Merge pull request #36 from ChingEnLin/feat/queryargus-integration

feat: QueryArgus data-quality integration

Author: ChingEnLin

.github/workflows/ci.yml

@@ -15,7 +15,9 @@ jobs:
     steps:
     - name: Checkout code
       uses: actions/checkout@v4
-      
+      with:
+        submodules: recursive
+
     - name: Set up Python 3.12
       uses: actions/setup-python@v4
       with:
@@ -34,6 +36,9 @@ jobs:
       run: |
         python -m pip install --upgrade pip
         pip install -r requirements.txt
+        # queryargus (submodule) installed with --no-deps; its google-genai<1 pin
+        # conflicts with langchain-google-genai. 1.x API is compatible.
+        pip install --no-deps -e ./queryargus
         
     - name: Lint with flake8
       working-directory: ./backend
@@ -53,7 +58,9 @@ jobs:
       env:
         GEMINI_API_KEY: "dummy-key-for-tests"
       run: |
-        PYTHONPATH=. pytest --cov=. --cov-report=term-missing --cov-report=xml --verbose
+        # Skip queryargus submodule tests: they need extras (azure-*, typer)
+        # that we deliberately don't install via `pip install --no-deps`.
+        PYTHONPATH=. pytest --ignore=queryargus --cov=. --cov-report=term-missing --cov-report=xml --verbose
         
     - name: Upload coverage to Codecov
       uses: codecov/codecov-action@v3
@@ -70,7 +77,9 @@ jobs:
     steps:
     - name: Checkout code
       uses: actions/checkout@v4
-      
+      with:
+        submodules: recursive
+
     - name: Set up Node.js 20
       uses: actions/setup-node@v4
       with:
@@ -103,7 +112,9 @@ jobs:
     steps:
     - name: Checkout code
       uses: actions/checkout@v4
-      
+      with:
+        submodules: recursive
+
     - name: Set up Node.js 20
       uses: actions/setup-node@v4
       with:

.github/workflows/google-cloudrun-docker.yml

@@ -35,6 +35,8 @@ jobs:
     steps:
       - name: 'Checkout'
         uses: 'actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332' # actions/checkout@v4
+        with:
+          submodules: recursive
 
       - id: 'auth'
         name: 'Authenticate to Google Cloud'

.gitignore

@@ -56,3 +56,10 @@ CLAUDE.md
 .claude/settings.local.json
 HANDOFF.md
 DESIGN_HANDBOOK.md
+
+# virtual environment
+.venv/
+
+# HITL experiment artifacts (lives on experiment/hitl-* branches)
+results/
+backend/experiments/

.gitmodules

@@ -0,0 +1,4 @@
+[submodule "backend/queryargus"]
+	path = backend/queryargus
+	url = https://github.com/ChingEnLin/QueryArgus
+	branch = dev

backend/.flake8

@@ -7,6 +7,7 @@ exclude =
     .pytest_cache,
     htmlcov,
     venv,
-    .venv
+    .venv,
+    queryargus
 per-file-ignores = 
     __init__.py:F401

backend/Dockerfile

@@ -1,11 +1,13 @@
 # Backend Dockerfile
-FROM python:3.11-slim
+FROM python:3.12-slim
 
 WORKDIR /app/backend
 
 COPY requirements.txt .
+COPY queryargus ./queryargus
 RUN pip install --no-cache-dir --upgrade pip \
-    && pip install --no-cache-dir -r requirements.txt
+    && pip install --no-cache-dir -r requirements.txt \
+    && pip install --no-cache-dir --no-deps -e ./queryargus
 
 COPY . .
 

backend/main.py

@@ -1,10 +1,21 @@
 import os
+from contextlib import asynccontextmanager
+
 import uvicorn
 from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
-from routes import query, azure, system, user_queries, data_documents, audit
+from routes import query, azure, system, user_queries, data_documents, audit, argus
+
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    from services.argus_store import get_report_store
+
+    get_report_store()
+    yield
+
 
-app = FastAPI()
+app = FastAPI(lifespan=lifespan)
 
 # Configure CORS origins based on environment
 # Check for production indicators
@@ -56,6 +67,7 @@ async def health_check():
 app.include_router(user_queries.router, prefix="/user", tags=["User Queries"])
 app.include_router(data_documents.router, prefix="/data", tags=["Data Documents"])
 app.include_router(audit.router, prefix="/audit", tags=["Audit"])
+app.include_router(argus.router, prefix="/argus", tags=["Argus"])
 
 if __name__ == "__main__":
     uvicorn.run(app, host="0.0.0.0", port=8000)

backend/pyproject.toml

@@ -10,5 +10,6 @@ exclude = '''
   | htmlcov
   | venv
   | \.venv
+  | queryargus
 )/
 '''

backend/pytest.ini

@@ -3,14 +3,16 @@ testpaths = tests
 python_files = test_*.py
 python_classes = Test*
 python_functions = test_*
-addopts = 
+addopts =
     --strict-markers
     --strict-config
     --verbose
     --cov=.
     --cov-report=term-missing
     --cov-report=html
     --cov-exclude=tests/*
+    --cov-exclude=queryargus/*
+    --ignore=queryargus
 markers =
     unit: Unit tests
     integration: Integration tests