From 912dabf25c87f64802fc6c2383cbf055e306881d Mon Sep 17 00:00:00 2001 From: Claude Date: Sat, 12 Sep 2026 03:33:01 +0000 Subject: [PATCH] Add detailed market data backend design document Consolidates the interface, simulator, and Massive API design docs into one implementation-accurate reference, matching the as-built code in backend/app/market/ after code review fixes were applied. Co-Authored-By: Claude Sonnet 5 Claude-Session: https://claude.ai/code/session_01VxEsuAL4E6q2LaTfu9BqPW --- planning/MARKET_DATA_DESIGN.md | 1388 ++++++++++++++++++++++++++++++++ 1 file changed, 1388 insertions(+) create mode 100644 planning/MARKET_DATA_DESIGN.md diff --git a/planning/MARKET_DATA_DESIGN.md b/planning/MARKET_DATA_DESIGN.md new file mode 100644 index 000000000..658f747e1 --- /dev/null +++ b/planning/MARKET_DATA_DESIGN.md @@ -0,0 +1,1388 @@ +# Market Data Backend — Design Document + +Implementation-ready design for the FinAlly market data subsystem: a unified +interface with two interchangeable implementations (a GBM simulator and a +Massive/Polygon.io REST poller), a thread-safe price cache, and an SSE +streaming endpoint. This document reflects the **as-built** code in +`backend/app/market/` (8 modules) — it is the authoritative reference for +any agent wiring the rest of the backend (portfolio, watchlist, chat) on top +of live prices. + +Status: this subsystem is complete and tested (see +`planning/MARKET_DATA_SUMMARY.md`). `backend/app/main.py` — the FastAPI app +that wires this subsystem into a running server — does not exist yet; §10 +below is the design for building it. + +--- + +## Table of Contents + +1. [Architecture](#1-architecture) +2. [File Structure](#2-file-structure) +3. [Data Model — `models.py`](#3-data-model) +4. [Price Cache — `cache.py`](#4-price-cache) +5. [Abstract Interface — `interface.py`](#5-abstract-interface) +6. [Seed Prices & Ticker Parameters — `seed_prices.py`](#6-seed-prices--ticker-parameters) +7. [GBM Simulator — `simulator.py`](#7-gbm-simulator) +8. [Massive API Client — `massive_client.py`](#8-massive-api-client) +9. [Factory — `factory.py`](#9-factory) +10. [FastAPI Integration — `stream.py` and `main.py`](#10-fastapi-integration) +11. [Watchlist Coordination](#11-watchlist-coordination) +12. [Testing Strategy](#12-testing-strategy) +13. [Error Handling & Edge Cases](#13-error-handling--edge-cases) +14. [Configuration Summary](#14-configuration-summary) + +--- + +## 1. Architecture + +``` + MarketDataSource (ABC) + / \ + SimulatorDataSource MassiveDataSource + (GBM, in-process, (Polygon.io REST + no external deps) poller, needs API key) + \ / + v v + PriceCache + (thread-safe, in-memory, + versioned for change detection) + / | \ + v v v + SSE /api/stream Portfolio Trade + /prices valuation execution +``` + +**Strategy pattern.** Both data sources implement `MarketDataSource`. +Downstream code (SSE streaming, portfolio valuation, trade execution) never +knows or cares which one is active — it only ever talks to the shared +`PriceCache`. + +**Push model, not pull.** A data source is not asked for a price; it writes +prices into the cache on its own schedule (simulator: every 500ms, Massive: +every 15s by default). Readers poll the cache at whatever cadence they need, +decoupled from the producer's timing. + +**Selection is environment-driven.** `create_market_data_source()` picks the +implementation based on whether `MASSIVE_API_KEY` is set — no code change +needed to switch between simulated and real data (see [PLAN.md §6](PLAN.md)). + +--- + +## 2. File Structure + +``` +backend/ + app/ + market/ + __init__.py # Re-exports: PriceUpdate, PriceCache, MarketDataSource, + # create_market_data_source, create_stream_router + models.py # PriceUpdate dataclass + cache.py # PriceCache (thread-safe in-memory store) + interface.py # MarketDataSource ABC + seed_prices.py # SEED_PRICES, TICKER_PARAMS, DEFAULT_PARAMS, CORRELATION_GROUPS + simulator.py # GBMSimulator + SimulatorDataSource + massive_client.py # MassiveDataSource + factory.py # create_market_data_source() + stream.py # SSE endpoint (FastAPI router factory) + market_data_demo.py # Rich terminal demo (uv run market_data_demo.py) + tests/ + market/ + test_models.py + test_cache.py + test_simulator.py + test_simulator_source.py + test_factory.py + test_massive.py +``` + +Each module has a single responsibility. `app/market/__init__.py` re-exports +the public API so the rest of the backend imports from `app.market` without +reaching into submodules: + +```python +from app.market import PriceCache, PriceUpdate, MarketDataSource, create_market_data_source +``` + +--- + +## 3. Data Model + +**File: `backend/app/market/models.py`** + +`PriceUpdate` is the only data structure that leaves the market data layer. +Every downstream consumer — SSE streaming, portfolio valuation, trade +execution — works exclusively with this type. + +```python +from __future__ import annotations + +import time +from dataclasses import dataclass, field + + +@dataclass(frozen=True, slots=True) +class PriceUpdate: + """Immutable snapshot of a single ticker's price at a point in time.""" + + ticker: str + price: float + previous_price: float + timestamp: float = field(default_factory=time.time) # Unix seconds + + @property + def change(self) -> float: + """Absolute price change from previous update.""" + return round(self.price - self.previous_price, 4) + + @property + def change_percent(self) -> float: + """Percentage change from previous update.""" + if self.previous_price == 0: + return 0.0 + return round((self.price - self.previous_price) / self.previous_price * 100, 4) + + @property + def direction(self) -> str: + """'up', 'down', or 