEBUG guard at the start."""
-    if not func.body:
-        return False
-
-    for stmt in func.body[:5]:
-        if isinstance(stmt, ast.If):
-            test = stmt.test
-
-            # Pattern 1: if not settings.DEBUG: raise/return
-            if isinstance(test, ast.UnaryOp) and isinstance(test.op, ast.Not):
-                if _is_debug_check(test.operand):
-                    return True
-
-            # Pattern 2: if settings.DEBUG: ... else: raise/return
-            if _is_debug_check(test):
-                if stmt.orelse:
-                    # Check if else clause has raise/return
-                    if _has_early_exit(stmt.orelse):
-                        return True
-                # if settings.DEBUG: with no else is also valid
-                return True
-
-    return False
-
-
-def _has_early_exit(statements: List[ast.stmt]) -> bool:
-    """Check if statements contain raise or return."""
-    for stmt in statements:
-        if isinstance(stmt, (ast.Raise, ast.Return)):
-            return True
-        # Check nested if/else
-        if isinstance(stmt, ast.If):
-            if _has_early_exit(stmt.body) or (stmt.orelse and _has_early_exit(stmt.orelse)):
-                return True
-    return False
-```
-
-**Impact:** Currently REJECTS valid DEBUG guard patterns, forcing developers to use only negative checks.
-
-### MINOR ISSUE: Complex Boolean Expressions
-
-**Severity: LOW**
-
-**Issue:** The validator rejects `if not settings.DEBUG and other_condition:`.
-
-**Test File:** `cmd_08_debug_with_and.py`
-```python
-if not settings.DEBUG and True:
-    raise CommandError("This command can only be run in DEBUG mode")
-```
-
-**Expected:** DEBATABLE (could be allowed if DEBUG is the primary condition)
-**Actual:** CAUGHT (flagged as violation)
-
-**Analysis:**
-- Current code only checks for simple `UnaryOp(Not)` with `settings.DEBUG`
-- Doesn't handle `BoolOp` (and/or) expressions
-- This is arguably correct behavior - keeps the check simple and strict
-
-**Recommendation:** Document this limitation. Developers should use:
-```python
-if not settings.DEBUG:
-    raise CommandError("...")
-# Then check other conditions separately
-```
-
----
-
-## Additional Edge Cases Tested
-
-### Nested Directory Structure
-- File in `management/commands/subdir/command.py` - NOT tested
-- **Recommendation:** Add test case to verify path matching works with subdirectories
-
-### File Encoding Issues
-- Files with syntax errors - Handled gracefully (returns empty violations)
-- Files that don't exist - Handled with error message
-
-### Multiple Commands in One File
-- NOT tested
-- **Recommendation:** Add test case with multiple Command classes in one file
-
----
-
-## Recommended Priority Fixes
-
-1. **HIGH PRIORITY:** Fix GAP #2 (positive DEBUG check pattern)
-   - Current behavior rejects valid code
-   - Breaking change for developers using this pattern
-
-2. **MEDIUM PRIORITY:** Fix GAP #1 (case-sensitive skip decorators)
-   - Low probability but easy to fix
-   - Prevents trivial evasion
-
-3. **LOW PRIORITY:** Add test for nested management commands
-   - Verify path matching works with subdirectories
-
----
-
-## Test Coverage Summary
-
-**Skip Decorators:**
-- Simple decorators: TESTED
-- Attribute decorators: TESTED
-- Called decorators: TESTED
-- Case variations: **GAP FOUND**
-- Custom decorators: TESTED (correctly allowed)
-
-**DEBUG Guards:**
-- No check: TESTED
-- Negative check (`if not`): TESTED
-- Positive check (`if ... else`): **GAP FOUND**
-- Imported DEBUG: TESTED (correctly rejected)
-- Helper function: TESTED (correctly rejected)
-- Late check (>5 statements): TESTED (correctly rejected)
-- Path matching: TESTED
-- Complex boolean: TESTED (debatable behavior)
-
----
-
-## Files Created for Testing
-
-### Skip Decorators (9 files)
-```
-test_files/skip_decorators/
-├── test_01_simple_skip.py
-├── test_02_pytest_skipif.py
-├── test_03_unittest_skipIf.py
-├── test_04_skip_with_parens.py
-├── test_05_xfail.py
-├── test_06_custom_skip.py
-├── test_07_capital_Skip.py (GAP)
-├── test_08_skipUnless.py
-└── test_09_pytest_mark_skip_simple.py
-```
-
-### Management Commands (9 files)
-```
-test_files/management/commands/
-├── cmd_01_no_debug_check.py
-├── cmd_02_proper_debug_check.py
-├── cmd_03_debug_check_with_return.py
-├── cmd_04_imported_DEBUG.py
-├── cmd_05_debug_check_in_helper.py
-├── cmd_06_debug_check_late.py
-├── cmd_07_positive_debug_check.py (GAP)
-├── cmd_08_debug_with_and.py
-test_files/
-└── not_management_command.py
-```
-
----
-
-## Conclusion
-
-The validator is **mostly effective** but has **2 critical gaps**:
-
-1. **Case-sensitive decorator matching** - Easy fix, low impact
-2. **Positive DEBUG check rejection** - HIGH PRIORITY, rejects valid code
-
-The implementation correctly handles:
-- Most skip decorator patterns
-- Simple DEBUG guard patterns
-- Path filtering for management commands
-- Graceful error handling
-
-**Overall Assessment: 82% effective (14/17 test cases passed)**
-
-**Action Required:**
-1. Fix GAP #2 immediately (breaking valid code)
-2. Fix GAP #1 for completeness
-3. Add test for nested management command directories
-4. Document the complex boolean limitation

package/hooks/validators/validator_defaults.py

@@ -1,5 +0,0 @@
-"""Shared constants for the validators package."""
-
-# pragma: no-tdd-gate
-
-DEFAULT_BASE_BRANCH_WHEN_UNKNOWN = "main"