Staging-->Main

.env.template

@@ -2,15 +2,28 @@
 FALKORDB_HOST=localhost
 FALKORDB_PORT=6379
 
-# OpenAI API key for LLM features
-OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>
+# Optional FalkorDB authentication
+FALKORDB_USERNAME=
+FALKORDB_PASSWORD=
 
-# Secret token for API authentication
+# Token checked by authenticated endpoints. If left empty, the current
+# implementation accepts requests without an Authorization header.
 SECRET_TOKEN=<YOUR_SECRET_TOKEN>
 
-# Flask server settings
-FLASK_RUN_HOST=0.0.0.0
-FLASK_RUN_PORT=5000
-
-# Set to 1 to enable public access for analyze_repo/switch_commit endpoints
+# Set to 1 to make read-only endpoints public.
 CODE_GRAPH_PUBLIC=0
+
+# Limit /api/analyze_folder to this directory tree. Leave commented to use
+# the repository root as the default allowed directory.
+# ALLOWED_ANALYSIS_DIR=/absolute/path/to/projects
+
+# LiteLLM model used by /api/chat
+MODEL_NAME=gemini/gemini-flash-lite-latest
+
+# Provider credential for the default Gemini model. Change this to the
+# appropriate provider key if you change MODEL_NAME.
+GEMINI_API_KEY=<YOUR_GEMINI_API_KEY>
+
+# Optional Uvicorn bind settings used by start.sh / make run-*
+HOST=0.0.0.0
+PORT=5000

.github/workflows/playwright.yml

@@ -81,17 +81,17 @@ jobs:
         npx playwright install chromium firefox
         npx playwright install-deps chromium firefox
 
-    - name: Start Flask server
+    - name: Start server
       id: start-server
       env:
         OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
         SECRET_TOKEN: ${{ secrets.SECRET_TOKEN }}
         CODE_GRAPH_PUBLIC: "1"
         MODEL_NAME: "openai/gpt-4.1-mini"
       run: |
-        uv run flask --app api/index.py run --host 0.0.0.0 --port 5000 &
+        uv run uvicorn api.index:app --host 0.0.0.0 --port 5000 &
         echo "pid=$!" >> "$GITHUB_OUTPUT"
-        # Wait for Flask to be ready
+        # Wait for server to be ready
         timeout 30 bash -c 'until curl -s http://localhost:5000/ > /dev/null 2>&1; do sleep 0.5; done'
 
     - name: Run Playwright tests
@@ -102,7 +102,7 @@ jobs:
         MODEL_NAME: "openai/gpt-4.1-mini"
       run: npx playwright test --shard=${{ matrix.shard }}/2 --reporter=dot,list
 
-    - name: Stop Flask server
+    - name: Stop server
       if: always()
       run: kill ${{ steps.start-server.outputs.pid }} 2>/dev/null || true
 

Makefile

@@ -40,10 +40,10 @@ clean: ## Clean up build and test artifacts
 	find . -name "*.pyo" -delete
 
 run-dev: build-dev ## Run development server (Python backend serving built frontend)
-	uv run flask --app api/index.py run --host $${HOST:-127.0.0.1} --port $${PORT:-5000} --debug
+	uv run uvicorn api.index:app --host $${HOST:-127.0.0.1} --port $${PORT:-5000} --reload
 
 run-prod: build-prod ## Run production server
-	uv run flask --app api/index.py run --host $${HOST:-0.0.0.0} --port $${PORT:-5000}
+	uv run uvicorn api.index:app --host $${HOST:-0.0.0.0} --port $${PORT:-5000}
 
 docker-falkordb: ## Start FalkorDB in Docker for testing
 	docker run -d --name falkordb-test -p 6379:6379 falkordb/falkordb:latest