feat: Codebase Test Generator — Fill Coverage Gaps (#667)

Add scripts/codebase_test_generator.py:
- AST analysis: finds all functions/methods in source files
- Coverage gap detection: identifies functions without tests
- Test generation: creates pytest test cases for each gap
- Priority: high (has return/raises), medium (public), low (private)
- Auto-generated markers for human review

Stats: 161 source files, 1219 functions, 873 coverage gaps found
Generated 50 tests: 14 pass, 30 skip (import), 6 fail (wrong args)

Usage:
  python scripts/codebase_test_generator.py --source . --output tests/test_genome_generated.py

scripts/codebase_test_generator.py

@@ -0,0 +1,290 @@
+#!/usr/bin/env python3
+"""Codebase Test Generator — Fill Coverage Gaps (#667)."""
+
+import ast
+import os
+import sys
+import argparse
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import Dict, List, Optional, Set, Tuple
+
+
+@dataclass
+class FunctionInfo:
+    name: str
+    module_path: str
+    class_name: Optional[str] = None
+    lineno: int = 0
+    args: List[str] = field(default_factory=list)
+    is_async: bool = False
+    is_private: bool = False
+    is_property: bool = False
+    docstring: Optional[str] = None
+    has_return: bool = False
+    raises: List[str] = field(default_factory=list)
+    decorators: List[str] = field(default_factory=list)
+
+    @property
+    def qualified_name(self):
+        if self.class_name:
+            return f"{self.class_name}.{self.name}"
+        return self.name
+
+    @property
+    def test_name(self):
+        safe_mod = self.module_path.replace("/", "_").replace(".py", "").replace("-", "_")
+        safe_cls = self.class_name + "_" if self.class_name else ""
+        return f"test_{safe_mod}_{safe_cls}{self.name}"
+
+
+@dataclass
+class CoverageGap:
+    func: FunctionInfo
+    reason: str
+    test_priority: int
+
+
+class SourceAnalyzer(ast.NodeVisitor):
+    def __init__(self, module_path: str):
+        self.module_path = module_path
+        self.functions: List[FunctionInfo] = []
+        self._class_stack: List[str] = []
+
+    def visit_ClassDef(self, node):
+        self._class_stack.append(node.name)
+        self.generic_visit(node)
+        self._class_stack.pop()
+
+    def visit_FunctionDef(self, node):
+        self._collect(node, False)
+        self.generic_visit(node)
+
+    def visit_AsyncFunctionDef(self, node):
+        self._collect(node, True)
+        self.generic_visit(node)
+
+    def _collect(self, node, is_async):
+        cls = self._class_stack[-1] if self._class_stack else None
+        args = [a.arg for a in node.args.args if a.arg not in ("self", "cls")]
+        has_ret = any(isinstance(c, ast.Return) and c.value for c in ast.walk(node))
+        raises = []
+        for c in ast.walk(node):
+            if isinstance(c, ast.Raise) and c.exc:
+                if isinstance(c.exc, ast.Call) and isinstance(c.exc.func, ast.Name):
+                    raises.append(c.exc.func.id)
+        decos = []
+        for d in node.decorator_list:
+            if isinstance(d, ast.Name): decos.append(d.id)
+            elif isinstance(d, ast.Attribute): decos.append(d.attr)
+        self.functions.append(FunctionInfo(
+            name=node.name, module_path=self.module_path, class_name=cls,
+            lineno=node.lineno, args=args, is_async=is_async,
+            is_private=node.name.startswith("_") and not node.name.startswith("__"),
+            is_property="property" in decos,
+            docstring=ast.get_docstring(node), has_return=has_ret,
+            raises=raises, decorators=decos))
+
+
+def analyze_file(filepath, base_dir):
+    module_path = os.path.relpath(filepath, base_dir)
+    try:
+        with open(filepath, "r", errors="replace") as f:
+            tree = ast.parse(f.read(), filename=filepath)
+    except (SyntaxError, UnicodeDecodeError):
+        return []
+    a = SourceAnalyzer(module_path)
+    a.visit(tree)
+    return a.functions
+
+