'flat'.""" + if self.price > self.previous_price: + return "up" + elif self.price < self.previous_price: + return "down" + return "flat" + + def to_dict(self) -> dict: + """Serialize for JSON / SSE transmission.""" + return { + "ticker": self.ticker, + "price": self.price, + "previous_price": self.previous_price, + "timestamp": self.timestamp, + "change": self.change, + "change_percent": self.change_percent, + "direction": self.direction, + } +``` + +### Design decisions + +- **`frozen=True`** — price updates are immutable value objects; once + created they never change, so they're safe to share across async tasks + without copying. +- **`slots=True`** — memory optimization; many of these are created per + second. +- **Computed properties** (`change`, `change_percent`, `direction`) are + derived from `price`/`previous_price` so they can never drift out of sync + with each other — there is no stale `direction` field to forget to update. +- **`to_dict()`** is the single serialization point used by both the SSE + endpoint and any future REST API response. + +--- + +## 4. Price Cache + +**File: `backend/app/market/cache.py`** + +The central data hub. Data sources write to it; SSE streaming and (later) +portfolio valuation / trade execution read from it. It must be thread-safe +because the Massive client's synchronous calls run in a thread-pool +executor via `asyncio.to_thread`, while SSE reads happen on the event loop. + +```python +from __future__ import annotations + +import time +from threading import Lock + +from .models import PriceUpdate + + +class PriceCache: + """Thread-safe in-memory cache of the latest price for each ticker. + + Writers: SimulatorDataSource or MassiveDataSource (one at a time). + Readers: SSE streaming endpoint, portfolio valuation, trade execution. + """ + + def __init__(self) -> None: + self._prices: dict[str, PriceUpdate] = {} + self._lock = Lock() + self._version: int = 0 # Monotonically increasing; bumped on every update + + def update(self, ticker: str, price: float, timestamp: float | None = None) -> PriceUpdate: + """Record a new price for a ticker. Returns the created PriceUpdate. + + Automatically computes direction and change from the previous price. + If this is the first update for the ticker, previous_price == price + (direction='flat'). + """ + with self._lock: + ts = timestamp or time.time() + prev = self._prices.get(ticker) + previous_price = prev.price if prev else price + + update = PriceUpdate( + ticker=ticker, + price=round(price, 2), + previous_price=round(previous_price, 2), + timestamp=ts, + ) + self._prices[ticker] = update + self._version += 1 + return update + + def get(self, ticker: str) -> PriceUpdate | None: + """Get the latest price for a single ticker, or None if unknown.""" + with self._lock: + return self._prices.get(ticker) + + def get_all(self) -> dict[str, PriceUpdate]: + """Snapshot of all current prices. Returns a shallow copy.""" + with self._lock: + return dict(self._prices) + + def get_price(self, ticker: str) -> float | None: + """Convenience: get just the price float, or None.""" + update = self.get(ticker) + return update.price if update else None + + def remove(self, ticker: str) -> None: + """Remove a ticker from the cache (e.g., when removed from watchlist).""" + with self._lock: + self._prices.pop(ticker, None) + + @property + def version(self) -> int: + """Current version counter. Useful for SSE change detection.""" + return self._version + + def __len__(self) -> int: + with self._lock: + return len(self._prices) + + def __contains__(self, ticker: str) -> bool: + with self._lock: + return ticker in self._prices +``` + +### Why a version counter + +The SSE loop polls the cache every ~500ms. Without a version counter it +would serialize and send all prices on every tick even when nothing +changed (e.g. Massive only updates every 15s). The counter lets the SSE +loop skip sends when there's nothing new: + +```python +last_version = -1 +while True: + if price_cache.version != last_version: + last_version = price_cache.version + yield format_sse(price_cache.get_all()) + await asyncio.sleep(0.5) +``` + +### Thread safety rationale + +`threading.Lock` is used instead of `asyncio.Lock` because: + +- The Massive client's synchronous `get_snapshot_all()` runs via + `asyncio.to_thread()`, which executes in a real OS thread — + `asyncio.Lock` would not protect against that. +- `threading.Lock` works correctly from both sync threads and the async + event loop, so one cache implementation serves both data sources. + +--- + +## 5. Abstract Interface + +**File: `backend/app/market/interface.py`** + +```python +from __future__ import annotations + +from abc import ABC, abstractmethod + + +class MarketDataSource(ABC): + """Contract for market data providers. + + Implementations push price updates into a shared PriceCache on their own + schedule. Downstream code never calls the data source directly for prices — + it reads from the cache. + + Lifecycle: + source = create_market_data_source(cache) + await source.start(["AAPL", "GOOGL", ...]) + # ... app runs ... + await source.add_ticker("TSLA") + await source.remove_ticker("GOOGL") + # ... app shutting down ... + await source.stop() + """ + + @abstractmethod + async def start(self, tickers: list[str]) -> None: + """Begin producing price updates for the given tickers. + + Starts a background task that periodically writes to the PriceCache. + Must be called exactly once. Calling start() twice is undefined behavior. + """ + + @abstractmethod + async def stop(self) -> None: + """Stop the background task and release resources. + + Safe to call multiple times. After stop(), the source will