Merge pull request #166 from ggozad/fix/init-config

Fix `init-config` command generating invalid configuration files

CHANGELOG.md

@@ -1,6 +1,12 @@
 # Changelog
 ## [Unreleased]
 
+### Fixed
+
+- **Configuration**: Fixed `init-config` command generating invalid configuration files (#165)
+  - Refactored `generate_default_config()` to use Pydantic model serialization instead of manual dict construction
+  - Updated `qa`, `research`, and `reranking` sections to use new `ModelConfig` structure
+
 ## [0.19.0] - 2025-11-25
 
 ### Added

README.md

@@ -79,7 +79,7 @@ haiku-rag rebuild
 haiku-rag serve --monitor
 ```
 
-To customize settings, create a `haiku.rag.yaml` config file (see [Configuration](https://ggozad.github.io/haiku.rag/config-index/)).
+To customize settings, create a `haiku.rag.yaml` config file (see [Configuration](https://ggozad.github.io/haiku.rag/configuration/)).
 
 ## Python Usage
 
@@ -162,7 +162,7 @@ See the [examples directory](examples/) for working examples:
 Full documentation at: https://ggozad.github.io/haiku.rag/
 
 - [Installation](https://ggozad.github.io/haiku.rag/installation/) - Provider setup
-- [Configuration](https://ggozad.github.io/haiku.rag/config-index/) - YAML configuration
+- [Configuration](https://ggozad.github.io/haiku.rag/configuration/) - YAML configuration
 - [CLI](https://ggozad.github.io/haiku.rag/cli/) - Command reference
 - [Python API](https://ggozad.github.io/haiku.rag/python/) - Complete API docs
 - [Agents](https://ggozad.github.io/haiku.rag/agents/) - QA agent and multi-agent research

docs/cli.md

@@ -69,7 +69,7 @@ haiku-rag add-src /path/to/documents/
 ```
 
 !!! note
-    When adding a directory, the same content filters configured for [file monitoring](processing.md#filtering-monitored-files) are applied. This means `ignore_patterns` and `include_patterns` from your configuration will be used to filter which files are added.
+    When adding a directory, the same content filters configured for [file monitoring](configuration/processing.md#filtering-monitored-files) are applied. This means `ignore_patterns` and `include_patterns` from your configuration will be used to filter which files are added.
 
 !!! note
     As you add documents to `haiku.rag` the database keeps growing. By default, LanceDB supports versioning
@@ -158,7 +158,7 @@ haiku-rag research "How does haiku.rag organize and query documents?" --verbose
 Flags:
 - `--verbose`: Show planning, searching previews, evaluation summary, and stop reason
 
-Research parameters like `max_iterations`, `confidence_threshold`, and `max_concurrency` are configured in your [configuration file](config-index.md) under the `research` section.
+Research parameters like `max_iterations`, `confidence_threshold`, and `max_concurrency` are configured in your [configuration file](configuration/index.md) under the `research` section.
 
 When `--verbose` is set, the CLI consumes the research graph's AG-UI event stream, displaying step events and activity snapshots as agents progress through planning, search, evaluation, and synthesis. Without `--verbose`, only the final research report is displayed.
 

docs/configuration/index.md

@@ -3,7 +3,7 @@
 Configuration is done through YAML configuration files.
 
 !!! note
-    If you create a db with certain settings and later change them, `haiku.rag` will detect incompatibilities (for example, if you change embedding provider) and will exit. You can **rebuild** the database to apply the new settings, see [Rebuild Database](./cli.md#rebuild-database).
+    If you create a db with certain settings and later change them, `haiku.rag` will detect incompatibilities (for example, if you change embedding provider) and will exit. You can **rebuild** the database to apply the new settings, see [Rebuild Database](../cli.md#rebuild-database).
 
 ## Getting Started
 

docs/configuration/processing.md

@@ -92,7 +92,7 @@ conversion_options:
 
 - Offloads processing to docling-serve API
 - Better for heavy workloads and production
-- Requires docling-serve instance (see [Remote processing setup](remote-processing.md))
+- Requires docling-serve instance (see [Remote processing setup](../remote-processing.md))
 
 To use remote processing:
 

docs/configuration/qa-research.md

@@ -68,4 +68,4 @@ The server exposes:
 - `GET /health` - Health check endpoint
 - `POST /v1/agent/stream` - Research graph streaming endpoint (Server-Sent Events)
 
-See [Server Mode](server.md) for more details.
+See [Server Mode](../server.md) for more details.

docs/index.md

@@ -55,7 +55,7 @@ haiku-rag ask "Who is the author of haiku.rag?"
 
