Add WebSocket streaming, mocked tests, and exchange metadata support

[Copilot]

Adds missing components to the FastAPI crypto data service: deterministic mocked tests for CI, real-time WebSocket streaming, and exchange metadata in API responses.

Changes

WebSocket Streaming (src/app/api/v1/ws_live_data.py)

• New /api/v1/live_data/ws endpoint for real-time data streaming
• Configurable update interval via query param (10-300s)
• Graceful shutdown on client "close" message
• Error recovery with exponential backoff

Mocked Tests (tests/test_live_data_mocked.py)

• 6 test scenarios using monkeypatch to stub ExchangeClient.fetch_ohlcv
• Validates NaN→None conversion, error handling (503/400), and validation (422)
• Eliminates network dependency for CI reliability

Exchange Metadata

• ExchangeClient.get_meta_info() exposes exchange configuration
• Response meta field now includes default_type (spot/future/etc.)
• Updated process_ohlcv_data signature to accept metadata

# WebSocket usage
ws = websocket.connect("ws://localhost:8000/api/v1/live_data/ws?symbol=BTC/USDT&interval=30")
data = ws.recv()  # Receives updates every 30s

# Meta information in response
response = requests.get("/api/v1/live_data")
print(response.json()["meta"])  # {"default_type": "spot"}

Code Quality

• Flattened nested conditionals in get_meta_info()
• Added clarifying comments for timeout handling in WebSocket loop
• All tests passing (9/9), linting clean, mypy strict mode compliant

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• api.binance.com
  • Triggering command: /home/REDACTED/.local/bin/pytest pytest -v (dns block)
  • Triggering command: /home/REDACTED/.local/bin/uvicorn uvicorn app.main:app --host 0.0.0.0 --port 8000 (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)

Original prompt

Add a complete FastAPI service for fetching OHLCV candles and computing indicators (EMA/RSI/ATR) with Docker, CI, typing, and tests.

Include the following features and files (create new branch and open a PR against 'main'):

1. Project files

• pyproject.toml (deps: fastapi, uvicorn[standard], pydantic, pydantic-settings, ccxt, pandas, ta; dev: pytest, httpx, ruff, mypy, types-requests)
• README.md (quickstart, Docker, notes)
• .env.example
• .gitignore
• Dockerfile
• docker-compose.yml
• .github/workflows/ci.yml

2. Application package (src/app)

• src/app/init.py
• src/app/main.py (FastAPI app, health endpoint, include router)

3. core

• src/app/core/init.py
• src/app/core/config.py (pydantic-settings Settings)
• src/app/core/logging.py (basic logging config)

4. api

• src/app/api/init.py
• src/app/api/v1/init.py
• src/app/api/v1/routes_live_data.py (GET /live_data route, validation, response_model)

5. integrations

• src/app/integrations/init.py
• src/app/integrations/exchanges.py (ExchangeClient wrapper, build_exchange)

6. schemas

• src/app/schemas/init.py
• src/app/schemas/live_data.py (Candle, LatestIndicators, LiveDataResponse Pydantic models)

7. services

• src/app/services/init.py
• src/app/services/indicators.py (add_indicators, latest_indicator_values, NaN->None handling)
• src/app/services/market_data.py (get_live_data, fetch ohlcv via ccxt, build response)

8. WebSocket streaming

• src/app/api/v1/ws_live_data.py (optional: /api/v1/live_data/ws WebSocket endpoint that streams recent candle data every N seconds; configurable via query param interval)

9. tests

• tests/init.py
• tests/test_health.py
• tests/test_live_data.py (network smoke test)
• tests/test_live_data_mocked.py (mocked ccxt tests using pytest + monkeypatch to avoid network in CI)

Implementation details and behavior:

• Default exchange: binance (configurable via .env)
• Indicators: EMA 20/50/200, RSI 14, ATR 14 using ta and pandas
• Handle NaN and infinite values by converting to None before JSON serialization
• Endpoint validates symbol, timeframe, limit, exchange via fastapi Query
• Error mapping: ccxt.NetworkError -> HTTP 503, ccxt.ExchangeError -> HTTP 400, other exceptions -> HTTP 500
• recent_candles: return last 20 candles
• Provide meta information including exchange.options.get('defaultType') if available
• Configure logging and settings via pydantic-settings
• Dockerfile installs editable package with dev deps and runs uvicorn
• GitHub Actions CI: checkout, setup Python 3.11, install deps, run ruff, mypy, pytest

Testing and CI notes:

• Add mocked ccxt tests (tests/test_live_data_mocked.py) to stub exchange.fetch_ohlcv to ensure CI deterministic
• Keep one smoke network test but mark or guard it in CI if necessary

Branch and PR details:

• Create a new branch named: add/fastapi-live-data
• Open a pull request against base 'main'
• PR title: "Add professional FastAPI crypto data service with OHLCV + indicators"
• PR description: include this problem statement and list of files added
• Do not assign reviewers or assignees or labels by default
• Preserve multiple logical commits (do not squash)

Please create the PR in the repository: Nfectious/crypto-trade-analysis

This pull request was created from Copilot chat.

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.