not write + to the cache again. + """ + + @abstractmethod + async def add_ticker(self, ticker: str) -> None: + """Add a ticker to the active set. No-op if already present. + + The next update cycle will include this ticker. + """ + + @abstractmethod + async def remove_ticker(self, ticker: str) -> None: + """Remove a ticker from the active set. No-op if not present. + + Also removes the ticker from the PriceCache. + """ + + @abstractmethod + def get_tickers(self) -> list[str]: + """Return the current list of actively tracked tickers.""" +``` + +### Why the source writes to the cache instead of returning prices + +This push model decouples timing. The simulator ticks at 500ms, Massive +polls at 15s, but SSE always reads from the cache at its own 500ms cadence. +The SSE layer never needs to know which data source is active or what its +update interval is. + +--- + +## 6. Seed Prices & Ticker Parameters + +**File: `backend/app/market/seed_prices.py`** + +Constants only — no logic, no imports beyond stdlib. Shared by the +simulator (initial prices and GBM parameters) and available as a fallback +reference for any code that wants a sane starting price for an unknown +ticker. + +```python +"""Seed prices and per-ticker parameters for the market simulator.""" + +# Realistic starting prices for the default watchlist (as of project creation) +SEED_PRICES: dict[str, float] = { + "AAPL": 190.00, + "GOOGL": 175.00, + "MSFT": 420.00, + "AMZN": 185.00, + "TSLA": 250.00, + "NVDA": 800.00, + "META": 500.00, + "JPM": 195.00, + "V": 280.00, + "NFLX": 600.00, +} + +# Per-ticker GBM parameters +# sigma: annualized volatility (higher = more price movement) +# mu: annualized drift / expected return +TICKER_PARAMS: dict[str, dict[str, float]] = { + "AAPL": {"sigma": 0.22, "mu": 0.05}, + "GOOGL": {"sigma": 0.25, "mu": 0.05}, + "MSFT": {"sigma": 0.20, "mu": 0.05}, + "AMZN": {"sigma": 0.28, "mu": 0.05}, + "TSLA": {"sigma": 0.50, "mu": 0.03}, # High volatility + "NVDA": {"sigma": 0.40, "mu": 0.08}, # High volatility, strong drift + "META": {"sigma": 0.30, "mu": 0.05}, + "JPM": {"sigma": 0.18, "mu": 0.04}, # Low volatility (bank) + "V": {"sigma": 0.17, "mu": 0.04}, # Low volatility (payments) + "NFLX": {"sigma": 0.35, "mu": 0.05}, +} + +# Default parameters for tickers not in the list above (dynamically added) +DEFAULT_PARAMS: dict[str, float] = {"sigma": 0.25, "mu": 0.05} + +# Correlation groups for the simulator's Cholesky decomposition +# Tickers in the same group have higher intra-group correlation +CORRELATION_GROUPS: dict[str, set[str]] = { + "tech": {"AAPL", "GOOGL", "MSFT", "AMZN", "META", "NVDA", "NFLX"}, + "finance": {"JPM", "V"}, +} + +# Correlation coefficients +INTRA_TECH_CORR = 0.6 # Tech stocks move together +INTRA_FINANCE_CORR = 0.5 # Finance stocks move together +CROSS_GROUP_CORR = 0.3 # Between sectors / unknown tickers +TSLA_CORR = 0.3 # TSLA does its own thing +``` + +Tickers added dynamically that aren't in `SEED_PRICES`/`TICKER_PARAMS` fall +back to a random seed price between $50–$300 and `DEFAULT_PARAMS`. + +--- + +## 7. GBM Simulator + +**File: `backend/app/market/simulator.py`** + +Two classes live here: `GBMSimulator` (pure math engine, stateful) and +`SimulatorDataSource` (the `MarketDataSource` implementation that wraps it +in an async loop and writes to the `PriceCache`). + +### 7.1 The math + +Geometric Brownian Motion is the standard model underlying Black-Scholes: +prices evolve continuously with random noise, can never go negative, and +follow the lognormal distribution seen in real markets. + +``` +S(t+dt) = S(t) * exp((mu - sigma^2/2) * dt + sigma * sqrt(dt) * Z) +``` + +- `S(t)` — current price +- `mu` — annualized drift (expected return), e.g. `0.05` +- `sigma` — annualized volatility, e.g. `0.20` +- `dt` — time step as a fraction of a trading year +- `Z` — a (correlated) standard normal random variable + +For 500ms ticks over a 252-day, 6.5-hour trading year: + +``` +dt = 0.5 / (252 * 6.5 * 3600) ≈ 8.48e-8 +``` + +This tiny `dt` produces sub-cent moves per tick that accumulate naturally +into realistic intraday ranges over time. Prices can never go negative +because the update is multiplicative through `exp()`. + +### 7.2 Correlated moves via Cholesky decomposition + +Real stocks don't move independently — tech stocks tend to move together. +Given a correlation matrix `C`, compute `L = cholesky(C)`; for independent +standard normals `Z_independent`, `Z_correlated = L @ Z_independent` gives +draws with the desired correlation structure. Cholesky decomposition +requires the matrix be positive semi-definite, which holds for any valid +correlation matrix (all diagonal 1s, off-diagonal in `[-1, 1]`, symmetric). + +Correlation structure used here: + +| Pair | Correlation | +|---|---| +| Tech ↔ tech (AAPL, GOOGL, MSFT, AMZN, META, NVDA, NFLX) | 0.6 | +| Finance ↔ finance (JPM, V) | 0.5 | +| TSLA ↔ anything | 0.3 (it does its own thing) | +| Cross-sector / unknown tickers | 0.3 | + +### 7.3 Random shock events + +Each tick, each ticker has a small probability (default `0.001`) of a +sudden 2–5% move — visual drama for the demo. With 10 tickers at 2 +ticks/sec, expect an event roughly every 50 seconds. + +### 7.4 Full implementation + +```python +from __future__ import annotations + +import asyncio +import logging +import math +import random + +import numpy as np + +from .cache import PriceCache +from .interface import MarketDataSource +from .seed_prices import ( + CORRELATION_GROUPS, + CROSS_GROUP_CORR, + DEFAULT_PARAMS, + INTRA_FINANCE_CORR, + INTRA_TECH_CORR, + SEED_PRICES, + TICKER_PARAMS, + TSLA_CORR, +) + +logger = logging.getLogger(__name__) + + +class GBMSimulator: + """Geometric