 - [Getting started](tutorial.md) - Tutorial
 - [Installation](installation.md) - Install haiku.rag with different providers
-- [Configuration](config-index.md) - Environment variables and settings
+- [Configuration](configuration/index.md) - Environment variables and settings
 - [CLI](cli.md) - Command line interface usage
 - [Server](server.md) - File monitoring and server mode
 - [MCP](mcp.md) - Model Context Protocol integration

docs/installation.md

@@ -43,7 +43,7 @@ The slim package has minimal dependencies and lets you install only what you nee
 - **OpenAI** (GPT models for QA and embeddings)
 - **Anthropic** (Claude models for QA)
 
-See [Configuration](config-index.md) for configuring providers including advanced options like vLLM.
+See [Configuration](configuration/index.md) for configuring providers including advanced options like vLLM.
 
 ## Requirements
 
@@ -71,7 +71,7 @@ When using `haiku.rag-slim`, you can skip installing the `docling` extra and ins
 - Offloading heavy document processing to a dedicated service
 - Production deployments with separate processing infrastructure
 
-See [Remote processing](remote-processing.md) for setup instructions and [Document Processing](processing.md) for configuration options.
+See [Remote processing](remote-processing.md) for setup instructions and [Document Processing](configuration/processing.md) for configuration options.
 
 ## Docker
 

docs/python.md

@@ -321,6 +321,6 @@ answer = await client.ask(
 
 The QA agent will search your documents for relevant information and use the configured LLM to generate a comprehensive answer. With `cite=True`, responses include citations showing which documents were used as sources. Citations prefer the document title when present, otherwise they use the URI.
 
-The QA provider and model are configured in `haiku.rag.yaml` or can be passed directly to the client (see [Configuration](config-index.md)).
+The QA provider and model are configured in `haiku.rag.yaml` or can be passed directly to the client (see [Configuration](configuration/index.md)).
 
 See also: [Agents](agents.md) for details on the QA agent and the multi‑agent research workflow.

docs/remote-processing.md

@@ -44,7 +44,7 @@ docker run -p 5001:5001 -e DOCLING_SERVE_ENABLE_UI=1 quay.io/docling-project/doc
 
 ### Configuration
 
-Configure haiku.rag to use docling-serve. See the [Document Processing](processing.md) guide for all available options.
+Configure haiku.rag to use docling-serve. See the [Document Processing](configuration/processing.md) guide for all available options.
 
 ```yaml
 # haiku.rag.yaml

docs/server.md

@@ -122,7 +122,7 @@ agui:
   cors_credentials: true
 ```
 
-See [Configuration](qa-research.md#ag-ui-server-configuration) for all available options.
+See [Configuration](configuration/qa-research.md#ag-ui-server-configuration) for all available options.
 
 ### Using the Streaming Endpoints
 

docs/tutorial.md

@@ -51,7 +51,7 @@ export OPENAI_API_KEY="<your OpenAI API key>"
 
 For the list of available OpenAI models and their vector dimensions, see the [OpenAI documentation](https://platform.openai.com/docs/guides/embeddings).
 
-See [Configuration](config-index.md) for all available options.
+See [Configuration](configuration/index.md) for all available options.
 
 ## Adding the first documents
 
@@ -216,4 +216,4 @@ The following people are presenting talks at PyCon Finland 2025:
 
 ## Configuration
 
-See [Configuration page](./config-index.md) for complete documentation on YAML configuration and all available options.
+See [Configuration page](./configuration/index.md) for complete documentation on YAML configuration and all available options.

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)

mkdocs.yml

@@ -60,11 +60,11 @@ nav:
       - Getting started: tutorial.md
       - Installation: installation.md
       - Configuration:
-          - config-index.md
-          - Providers: providers.md
-          - QA and Research: qa-research.md
-          - Document Processing: processing.md
-          - Storage: storage.md
+          - configuration/index.md
+          - Providers: configuration/providers.md
+          - QA and Research: configuration/qa-research.md
+          - Document Processing: configuration/processing.md
+          - Storage: configuration/storage.md
       - CLI: cli.md
       - Python: python.md
       - Agents: agents.md

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"