feat: implement tddai Python library for TDD workspace management

- Create comprehensive tddai package with workspace, issue fetcher, and test generator modules
- Add Python CLI interface (tddai_cli.py) to replace complex Makefile shell logic
- Update Makefile targets to use Python CLI for better maintainability
- Implement proper behavior-based tests instead of file existence checks
- Add workspace lifecycle management (create, active, finish, cleanup)
- Add issue fetching from Gitea API with error handling
- Add comprehensive test coverage with 19 passing tests
- Support environment variable configuration for different deployments

This addresses issue #11: Setup TDD workspace infrastructure
All tests pass and the system achieves green state before commit.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

tddai/test_generator.py

@@ -0,0 +1,163 @@
+"""
+Test generation with AI assistance.
+"""
+
+import subprocess
+import tempfile
+from pathlib import Path
+from typing import Optional
+
+from .config import get_config
+from .workspace import WorkspaceManager
+from .exceptions import TestGenerationError
+
+
+class TestGenerator:
+    """Generates tests using AI assistance."""
+
+    def __init__(self, config=None):
+        self.config = config or get_config()
+        self.workspace_manager = WorkspaceManager(config)
+
+    def generate_test(self, scenario_name: str, test_description: str) -> Path:
+        """Generate a test file for the current workspace issue."""
+        workspace = self.workspace_manager.get_current_workspace()
+        if not workspace:
+            raise TestGenerationError("No active workspace found")
+
+        # Create test file name
+        test_filename = self.config.test_file_pattern.format(
+            issue_num=workspace.issue_number,
+            scenario=scenario_name.lower().replace(' ', '_').replace('-', '_')
+        )
+        test_file_path = workspace.tests_dir / test_filename
+
+        # Generate test prompt
+        prompt = self._create_test_prompt(workspace, scenario_name, test_description)
+
+        # Use Claude Code to generate the test
+        try:
+            with tempfile.NamedTemporaryFile(mode='w', suffix='.md', delete=False) as f:
+                f.write(prompt)
+                prompt_file = Path(f.name)
+
+            result = subprocess.run(
+                [self.config.claude_code_command, '--file', str(prompt_file)],
+                cwd=workspace.workspace_dir,
+                capture_output=True,
+                text=True
+            )
+
+            prompt_file.unlink()  # Clean up temp file
+
+            if result.returncode != 0:
+                raise TestGenerationError(f"Claude Code failed: {result.stderr}")
+
+            # Extract Python code from Claude's response
+            test_content = self._extract_test_code(result.stdout)
+
+            # Write test file
+            test_file_path.write_text(test_content)
+
+            # Update test plan
+            self._update_test_plan(workspace, scenario_name, test_filename)
+
+            return test_file_path
+
+        except subprocess.CalledProcessError as e:
+            raise TestGenerationError(f"Failed to generate test: {e}")
+        except Exception as e:
+            raise TestGenerationError(f"Test generation error: {e}")
+
+    def _create_test_prompt(self, workspace, scenario_name: str, test_description: str) -> str:
+        """Create prompt for Claude Code to generate test."""
+        return f"""# Test Generation Request
+
+## Context
+- Issue #{workspace.issue_number}: {workspace.issue_title}
+- Scenario: {scenario_name}
+
+## Issue Description
+{workspace.issue_body}
+
+## Test Requirements
+{test_description}
+
+## Instructions
+Please generate a comprehensive Python test file that:
+
+1. Tests the behavior described in the scenario
+2. Follows pytest conventions
+3. Includes proper docstrings and comments
+4. Tests both positive and negative cases
+5. Uses meaningful test method names
+6. Includes appropriate assertions
+
+The test should focus on behavior verification rather than implementation details.
+
+## Expected Output
+Please provide only the Python test code without any additional explanation.
+The code should be ready to save as `{self.config.test_file_pattern.format(issue_num=workspace.issue_number, scenario=scenario_name.lower().replace(' ', '_'))}`
+"""
+
+    def _extract_test_code(self, claude_response: str) -> str:
+        """Extract Python test code from Claude's response."""
+        lines = claude_response.split('\n')
+        code_lines = []
+        in_code_block = False
+
+        for line in lines:
+            if line.strip().startswith('```python'):
+                in_code_block = True
+                continue
+            elif line.strip() == '```' and in_code_block:
+                break
+            elif in_code_block:
+                code_lines.append(line)
+
+        if not code_lines:
+            # If no code block found, assume entire response is code
+            return claude_response.strip()
+
+        return '\n'.join(code_lines)
+
+    def _update_test_plan(self, workspace, scenario_name: str, test_filename: str) -> None:
+        """Update the test plan with the new test."""
+        test_plan_content = workspace.test_plan_file.read_text()
+
+        # Add test to the generated tests section
+        new_entry = f"- [x] {scenario_name} (`{test_filename}`)"
+
+        if "### Generated Tests" in test_plan_content:
+            # Add to existing generated tests section
+            lines = test_plan_content.split('\n')
+            for i, line in enumerate(lines):
+                if line.strip() == "Tests generated for this workspace will be listed here as they are created.":
+                    lines[i] = new_entry
+                    break
+                elif line.startswith("- [") and "Generated Tests" in lines[max(0, i-5):i]:
+                    lines.insert(i, new_entry)
+                    break
+            else:
+                # Add at the end of generated tests section
+                for i, line in enumerate(lines):
+                    if "### Generated Tests" in line:
+                        # Find next section or end
+                        j = i + 1
+                        while j < len(lines) and not lines[j].startswith('##'):
+                            j += 1
+                        lines.insert(j, new_entry)
+                        break
+
+            workspace.test_plan_file.write_text('\n'.join(lines))
+
+    def list_generated_tests(self) -> list:
+        """List all generated tests for the current workspace."""
+        workspace = self.workspace_manager.get_current_workspace()
+        if not workspace:
+            return []
+
+        if not workspace.tests_dir.exists():
+            return []
+
+        return list(workspace.tests_dir.glob("*.py"))