Brownian Motion simulator for correlated stock prices. + + Math: + S(t+dt) = S(t) * exp((mu - sigma^2/2) * dt + sigma * sqrt(dt) * Z) + """ + + # 252 trading days * 6.5 hours/day * 3600 seconds/hour = 5,896,800 seconds + TRADING_SECONDS_PER_YEAR = 252 * 6.5 * 3600 + DEFAULT_DT = 0.5 / TRADING_SECONDS_PER_YEAR # ~8.48e-8 + + def __init__( + self, + tickers: list[str], + dt: float = DEFAULT_DT, + event_probability: float = 0.001, + ) -> None: + self._dt = dt + self._event_prob = event_probability + + self._tickers: list[str] = [] + self._prices: dict[str, float] = {} + self._params: dict[str, dict[str, float]] = {} + self._cholesky: np.ndarray | None = None + + for ticker in tickers: + self._add_ticker_internal(ticker) + self._rebuild_cholesky() + + # --- Public API --- + + def step(self) -> dict[str, float]: + """Advance all tickers by one time step. Returns {ticker: new_price}. + + Hot path — called every 500ms. Keep it fast. + """ + n = len(self._tickers) + if n == 0: + return {} + + z_independent = np.random.standard_normal(n) + z_correlated = self._cholesky @ z_independent if self._cholesky is not None else z_independent + + result: dict[str, float] = {} + for i, ticker in enumerate(self._tickers): + params = self._params[ticker] + mu, sigma = params["mu"], params["sigma"] + + drift = (mu - 0.5 * sigma**2) * self._dt + diffusion = sigma * math.sqrt(self._dt) * z_correlated[i] + self._prices[ticker] *= math.exp(drift + diffusion) + + # Random event: ~0.1% chance per tick per ticker + if random.random() < self._event_prob: + shock_magnitude = random.uniform(0.02, 0.05) + shock_sign = random.choice([-1, 1]) + self._prices[ticker] *= 1 + shock_magnitude * shock_sign + logger.debug( + "Random event on %s: %.1f%% %s", + ticker, shock_magnitude * 100, "up" if shock_sign > 0 else "down", + ) + + result[ticker] = round(self._prices[ticker], 2) + + return result + + def add_ticker(self, ticker: str) -> None: + """Add a ticker to the simulation. Rebuilds the correlation matrix.""" + if ticker in self._prices: + return + self._add_ticker_internal(ticker) + self._rebuild_cholesky() + + def remove_ticker(self, ticker: str) -> None: + """Remove a ticker from the simulation. Rebuilds the correlation matrix.""" + if ticker not in self._prices: + return + self._tickers.remove(ticker) + del self._prices[ticker] + del self._params[ticker] + self._rebuild_cholesky() + + def get_price(self, ticker: str) -> float | None: + """Current price for a ticker, or None if not tracked.""" + return self._prices.get(ticker) + + def get_tickers(self) -> list[str]: + """Return the list of currently tracked tickers.""" + return list(self._tickers) + + # --- Internals --- + + def _add_ticker_internal(self, ticker: str) -> None: + """Add a ticker without rebuilding Cholesky (for batch initialization).""" + if ticker in self._prices: + return + self._tickers.append(ticker) + self._prices[ticker] = SEED_PRICES.get(ticker, random.uniform(50.0, 300.0)) + self._params[ticker] = TICKER_PARAMS.get(ticker, dict(DEFAULT_PARAMS)) + + def _rebuild_cholesky(self) -> None: + """Rebuild the Cholesky decomposition of the ticker correlation matrix. + + Called whenever tickers are added or removed. O(n^2) but n < 50. + """ + n = len(self._tickers) + if n <= 1: + self._cholesky = None + return + + corr = np.eye(n) + for i in range(n): + for j in range(i + 1, n): + rho = self._pairwise_correlation(self._tickers[i], self._tickers[j]) + corr[i, j] = corr[j, i] = rho + + self._cholesky = np.linalg.cholesky(corr) + + @staticmethod + def _pairwise_correlation(t1: str, t2: str) -> float: + """Determine correlation between two tickers based on sector grouping.""" + tech = CORRELATION_GROUPS["tech"] + finance = CORRELATION_GROUPS["finance"] + + # TSLA is in the tech set but behaves independently + if t1 == "TSLA" or t2 == "TSLA": + return TSLA_CORR + if t1 in tech and t2 in tech: + return INTRA_TECH_CORR + if t1 in finance and t2 in finance: + return INTRA_FINANCE_CORR + return CROSS_GROUP_CORR + + +class SimulatorDataSource(MarketDataSource): + """MarketDataSource backed by the GBM simulator. + + Runs a background asyncio task that calls GBMSimulator.step() every + `update_interval` seconds and writes results to the PriceCache. + """ + + def __init__( + self, + price_cache: PriceCache, + update_interval: float = 0.5, + event_probability: float = 0.001, + ) -> None: + self._cache = price_cache + self._interval = update_interval + self._event_prob = event_probability + self._sim: GBMSimulator | None = None + self._task: asyncio.Task | None = None + + async def start(self, tickers: list[str]) -> None: + self._sim = GBMSimulator(tickers=tickers, event_probability=self._event_prob) + # Seed the cache with initial prices so SSE has data immediately + for ticker in tickers: + price = self._sim.get_price(ticker) + if price is not None: + self._cache.update(ticker=ticker, price=price) + self._task = asyncio.create_task(self._run_loop(), name="simulator-loop") + logger.info("Simulator started with %d tickers", len(tickers)) + + async def stop(self) -> None: + if self._task and not self._task.done(): + self._task.cancel() + try: + await self._task + except asyncio.CancelledError: + pass + self._task = None + logger.info("Simulator stopped") + + async def add_ticker(self, ticker: str) -> None: + if self._sim: + self._sim.add_ticker(ticker) + price = self._sim.get_price(ticker) + if price is not None: + self._cache.update(ticker=ticker, price=price) + logger.info("Simulator: added ticker %s", ticker) + + async def remove_ticker(self, ticker: str) -> None: + if self._sim: + self._sim.remove_ticker(ticker) + self._cache.remove(ticker) + logger.info("Simulator: removed ticker %s", ticker) + + def get_tickers(self) -> list[str]: + return self._sim.get_tickers() if self._sim else [] + + async def _run_loop(self) -> None: + """Core loop: step the simulation, write to cache, sleep.""" + while True: + try: + if self._sim: + prices = self._sim.step() + for ticker, price in prices.items(): + self._cache.update(ticker=ticker, price=price) + except Exception: + logger.exception("Simulator step failed") + await asyncio.sleep(self._interval) +``` + +### Key behaviors + +- **Immediate seeding** — `start()` populates the cache with seed prices + *before* the loop begins, so the SSE endpoint has data to send on its + very first tick (no blank-screen delay). +- **Graceful cancellation** — `stop()` cancels the task and awaits it, + swallowing `CancelledError`, for clean shutdown during FastAPI lifespan + teardown. +- **Exception resilience** — the loop catches exceptions per-step so one + bad tick doesn't kill the entire feed. +- **`GBMSimulator.get_tickers()`** is a public method — `SimulatorDataSource` + never reaches into a private attribute to expose the ticker list. + +--- + +## 8. Massive API Client + +**File: `backend/app/market/massive_client.py`** + +Polls the Massive (formerly Polygon.io) REST API snapshot endpoint on a +configurable interval. The client is synchronous, so it runs inside +`asyncio.to_thread()` to avoid blocking the event loop. + +### 8.1 Massive API primer + +- **Package**: `massive` (declared as a core dependency in + `backend/pyproject.toml`; `uv add massive`) +- **Auth**: `RESTClient(api_key=...)` — reads `MASSIVE_API_KEY` automatically + if omitted +- **Rate limits**: free tier 5 req/min → poll every 15s; paid tiers support + polling every 2–5s +- **Primary endpoint**: `GET /v2/snapshot/locale/us/markets/stocks/tickers` + — returns current data for *all requested tickers in one call*, which is + what keeps us within the free-tier rate limit regardless of watchlist size + +```python +from massive import RESTClient +from massive.rest.models import SnapshotMarketType + +client = RESTClient(api_key="...") +snapshots = client.get_snapshot_all( + market_type=SnapshotMarketType.STOCKS, + tickers=["AAPL", "GOOGL", "MSFT"], +) +for snap in snapshots: + print(snap.ticker, snap.last_trade.price, snap.last_trade.timestamp) +``` + +Relevant response fields per ticker: `last_trade.price` (current price used +for trading/display), `last_trade.timestamp` (Unix **milliseconds**), +`day.previous_close` / `day.change_percent` (available if a day-change UI +element is added later). + +### 8.2 Implementation + +```python +from __future__ import annotations + +import asyncio +import logging + +from massive import RESTClient +from massive.rest.models import SnapshotMarketType + +from .cache import PriceCache +from .interface import MarketDataSource + +logger = logging.getLogger(__name__) + + +class MassiveDataSource(MarketDataSource): + """MarketDataSource backed by the Massive (Polygon.io) REST API. + + Polls GET /v2/snapshot/locale/us/markets/stocks/tickers for all watched + tickers in a single API call, then writes results to the PriceCache. + + Rate limits: + - Free tier: 5 req/min → poll every 15s (default) + - Paid tiers: higher limits → poll every 2-5s + """ + + def __init__( + self, + api_key: str, + price_cache: PriceCache, + poll_interval: float = 15.0, + ) -> None: + self._api_key = api_key + self._cache = price_cache + self._interval = poll_interval + self._tickers: list[str] = [] + self._task: asyncio.Task | None = None + self._client: RESTClient | None = None + + async def start(self, tickers: list[str]) -> None: + self._client = RESTClient(api_key=self._api_key) + self._tickers = list(tickers) + + # Do an immediate first poll so the cache has data right away + await self._poll_once() + + self._task = asyncio.create_task(self._poll_loop(), name="massive-poller") + logger.info( + "Massive poller started: %d tickers, %.1fs interval", + len(tickers), self._interval, + ) + + async def stop(self) -> None: + if self._task and not self._task.done(): + self._task.cancel() + try: + await self._task + except asyncio.CancelledError: + pass + self._task = None + self._client = None + logger.info("Massive poller stopped") + + async def add_ticker(self, ticker: str) -> None: + ticker = ticker.upper().strip() + if ticker not in self._tickers: + self._tickers.append(ticker) + logger.info("Massive: added ticker %s (will appear on next poll)", ticker) + + async def remove_ticker(self, ticker: str) -> None: + ticker = ticker.upper().strip() + self._tickers = [t for t in self._tickers if t != ticker] + self._cache.remove(ticker) + logger.info("Massive: removed ticker %s", ticker) + + def get_tickers(self) -> list[str]: + return list(self._tickers) + + # --- Internal --- + + async def _poll_loop(self) -> None: + """Poll on interval. First poll already happened in start().""" + while True: + await asyncio.sleep(self._interval) + await self._poll_once() + + async def _poll_once(self) -> None: + """Execute one poll cycle: fetch snapshots, update cache.""" + if not self._tickers or not self._client: + return + + try: + # The Massive RESTClient is synchronous — run in a thread to + # avoid blocking the event loop. + snapshots = await asyncio.to_thread(self._fetch_snapshots) + processed = 0 + for snap in snapshots: + try: + price = snap.last_trade.price + # Massive timestamps are Unix milliseconds -> seconds + timestamp = snap.last_trade.timestamp / 1000.0 + self._cache.update(ticker=snap.ticker, price=price, timestamp=timestamp) + processed += 1 + except (AttributeError, TypeError) as e: + logger.warning("Skipping snapshot for %s: %s", getattr(snap, "ticker", "???"), e) + logger.debug("Massive poll: updated %d/%d tickers", processed, len(self._tickers)) + + except Exception as e: + logger.error("Massive poll failed: %s", e) + # Don't re-raise — the loop retries on the next interval. + # Common failures: 401 (bad key), 429 (rate limit), network errors. + + def _fetch_snapshots(self) -> list: + """Synchronous call to the Massive REST API. Runs in a thread.""" + return self._client.get_snapshot_all( + market_type=SnapshotMarketType.STOCKS, + tickers=self._tickers, + ) +``` + +Note: imports are at module level (not lazy) because `massive` is a core +dependency of `backend/pyproject.toml` — the simulator path still has zero +*runtime* dependency on it being *configured* (no API key → this module is +simply never instantiated), but the package itself is always installed. + +### 8.3 Error handling philosophy + +The poller is intentionally resilient — a bad response never takes down the +price feed: + +| Error | Behavior | +|---|---| +| **401 Unauthorized** | Logged as error; poller keeps running (user might fix `.env` and restart). | +| **429 Rate Limited** | Logged as error; next poll retries after `poll_interval` seconds. | +| **Network timeout** | Logged as error; retries automatically on next cycle. | +| **Malformed snapshot** | That ticker is skipped with a warning; other tickers in the same response are still processed. | +| **All tickers fail** | Cache retains last-known prices; SSE keeps streaming stale data (better than no data). | + +--- + +## 9. Factory + +**File: `backend/app/market/factory.py`** + +```python +from __future__ import annotations + +import logging +import os + +from .cache import PriceCache +from .interface import MarketDataSource +from .massive_client import MassiveDataSource +from .simulator import SimulatorDataSource + +logger = logging.getLogger(__name__) + + +def create_market_data_source(price_cache: PriceCache) -> MarketDataSource: + """Create the appropriate market data source based on environment variables. + + - MASSIVE_API_KEY set and non-empty -> MassiveDataSource (real market data) + - Otherwise -> SimulatorDataSource (GBM simulation) + + Returns an unstarted source. Caller must await source.start(tickers). + """ + api_key = os.environ.get("MASSIVE_API_KEY", "").strip() + + if api_key: + logger.info("Market data source: Massive API (real data)") + return MassiveDataSource(api_key=api_key, price_cache=price_cache) + else: + logger.info("Market data source: GBM Simulator") + return SimulatorDataSource(price_cache=price_cache) +``` + +Usage at app startup: + +```python +price_cache = PriceCache() +source = create_market_data_source(price_cache) +await source.start(initial_tickers) # e.g., ["AAPL", "GOOGL", ...] +``` + +--- + +## 10. FastAPI Integration + +### 10.1 SSE Streaming Endpoint — `stream.py` (built) + +**File: `backend/app/market/stream.py`** + +A FastAPI route that holds open a long-lived HTTP connection and pushes +price updates to the client as `text/event-stream`. + +```python +from __future__ import annotations + +import asyncio +import json +import logging +from collections.abc import AsyncGenerator + +from fastapi import APIRouter, Request +from fastapi.responses import StreamingResponse + +from .cache import PriceCache + +logger = logging.getLogger(__name__) + +router = APIRouter(prefix="/api/stream", tags=["streaming"]) + + +def create_stream_router(price_cache: PriceCache) -> APIRouter: + """Create the SSE streaming router with a reference to the price cache. + + This factory pattern lets us inject the PriceCache without globals. + """ + + @router.get("/prices") + async def stream_prices(request: Request) -> StreamingResponse: + """SSE endpoint for live price updates. + + Streams all tracked ticker prices every ~500ms. The client connects + with EventSource and receives events in the format: + + data: {"AAPL": {"ticker": "AAPL", "price": 190.50, ...}, ...} + + Includes a retry directive so the browser auto-reconnects on + disconnection (EventSource built-in behavior). + """ + return StreamingResponse( + _generate_events(price_cache, request), + media_type="text/event-stream", + headers={ + "Cache-Control": "no-cache", + "Connection": "keep-alive", + "X-Accel-Buffering": "no", # Disable nginx buffering if proxied + }, + ) + + return router + + +async def _generate_events( + price_cache: PriceCache, + request: Request, + interval: float = 0.5, +) -> AsyncGenerator[str, None]: + """Async generator that yields SSE-formatted price events. + + Sends all prices every `interval` seconds. Stops when the client + disconnects (detected via request.is_disconnected()). + """ + yield "retry: 1000\n\n" # Reconnect after 1s on drop + + last_version = -1 + client_ip = request.client.host if request.client else "unknown" + logger.info("SSE client connected: %s", client_ip) + + try: + while True: + if await request.is_disconnected(): + logger.info("SSE client disconnected: %s", client_ip) + break + + current_version = price_cache.version + if current_version != last_version: + last_version = current_version + prices = price_cache.get_all() + if prices: + data = {ticker: update.to_dict() for ticker, update in prices.items()} + yield f"data: {json.dumps(data)}\n\n" + + await asyncio.sleep(interval) + except asyncio.CancelledError: + logger.info("SSE stream cancelled for: %s", client_ip) +``` + +**Wire format** — each event looks like: + +``` +data: {"AAPL":{"ticker":"AAPL","price":190.50,"previous_price":190.42,"timestamp":1707580800.5,"change":0.08,"change_percent":0.042,"direction":"up"},"GOOGL":{...