Claude/2 plus 2 calculation xhqecf

.claude/settings.json

@@ -1,7 +1,5 @@
 {
   "enabledPlugins": {
-    "frontend-design@claude-plugins-official": true,
-    "context7@claude-plugins-official": true,
-    "playwright@claude-plugins-official": true
+    "independent-reviewer@ed-tools": true
   }
 }

.github/workflows/claude-code-review.yml

@@ -38,7 +38,8 @@ jobs:
           claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
           plugin_marketplaces: 'https://github.com/anthropics/claude-code.git'
           plugins: 'code-review@claude-code-plugins'
-          prompt: '/code-review:code-review ${{ github.repository }}/pull/${{ github.event.pull_request.number }}'
+          prompt: '/code-review:code-review --comment ${{ github.repository }}/pull/${{ github.event.pull_request.number }}'
+          claude_args: '--allowedTools "mcp__github_inline_comment__create_inline_comment"'
           # See https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
           # or https://code.claude.com/docs/en/cli-reference for available options
 

.github/workflows/claude.yml

@@ -46,5 +46,5 @@ jobs:
           # Optional: Add claude_args to customize behavior and configuration
           # See https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
           # or https://code.claude.com/docs/en/cli-reference for available options
-          # claude_args: '--allowed-tools Bash(gh pr:*)'
+          # claude_args: '--allowed-tools Bash(gh pr *)'
 

README.md

@@ -1,61 +1,59 @@
 # FinAlly — AI Trading Workstation
 
-A visually stunning AI-powered trading workstation that streams live market data, simulates portfolio trading, and integrates an LLM chat assistant that can analyze positions and execute trades via natural language.
+A trading terminal that streams live market data, simulates portfolio trading, and puts
+an LLM assistant beside your positions — one that can analyze holdings and execute trades
+from natural language.
 
-Built entirely by coding agents as a capstone project for an agentic AI coding course.
+Built entirely by coding agents as the capstone for an agentic AI coding course. Agents
+coordinate through shared docs in [`planning/`](planning/).
 
-## Features
+## Status
 
-- **Live price streaming** via SSE with green/red flash animations
-- **Simulated portfolio** — $10k virtual cash, market orders, instant fills
-- **Portfolio visualizations** — heatmap (treemap), P&L chart, positions table
-- **AI chat assistant** — analyzes holdings, suggests and auto-executes trades
-- **Watchlist management** — track tickers manually or via AI
-- **Dark terminal aesthetic** — Bloomberg-inspired, data-dense layout
+**Early — market data is the only component built.** There's no frontend and no Dockerfile
+yet, so the app doesn't run end to end.
 
-## Architecture
-
-Single Docker container serving everything on port 8000:
+| Component | Status |
+|---|---|
+| Market data — simulator, Massive client, price cache, SSE | ✅ 73 tests, 84% coverage |
+| Portfolio, trades, watchlist, chat API | ⬜ |
+| Database, frontend, Docker, E2E tests | ⬜ |
 
-- **Frontend**: Next.js (static export) with TypeScript and Tailwind CSS
-- **Backend**: FastAPI (Python/uv) with SSE streaming
-- **Database**: SQLite with lazy initialization
-- **AI**: LiteLLM → OpenRouter (Cerebras inference) with structured outputs
-- **Market data**: Built-in GBM simulator (default) or Massive API (optional)
+## Try It
 
-## Quick Start
+Requires [uv](https://docs.astral.sh/uv/) and Python 3.12+. No API key needed.
 
 ```bash
-# Clone and configure
-cp .env.example .env
-# Add your OPENROUTER_API_KEY to .env
+cd backend
+uv sync --dev
+uv run market_data_demo.py   # live terminal dashboard, 10 tickers, ~60s
+uv run pytest                # test suite
+```
 
-# Run with Docker
-docker build -t finally .
-docker run -v finally-data:/app/db -p 8000:8000 --env-file .env finally
+## Architecture
 
-# Open http://localhost:8000
-```
+Target design is one Docker container on port 8000: a **Next.js** static export served by
+**FastAPI**, backed by **SQLite**, with **LiteLLM → OpenRouter** (Cerebras) for chat and
+Server-Sent Events for price streaming. Single origin, so no CORS.
 
-## Environment Variables
+Market data has two interchangeable sources behind one interface — a GBM simulator
+(default) and a Massive/Polygon.io poller (when `MASSIVE_API_KEY` is set) — both writing
+to a thread-safe `PriceCache` that SSE, portfolio valuation, and trade pricing read from.
+See [`planning/MARKET_DATA_SUMMARY.md`](planning/MARKET_DATA_SUMMARY.md).
 
-| Variable | Required | Description |
-|---|---|---|
-| `OPENROUTER_API_KEY` | Yes | OpenRouter API key for AI chat |
-| `MASSIVE_API_KEY` | No | Massive (Polygon.io) key for real market data; omit to use simulator |
-| `LLM_MOCK` | No | Set `true` for deterministic mock LLM responses (testing) |
+## Configuration
 
-## Project Structure
+Read from a gitignored `.env` in the project root.
 
-```
-finally/
-├── frontend/    # Next.js static export
-├── backend/     # FastAPI uv project
-├── planning/    # Project documentation and agent contracts
-├── test/        # Playwright E2E tests
-├── db/          # SQLite volume mount (runtime)
-└── scripts/     # Start/stop helpers
-```
+| Variable | Description |
+|---|---|
+| `OPENROUTER_API_KEY` | LLM assistant. Everything except chat works without it. |
+| `MASSIVE_API_KEY` | Optional — real market data. Omit to use the simulator. |
+| `LLM_MOCK` | Optional — `true` for deterministic mock responses in tests. |
+
+## Docs
+
+- [`planning/PLAN.md`](planning/PLAN.md) — full spec, and the contract between agents
+- [`backend/README.md`](backend/README.md) — backend development and testing
 
 ## License