fix: address CodeRabbit Phase 6 review feedback

- Dockerfile: Add curl for HEALTHCHECK, use specific extras (not --all-extras)
- app.py: Tighten Magentic mode key detection to require OpenAI specifically
- embeddings.py: Move structlog import to module level
- test_embeddings.py: Remove redundant numpy import

Dockerfile

@@ -4,9 +4,10 @@ FROM python:3.11-slim
 # Set working directory
 WORKDIR /app
 
-# Install system dependencies
+# Install system dependencies (curl needed for HEALTHCHECK)
 RUN apt-get update && apt-get install -y \
     git \
+    curl \
     && rm -rf /var/lib/apt/lists/*
 
 # Install uv
@@ -18,8 +19,8 @@ COPY uv.lock .
 COPY src/ src/
 COPY README.md .
 
-# Install dependencies
-RUN uv sync --frozen --no-dev --all-extras
+# Install runtime dependencies only (no dev/test tools)
+RUN uv sync --frozen --no-dev --extra embeddings --extra magentic
 
 # Create non-root user BEFORE downloading models
 RUN useradd --create-home --shell /bin/bash appuser

src/app.py

@@ -72,23 +72,30 @@ async def research_agent(
         yield "Please enter a research question."
         return
 
-    # Create orchestrator (use mock if no API key)
-    use_mock = not (os.getenv("OPENAI_API_KEY") or os.getenv("ANTHROPIC_API_KEY"))
+    # Decide whether to use real LLMs or mock based on mode and available keys
+    has_openai = bool(os.getenv("OPENAI_API_KEY"))
+    has_anthropic = bool(os.getenv("ANTHROPIC_API_KEY"))
 
-    # If magentic mode requested but no keys, fallback/warn
+    if mode == "magentic":
+        # Magentic currently supports OpenAI only
+        use_mock = not has_openai
+    else:
+        # Simple mode can work with either provider
+        use_mock = not (has_openai or has_anthropic)
+
+    # If magentic mode requested but no OpenAI key, fallback/warn
     if mode == "magentic" and use_mock:
         yield (
-            "⚠️ **Warning**: Magentic mode requires valid API keys. "
+            "⚠️ **Warning**: Magentic mode requires OpenAI API key. "
             "Falling back to Mock Simple mode."
         )
         mode = "simple"
 
-    orchestrator = configure_orchestrator(use_mock=use_mock, mode=mode)
-
     # Run the agent and stream events
-    response_parts = []
+    response_parts: list[str] = []
 
     try:
+        orchestrator = configure_orchestrator(use_mock=use_mock, mode=mode)
         async for event in orchestrator.run(message):
             # Format event as markdown
             event_md = event.to_markdown()

src/services/embeddings.py

@@ -8,6 +8,7 @@ import asyncio
 from typing import Any
 
 import chromadb
+import structlog
 from sentence_transformers import SentenceTransformer
 
 from src.utils.models import Evidence
@@ -143,8 +144,6 @@ class EmbeddingService:
                     )
             except Exception as e:
                 # Log but don't fail entire deduplication for one bad item
-                import structlog
-
                 structlog.get_logger().warning(
                     "Failed to process evidence in deduplicate",
                     url=evidence.citation.url,

tests/unit/services/test_embeddings.py

@@ -51,8 +51,6 @@ class TestEmbeddingService:
     async def test_batch_embed_efficient(self, mock_sentence_transformer, mock_chroma_client):
         """Batch embedding should call encode with list."""
         # Setup mock for batch return (list of arrays)
-        import numpy as np
-
         mock_sentence_transformer.encode.return_value = np.array([[0.1, 0.2], [0.3, 0.4]])
 
         service = EmbeddingService()