Deploy: Docker-based Streamlit app with startup data generation

.gitignore

@@ -0,0 +1,11 @@
+__pycache__/
+*.pyc
+.env
+*.db
+*.db-journal
+data/processed/results.db
+data/processed/trace.jsonl
+.DS_Store
+.venv/
+venv/
+.claude/

Dockerfile

@@ -2,18 +2,21 @@ FROM python:3.11-slim
 
 WORKDIR /app
 
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    build-essential \
-    && rm -rf /var/lib/apt/lists/*
-
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt
 
 COPY . .
 
+# Remove __pycache__ dirs
+RUN find . -type d -name __pycache__ -exec rm -rf {} + 2>/dev/null; true
+
+# Build pipeline data at image build time
+ENV PYTHONPATH=/app
+RUN python scripts/startup.py
+
 EXPOSE 7860
 
-HEALTHCHECK CMD curl --fail http://localhost:7860/_stcore/health
+HEALTHCHECK CMD curl --fail http://localhost:7860/_stcore/health || exit 1
 
 ENTRYPOINT ["streamlit", "run", "app/Home.py", \
     "--server.port=7860", \

scripts/startup.py

@@ -0,0 +1,17 @@
+"""Startup script: rebuild DB + seed feedback for deployment.
+
+Run this before launching the Streamlit app to ensure data exists.
+"""
+import sys
+import os
+
+sys.path.insert(0, os.getcwd())
+
+from scripts.run_pipeline import run_pipeline
+from scripts.seed_feedback import seed_feedback
+
+print("=== Startup: rebuilding pipeline data ===")
+run_pipeline(use_mock=True)
+print("\n=== Startup: seeding feedback data ===")
+seed_feedback()
+print("\n=== Startup complete ===")