Refactor configuration management; remove deprecated files and unify settings in YAML format

README.md

@@ -17,7 +17,7 @@ src/helia/
 ├── analysis/
 │   └── extractor.py     # Metadata extraction (LLM-agnostic)
 ├── assessment/
-│   ├── core.py          # Clinical assessment logic (PHQ-8)
+│   └── core.py          # Clinical assessment logic (PHQ-8)
 │   └── schema.py        # Data models (AssessmentResult, PHQ8Item)
 ├── ingestion/
 │   └── parser.py        # Transcript parsing (DAIC-WOZ support)
@@ -50,6 +50,7 @@ graph TD
 -   **Clinical Parsing**: Native support for DAIC-WOZ transcript formats.
 -   **Structured Assessment**: Maps unstructured conversation to validatable PHQ-8 scores.
 -   **Document Persistence**: Stores full experimental context (config + evidence + scores) in MongoDB using Beanie.
+-   **Unified Configuration**: Single YAML config with environment variable fallbacks for system settings.
 
 ## Roadmap
 
@@ -67,22 +68,26 @@ uv sync
 
 ## Quick Start
 
-1.  **Environment Setup**:
+1.  **Configuration**:
+    Copy `example.config.yaml` to `config.yaml` and edit it.
     ```sh
-    export OPENAI_API_KEY=sk-...
-    # Ensure MongoDB is running (e.g., via Docker)
+    cp example.config.yaml config.yaml
     ```
+    
+    You can set system settings (MongoDB, S3) in the YAML file, or use environment variables (e.g., `HELIA_MONGO_URI`, `HELIA_S3_BUCKET`).
+    Provider API keys can be set in YAML or via `{PROVIDER_NAME}_API_KEY` (uppercased), e.g. `ANTHROPIC_API_KEY` for `providers.anthropic`.
 
 2.  **Run an Assessment**:
     ```sh
-    python -m helia.main "assess --input data/transcript.tsv"
+    # Ensure MongoDB is running
+    uv run python -m helia.main config.yaml
     ```
 
 ## Development
 
 -   **Linting**: `uv run ruff check .`
 -   **Formatting**: `uv run ruff format .`
--   **Type Checking**: `uv run pyrefly`
+-   **Type Checking**: `uv run ty check`
 
 ## License