}} + +``` + +Client-side (`EventSource`, native browser API — no library needed): + +```javascript +const eventSource = new EventSource('/api/stream/prices'); +eventSource.onmessage = (event) => { + const prices = JSON.parse(event.data); + // prices is { "AAPL": { ticker, price, previous_price, change, change_percent, direction, timestamp }, ... } +}; +``` + +**Why poll-and-push instead of event-driven?** The endpoint polls the cache +on a fixed interval rather than being notified by the data source +directly. This is simpler and produces evenly-spaced updates, which matters +because the frontend accumulates them into sparkline charts — regular +spacing keeps that visualization clean regardless of which backend data +source is active. + +### 10.2 Lifecycle Integration — `main.py` (not yet built) + +`backend/app/main.py` does not exist yet. This is the design for wiring +the market data subsystem into the FastAPI app via the `lifespan` context +manager, so whoever builds the rest of the backend (portfolio, watchlist, +chat routes) has a concrete pattern to follow. + +```python +from contextlib import asynccontextmanager + +from fastapi import FastAPI + +from app.market import PriceCache, create_market_data_source, create_stream_router +from app.market.interface import MarketDataSource + + +@asynccontextmanager +async def lifespan(app: FastAPI): + """Manage startup and shutdown of background services.""" + + # --- STARTUP --- + price_cache = PriceCache() + app.state.price_cache = price_cache + + source = create_market_data_source(price_cache) + app.state.market_source = source + + # Load initial tickers from the database watchlist (lazily initializes + # the DB and seeds default tickers on first run — see PLAN.md §7) + initial_tickers = await load_watchlist_tickers() + await source.start(initial_tickers) + + stream_router = create_stream_router(price_cache) + app.include_router(stream_router) + + yield # App is running + + # --- SHUTDOWN --- + await source.stop() + + +app = FastAPI(title="FinAlly", lifespan=lifespan) + + +def get_price_cache() -> PriceCache: + return app.state.price_cache + + +def get_market_source() -> MarketDataSource: + return app.state.market_source +``` + +Other routes access the price cache and data source via dependency +injection: + +```python +from fastapi import APIRouter, Depends, HTTPException + +router = APIRouter(prefix="/api") + + +@router.post("/portfolio/trade") +async def execute_trade( + trade: TradeRequest, + price_cache: PriceCache = Depends(get_price_cache), +): + current_price = price_cache.get_price(trade.ticker) + if current_price is None: + raise HTTPException(404, f"No price available for {trade.ticker}") + # ... execute trade at current_price ... + + +@router.post("/watchlist") +async def add_to_watchlist( + payload: WatchlistAdd, + source: MarketDataSource = Depends(get_market_source), +): + # ... insert into watchlist table ... + await source.add_ticker(payload.ticker) + # ... + + +@router.delete("/watchlist/{ticker}") +async def remove_from_watchlist( + ticker: str, + source: MarketDataSource = Depends(get_market_source), +): + # ... delete from watchlist table ... + await source.remove_ticker(ticker) + # ... +``` + +--- + +## 11. Watchlist Coordination + +When the watchlist changes (via REST API or LLM chat action), the market +data source must be told so it tracks the right set of tickers. + +### Adding a ticker + +``` +User (or LLM) -> POST /api/watchlist {ticker: "PYPL"} + -> Insert into watchlist table (SQLite) + -> await source.add_ticker("PYPL") + Simulator: adds to GBMSimulator, rebuilds Cholesky, seeds cache immediately + Massive: appends to ticker list, appears on next poll (up to poll_interval delay) + -> Return success (ticker + current price if available) +``` + +### Removing a ticker + +``` +User (or LLM) -> DELETE /api/watchlist/PYPL + -> Delete from watchlist table (SQLite) + -> await source.remove_ticker("PYPL") + Simulator: removes from GBMSimulator, rebuilds Cholesky, removes from cache + Massive: removes from ticker list, removes from cache + -> Return success +``` + +### Edge case: ticker still has an open position + +If the user removes a ticker from the watchlist but still holds shares, the +data source must keep tracking it so portfolio valuation stays accurate. +The watchlist route is responsible for this check — the market data layer +itself has no concept of "positions": + +```python +@router.delete("/watchlist/{ticker}") +async def remove_from_watchlist( + ticker: str, + source: MarketDataSource = Depends(get_market_source), +): + await db.delete_watchlist_entry(ticker) + + position = await db.get_position(ticker) + if position is None or position.quantity == 0: + await source.remove_ticker(ticker) + + return {"status": "ok"} +``` + +--- + +## 12. Testing Strategy + +**File location: `backend/tests/market/`** — 6 modules, 73 tests, 84% +overall coverage (see `planning/MARKET_DATA_SUMMARY.md` for the full +breakdown). Summary of what each module verifies: + +| Module | Focus | +|---|---| +| `test_models.py` | `PriceUpdate` computed properties (`change`, `change_percent`, `direction`), `to_dict()` serialization, immutability | +| `test_cache.py` | update/get/get_all/remove, first-update-is-flat, direction on up/down, version increments on every write | +| `test_simulator.py` | `GBMSimulator.step()` always returns all tickers, prices stay positive over 10k steps, add/remove ticker rebuilds Cholesky, unknown ticker gets a random seed in range, empty ticker list is a no-op | +| `test_simulator_source.py` | `SimulatorDataSource.start()` seeds the cache before the first tick, prices change over time, `stop()` is idempotent, `add_ticker`/`remove_ticker` propagate to both the simulator and the cache | +| `test_factory.py` | `MASSIVE_API_KEY` set → `MassiveDataSource`; unset/empty → `SimulatorDataSource` | +| `test_massive.py` | `_poll_once` updates the cache from mocked snapshots, malformed snapshots are skipped without aborting the batch, API exceptions don't crash the poller | + +Representative test (full suite is in the repo): + +```python +# backend/tests/market/test_simulator.py +class TestGBMSimulator: + def test_prices_are_positive(self): + """GBM prices can never go negative (exp() is always positive).""" + sim = GBMSimulator(tickers=["AAPL"]) + for _ in range(10_000): + prices = sim.step() + assert prices["AAPL"] > 0 + + def test_cholesky_rebuilds_on_add(self): + sim = GBMSimulator(tickers=["AAPL"]) + assert sim._cholesky is None # Only 1 ticker, no correlation matrix + sim.add_ticker("GOOGL") + assert sim._cholesky is not None +``` + +```python +# backend/tests/market/test_massive.py +@pytest.mark.asyncio +class TestMassiveDataSource: + async def test_malformed_snapshot_skipped(self): + cache = PriceCache() + source = MassiveDataSource(api_key="test-key", price_cache=cache, poll_interval=60.0) + source._tickers = ["AAPL", "BAD"] + + good_snap = _make_snapshot("AAPL", 190.50, 1707580800000) + bad_snap = MagicMock(ticker="BAD", last_trade=None) # triggers AttributeError + + with patch.object(source, "_fetch_snapshots", return_value=[good_snap, bad_snap]): + await source._poll_once() + + assert cache.get_price("AAPL") == 190.50 + assert cache.get_price("BAD") is None +``` + +Run locally: + +```bash +cd backend +uv run --extra dev pytest -v +uv run --extra dev pytest --cov=app +``` + +### Gaps to be aware of + +- `stream.py` has low direct coverage (31%) — exercising the SSE generator + properly requires a running ASGI test client (e.g. `httpx.AsyncClient` + against the FastAPI `app`), which isn't possible until `main.py` exists. + Add an SSE integration test once the app is wired up in §10.2. +- No dedicated concurrent-writer stress test for `PriceCache` (lock + correctness is verified by inspection, not empirically under contention). + +--- + +## 13. Error Handling & Edge Cases + +### 13.1 Startup with an empty watchlist + +If the database has no watchlist entries, `start()` receives an empty +list. Both data sources handle this gracefully — the simulator produces no +prices, the Massive poller skips its API call entirely. The SSE endpoint +simply sends no events until a ticker is added, at which point tracking +starts immediately. + +### 13.2 Price cache miss during a trade + +If a user tries to trade a ticker with no cached price yet (just added, +Massive hasn't polled it): + +```python +price = price_cache.get_price(ticker) +if price is None: + raise HTTPException( + status_code=400, + detail=f"Price not yet available for {ticker}. Please wait a moment and try again.", + ) +``` + +The simulator avoids this entirely by seeding the cache synchronously +inside `add_ticker()`. The Massive client may have a brief gap until its +next poll — the 400 with a clear message is the correct response there. + +### 13.3 Massive API key invalid + +If the key is set but wrong, the first poll fails with 401. The poller +logs the error and keeps retrying every `poll_interval`. SSE keeps +streaming (connected, just empty). The fix is correcting `.env` and +restarting the container. + +### 13.4 Thread safety under load + +`PriceCache` uses a `threading.Lock` (a mutex). Under expected load (10 +tickers, 2 updates/sec, one SSE reader per browser tab) contention is +negligible — the critical section is a dict lookup plus assignment. If this +ever became a bottleneck (hundreds of tickers, many concurrent readers) a +`ReadWriteLock` would be the fix, but that's unnecessary for this project's +scale. + +### 13.5 Simulator numerical precision + +The tiny `dt` produces very small per-tick moves; this is not a precision +concern because prices are rounded to 2 decimals in `GBMSimulator.step()`, +the `exp(drift + diffusion)` formulation is numerically stable, and prices +are always positive by construction (exponential of a real number). + +--- + +## 14. Configuration Summary + +| Parameter | Location | Default | Description | +|---|---|---|---| +| `MASSIVE_API_KEY` | Environment variable | `""` (empty) | If set, use Massive API; otherwise use the simulator | +| `update_interval` | `SimulatorDataSource.__init__` | `0.5` s | Time between simulator ticks | +| `poll_interval` | `MassiveDataSource.__init__` | `15.0` s | Time between Massive API polls (free tier: 5 req/min) | +| `event_probability` | `GBMSimulator.__init__` | `0.001` | Chance of a random shock event per ticker per tick | +| `dt` | `GBMSimulator.__init__` | `~8.5e-8` | GBM time step (fraction of a trading year) | +| SSE push interval | `_generate_events()` | `0.5` s | Time between SSE pushes to a connected client | +| SSE retry directive | `_generate_events()` | `1000` ms | Browser `EventSource` reconnection delay | + +### Package `__init__.py` + +**File: `backend/app/market/__init__.py`** + +```python +"""Market data subsystem for FinAlly. + +Public API: + PriceUpdate - Immutable price snapshot dataclass + PriceCache - Thread-safe in-memory price store + MarketDataSource - Abstract interface for data providers + create_market_data_source - Factory that selects simulator or Massive + create_stream_router - FastAPI router factory for SSE endpoint +""" + +from .cache import PriceCache +from .factory import create_market_data_source +from .interface import MarketDataSource +from .models import PriceUpdate +from .stream import create_stream_router + +__all__ = [ + "PriceUpdate", + "PriceCache", + "MarketDataSource", + "create_market_data_source", + "create_stream_router", +] +```