+def find_source_files(source_dir):
+    exclude = {"__pycache__", ".git", "venv", ".venv", "node_modules", ".tox", "build", "dist"}
+    files = []
+    for root, dirs, fs in os.walk(source_dir):
+        dirs[:] = [d for d in dirs if d not in exclude and not d.startswith(".")]
+        for f in fs:
+            if f.endswith(".py") and f != "__init__.py" and not f.startswith("test_"):
+                files.append(os.path.join(root, f))
+    return sorted(files)
+
+
+def find_existing_tests(test_dir):
+    existing = set()
+    for root, dirs, fs in os.walk(test_dir):
+        for f in fs:
+            if f.startswith("test_") and f.endswith(".py"):
+                try:
+                    with open(os.path.join(root, f)) as fh:
+                        tree = ast.parse(fh.read())
+                    for node in ast.walk(tree):
+                        if isinstance(node, ast.FunctionDef) and node.name.startswith("test_"):
+                            existing.add(node.name)
+                except (SyntaxError, UnicodeDecodeError):
+                    pass
+    return existing
+
+
+def identify_gaps(functions, existing_tests):
+    gaps = []
+    for func in functions:
+        if func.name.startswith("__") and func.name != "__init__":
+            continue
+        covered = func.name in str(existing_tests)
+        if not covered:
+            pri = 3 if func.is_private else (1 if (func.raises or func.has_return) else 2)
+            gaps.append(CoverageGap(func=func, reason="no test found", test_priority=pri))
+    gaps.sort(key=lambda g: (g.test_priority, g.func.module_path, g.func.name))
+    return gaps
+
+
+def generate_test(gap):
+    func = gap.func
+    lines = []
+    lines.append(f"    # AUTO-GENERATED -- review before merging")
+    lines.append(f"    # Source: {func.module_path}:{func.lineno}")
+    lines.append(f"    # Function: {func.qualified_name}")
+    lines.append("")
+    mod_imp = func.module_path.replace("/", ".").replace("-", "_").replace(".py", "")
+
+    call_args = []
+    for a in func.args:
+        if a in ("self", "cls"): continue
+        if "path" in a or "file" in a or "dir" in a: call_args.append(f"{a}='/tmp/test'")
+        elif "name" in a: call_args.append(f"{a}='test'")
+        elif "id" in a or "key" in a: call_args.append(f"{a}='test_id'")
+        elif "message" in a or "text" in a: call_args.append(f"{a}='test msg'")
+        elif "count" in a or "num" in a or "size" in a: call_args.append(f"{a}=1")
+        elif "flag" in a or "enabled" in a or "verbose" in a: call_args.append(f"{a}=False")
+        else: call_args.append(f"{a}=None")
+    args_str = ", ".join(call_args)
+
+    if func.is_async:
+        lines.append("    @pytest.mark.asyncio")
+    lines.append(f"    def {func.test_name}(self):")
+    lines.append(f'        """Test {func.qualified_name} -- auto-generated."""')
+
+    if func.class_name:
+        lines.append(f"        try:")
+        lines.append(f"            from {mod_imp} import {func.class_name}")
+        if func.is_private:
+            lines.append(f"            pytest.skip('Private method')")
+        elif func.is_property:
+            lines.append(f"            obj = {func.class_name}()")
+            lines.append(f"            _ = obj.{func.name}")
+        else:
+            if func.raises:
+                lines.append(f"            with pytest.raises(({', '.join(func.raises)})):")
+                lines.append(f"                {func.class_name}().{func.name}({args_str})")
+            else:
+                lines.append(f"            obj = {func.class_name}()")
+                lines.append(f"            result = obj.{func.name}({args_str})")
+                if func.has_return:
+                    lines.append(f"            assert result is not None or result is None  # Placeholder")
+        lines.append(f"        except ImportError:")
+        lines.append(f"            pytest.skip('Module not importable')")
+    else:
+        lines.append(f"        try:")
