Generate the config from the AppConfig model directly, add tests

haiku_rag_slim/haiku/rag/config/loader.py

@@ -48,47 +48,8 @@ def load_yaml_config(path: Path) -> dict:
 
 
 def generate_default_config() -> dict:
-    """Generate a default YAML config structure with documentation."""
-    return {
-        "environment": "production",
-        "storage": {
-            "data_dir": "",
-            "vacuum_retention_seconds": 86400,
-        },
-        "monitor": {
-            "directories": [],
-            "ignore_patterns": [],
-            "include_patterns": [],
-        },
-        "lancedb": {"uri": "", "api_key": "", "region": ""},
-        "embeddings": {
-            "provider": "ollama",
-            "model": "qwen3-embedding:4b",
-            "vector_dim": 2560,
-        },
-        "reranking": {"provider": "", "model": ""},
-        "qa": {"provider": "ollama", "model": "gpt-oss"},
-        "research": {"provider": "", "model": ""},
-        "processing": {
-            "chunk_size": 256,
-            "context_chunk_radius": 0,
-            "markdown_preprocessor": "",
-        },
-        "providers": {
-            "ollama": {"base_url": "http://localhost:11434"},
-            "vllm": {
-                "embeddings_base_url": "",
-                "rerank_base_url": "",
-                "qa_base_url": "",
-                "research_base_url": "",
-            },
-        },
-        "agui": {
-            "host": "0.0.0.0",
-            "port": 8000,
-            "cors_origins": ["*"],
-            "cors_credentials": True,
-            "cors_methods": ["GET", "POST", "OPTIONS"],
-            "cors_headers": ["*"],
-        },
-    }
+    """Generate a default YAML config structure from AppConfig defaults."""
+    from haiku.rag.config.models import AppConfig
+
+    default_config = AppConfig()
+    return default_config.model_dump(mode="json", exclude_none=False)

tests/test_config.py

@@ -1,5 +1,7 @@
 import pytest
+import yaml
 
+from haiku.rag.config import AppConfig
 from haiku.rag.config.loader import (
     find_config_file,
     generate_default_config,
@@ -98,19 +100,6 @@ def test_find_config_file_cli_path_not_exists(tmp_path):
         find_config_file(config_file)
 
 
-def test_generate_default_config():
-    """Test generating default config structure."""
-    config = generate_default_config()
-
-    assert config["environment"] == "production"
-    assert "storage" in config
-    assert "embeddings" in config
-    assert "qa" in config
-    assert "providers" in config
-    assert config["embeddings"]["provider"] == "ollama"
-    assert config["embeddings"]["vector_dim"] == 2560
-
-
 def test_config_precedence_cwd_over_user(tmp_path, monkeypatch):
     """Test that cwd config takes precedence over user config."""
     # Create separate directories for cwd and user config
@@ -163,3 +152,57 @@ def test_config_precedence_env_var_over_cwd(tmp_path, monkeypatch):
 
     config = load_yaml_config(found)
     assert config["environment"] == "from-env-var"
+
+
+def test_generate_default_config_completeness():
+    """Test that generated config has all fields from AppConfig and validates."""
+    config_data = generate_default_config()
+
+    # Validate against AppConfig model
+    config = AppConfig.model_validate(config_data)
+
+    # Get all fields from AppConfig
+    expected_fields = set(AppConfig.model_fields.keys())
+    actual_fields = set(config_data.keys())
+
+    # Verify all expected fields are present
+    assert expected_fields == actual_fields, (
+        f"Missing fields: {expected_fields - actual_fields}, "
+        f"Extra fields: {actual_fields - expected_fields}"
+    )
+
+    # Verify nested structures are dicts/lists, not model instances
+    for field_name, field_value in config_data.items():
+        assert not hasattr(field_value, "model_dump"), (
+            f"Field {field_name} should be dict/primitive, not Pydantic model"
+        )
+
+    # Verify config validates successfully
+    assert config.environment == "production"
+    assert config.embeddings.provider == "ollama"
+    assert config.qa.model.provider == "ollama"
+    assert config.research.model.provider == "ollama"
+    assert config.reranking.model is None
+
+
+def test_init_config_creates_valid_yaml(tmp_path):
+    """Test that generated config can be written to YAML and loaded back."""
+    config_file = tmp_path / "test-config.yaml"
+
+    # Generate and write config
+    config_data = generate_default_config()
+
+    with open(config_file, "w") as f:
+        f.write("# haiku.rag configuration file\n")
+        f.write(
+            "# See https://ggozad.github.io/haiku.rag/configuration/ for details\n\n"
+        )
+        yaml.dump(config_data, f, default_flow_style=False, sort_keys=False)
+
+    # Load it back
+    with open(config_file) as f:
+        loaded_data = yaml.safe_load(f)
+
+    # Validate it
+    config = AppConfig.model_validate(loaded_data)
+    assert config.environment == "production"