Add Phase 6: write tools, shell, and edit tools with reasoning-only fix

Implement 6 new agent tools — write_file, make_dir, delete_file,
str_replace, patch_apply, run_command — bringing the agent from
read-only observer to active code modifier. All write/shell operations
are gated through the existing permissions service.

Also fix a bug where qwen3.5 thinking mode produces reasoning tokens
but no content after tool results, causing the agent to silently exit.
The loop now detects reasoning-only responses, retries twice, then
injects a nudge message to break the model out of its thinking loop.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

tests/unit/test_tools.py

@@ -96,12 +96,18 @@ class TestToolRegistry:
     def test_create_default_registry(self, workspace: Path, config: AppConfig) -> None:
         registry = create_default_registry(workspace, config)
         names = set(registry.get_all().keys())
-        assert names == {"read_file", "list_dir", "grep_files", "find_files", "finish"}
+        assert names == {
+            "read_file", "list_dir", "grep_files", "find_files",
+            "write_file", "make_dir", "delete_file",
+            "str_replace", "patch_apply",
+            "run_command",
+            "finish",
+        }
 
     def test_schema_export(self, workspace: Path, config: AppConfig) -> None:
         registry = create_default_registry(workspace, config)
         schemas = registry.get_openai_tools_schema()
-        assert len(schemas) == 5
+        assert len(schemas) == 11
         assert all(s["type"] == "function" for s in schemas)