+        lines.append(f"            from {mod_imp} import {func.name}")
+        if func.is_private:
+            lines.append(f"            pytest.skip('Private function')")
+        else:
+            if func.raises:
+                lines.append(f"            with pytest.raises(({', '.join(func.raises)})):")
+                lines.append(f"                {func.name}({args_str})")
+            else:
+                lines.append(f"            result = {func.name}({args_str})")
+                if func.has_return:
+                    lines.append(f"            assert result is not None or result is None  # Placeholder")
+        lines.append(f"        except ImportError:")
+        lines.append(f"            pytest.skip('Module not importable')")
+
+    return chr(10).join(lines)
+
+
+def generate_test_suite(gaps, max_tests=50):
+    by_module = {}
+    for gap in gaps[:max_tests]:
+        by_module.setdefault(gap.func.module_path, []).append(gap)
+
+    lines = []
+    lines.append('"""Auto-generated test suite -- Codebase Genome (#667).')
+    lines.append("")
+    lines.append("Generated by scripts/codebase_test_generator.py")
+    lines.append("Coverage gaps identified from AST analysis.")
+    lines.append("")
+    lines.append("These tests are starting points. Review before merging.")
+    lines.append('"""')
+    lines.append("")
+    lines.append("import pytest")
+    lines.append("from unittest.mock import MagicMock, patch")
+    lines.append("")
+    lines.append("")
+    lines.append("# AUTO-GENERATED -- DO NOT EDIT WITHOUT REVIEW")
+
+    for module, mgaps in sorted(by_module.items()):
+        safe = module.replace("/", "_").replace(".py", "").replace("-", "_")
+        cls_name = "".join(w.title() for w in safe.split("_"))
+        lines.append("")
+        lines.append(f"class Test{cls_name}Generated:")
+        lines.append(f'    """Auto-generated tests for {module}."""')
+        for gap in mgaps:
+            lines.append("")
+            lines.append(generate_test(gap))
+        lines.append("")
+
+    return chr(10).join(lines)
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Codebase Test Generator")
+    parser.add_argument("--source", default=".")
+    parser.add_argument("--output", default="tests/test_genome_generated.py")
+    parser.add_argument("--max-tests", type=int, default=50)
+    parser.add_argument("--dry-run", action="store_true")
+    parser.add_argument("--include-private", action="store_true")
+    args = parser.parse_args()
+
+    source_dir = os.path.abspath(args.source)
+    test_dir = os.path.join(source_dir, "tests")
+
+    print(f"Scanning: {source_dir}")
+    source_files = find_source_files(source_dir)
+    print(f"Source files: {len(source_files)}")
+
+    all_funcs = []
+    for f in source_files:
+        all_funcs.extend(analyze_file(f, source_dir))
+    print(f"Functions/methods: {len(all_funcs)}")
+
+    existing = find_existing_tests(test_dir)
+    print(f"Existing tests: {len(existing)}")
+
+    gaps = identify_gaps(all_funcs, existing)
+    if not args.include_private:
+        gaps = [g for g in gaps if not g.func.is_private]
+    print(f"Coverage gaps: {len(gaps)}")
+
+    by_pri = {1: 0, 2: 0, 3: 0}
+    for g in gaps:
+        by_pri[g.test_priority] += 1
+    print(f"  High: {by_pri[1]}, Medium: {by_pri[2]}, Low: {by_pri[3]}")
+
+    if args.dry_run:
+        for g in gaps[:10]:
+            print(f"  {g.func.module_path}:{g.func.lineno} {g.func.qualified_name}")
+        return
+
+    if gaps:
+        content = generate_test_suite(gaps, max_tests=args.max-tests if hasattr(args, 'max-tests') else args.max_tests)
+        out = os.path.join(source_dir, args.output)
+        os.makedirs(os.path.dirname(out), exist_ok=True)
+        with open(out, "w") as f:
+            f.write(content)
+        print(f"Generated {min(len(gaps), args.max_tests)} tests -> {args.output}")
+    else:
+        print("No gaps found!")
+
+
+if __name__ == "__main__":
+    main()