Slack Trading Agent

The Slack Agent (slack_agent/app.py, ~1,960 lines) is an interactive trading bot that brings DepthSight's full capabilities into Slack. It renders rich visual cards as PNG images via Playwright headless Chromium, providing instant access to backtest results, market analysis, portfolio monitoring, and live trade alerts — all without leaving Slack.

---

Architecture

Key Components

Component	File	Purpose
Bot Entry Point	slack_agent/app.py	Slack Bolt SDK, slash commands, event handlers, button/modals
Card Renderer	slack_agent/card_renderer.py	HTML → PNG rendering via Playwright
Templates	slack_agent/templates/*.html	Four dark-theme card templates
API Client	slack_agent/app.py:52-288	DepthSightAPIClient — HTTP client for backend
Socket Wrapper	slack_agent/app.py:289-412	SlackWebSocketWrapper — manages Socket Mode lifecycle + reconnection
Chat Handler	slack_agent/app.py:413-530	handle_chat_message() — AI conversation with strategy JSON + trigger phrases
Autopilot Bridge	slack_agent/app.py:1812-1960	run_autopilot_and_send() — full autopilot loop with card rendering

Card Rendering Pipeline

HTML Template ({{ placeholders }})
  → String substitution with real/mock data
  → Playwright headless Chromium (800×420 or 800×480)
  → Google Fonts (Inter, Montserrat) loaded
  → 300ms settle for SVG animations
  → page.screenshot(type="png")
  → files_upload_v2 → Slack channel

---

Slack Commands & Interactions

Slash Command: /depthsight

Subcommand	Description	Card
help (or empty)	Show interactive help menu	—
analyze <symbol>	Market analysis (default BTCUSDT)	Market Analysis
backtest <symbol>	Run backtest simulation (default BTCUSDT)	Backtest Report
portfolio	Portfolio dashboard	Portfolio
memory	View agent memory summary	—
optimize <symbol>	Trigger autopilot loop for strategy optimization	Backtest Report
clear / reset	Clear AI chat session history	—
(anything else)	Passed to AI chat	—

Interactive Buttons

Button	Action
Analyze BTC	Instant market analysis for BTCUSDT
Backtest ETH	Opens backtest configuration modal
View Portfolio	Renders portfolio dashboard
Generate Strategy	Triggers AI strategy generation
Run Backtest	Opens modal with date, timeframe, capital inputs
Deploy Live	Deploys strategy as live trading bot

Events

Event	Behavior
@DepthSight mention	Starts AI conversation in thread
Direct Message	AI conversation; replies in thread stay active
Modal submission	Captures backtest config params
Button click	Routes to handler based on action_id prefix (analyze_, backtest_, run_autopilot_, etc.)

Button Interactions

Buttons are routed by action_id prefixes in the Slack interaction handler:

Prefix	Handler
analyze_*	handle_analyze_button() — runs market analysis for the symbol
backtest_*	Opens backtest config modal
run_autopilot_*	Opens autopilot config modal
view_portfolio	handle_portfolio() — renders portfolio card
generate_strategy	Opens strategy generation modal

Chat Message Flow

handle_chat_message() (slack_agent/app.py:413-530) handles all AI conversation messages:

1. Sends user input to POST /ai/chat via DepthSightAPIClient
2. Checks response for strategy JSON — if present, renders a backtest card
3. Listens for trigger phrases (run backtest, optimize, etc.) for card rendering cues
4. Tracks active threads to maintain conversation context across replies

---

SlackWebSocketWrapper

Sources: app.py

The wrapper handles:

• Auto-reconnection — reconnects on WebSocket disconnect with 5s backoff
• Graceful shutdown — cancels all pending tasks on SIGINT/SIGTERM
• Health monitoring — logs connection status at startup and on reconnect

---

Autopilot Bridge

The run_autopilot_and_send() function (slack_agent/app.py:1812-1960) bridges the autopilot loop into Slack:

1. Calls POST /ai/autopilot with symbol + params
2. Polls for completion (120 retries × 5s, matching the backtest poll pattern)
3. On completion, renders the result as a backtest card
4. Uploads card image to Slack with the strategy name as filename

---

MCP Query Integration

When a chat message contains market/symbol queries, the Slack agent can trigger MCP memory lookups:

1. handle_chat_message() detects query keywords
2. Calls GET /ai/memories via DepthSightAPIClient
3. Injects memory context into the AI prompt before sending to chat endpoint
4. Returns augmented response with memory-backed insights

---

Card Gallery

1. Backtest Result Card

A dark-themed card with the strategy name and DepthSight logo at top. Left panel shows the equity curve (SVG polyline with blue gradient fill). Right panel displays six KPIs in a 2×3 grid.

Dimensions: 800×480 px. Pipeline:

Backtest Logic Flow

Sources: app.py

2. Market Analysis Card

Dimensions: 800×420 px. Header with symbol + current price + 24h change. Left: sparkline chart. Right: four indicator panels (RSI, Volume, Trend, Volatility). Bottom: AI Insight box with real-time model commentary.

3. Portfolio Dashboard Card

Dimensions: 800×420 px. Hero PnL number at top, 4 stat cards (active bots, today's trades, win rate, today's PnL), 7-day bar chart, active bot pills at bottom.

4. Trade Alert Card

Dimensions: 800×420 px. Signal badge with animated pulsing green dot, symbol + strategy name. Left column: trade details (entry, size, SL, TP). Right panel: confidence score with gradient bar + unrealized PnL.

---

Card Templates

All templates share:

• Dark theme gradient (#1c1917 → #111827)
• Inter font for body, Montserrat for the DepthSight logo
• Animated reticle logo SVG with rotating crosshair
• depthsight.pro footer branding
• Placeholder substitution via {{ KEY }} syntax

Template Structure

Card	File	Dimensions	Sections
Backtest	templates/backtest_card.html	800×480	Strategy name + subtitle, equity chart (SVG), 2×3 KPI grid
Market Analysis	templates/market_analysis_card.html	800×420	Symbol + price header, sparkline chart, 4 indicator panels, AI insight
Portfolio	templates/portfolio_card.html	800×420	Hero PnL, 4 stat cards, 7-day bar chart, active bot pills
Trade Alert	templates/trade_alert_card.html	800×420	Signal badge + pulsing dot, trade details, confidence bar, unrealized PnL

---

Backend Integration

DepthSight API Endpoints

The Slack agent communicates with the main DepthSight API via DepthSightAPIClient:

Sources: app.py

API Endpoint	Method	Purpose
/api/v1/ai/chat	POST	AI conversation (advisor / generator modes)
/api/v1/ai/chat/history/{id}	DELETE	Clear session context
/api/v1/ai/memories	GET	Fetch agent memories
/api/v1/ai/autopilot	POST	Start autopilot loop
/api/v1/ai/optimize	POST	Start optimization process
/api/v1/strategies/config	POST	Save generated strategy
/api/v1/strategies/config	GET	List saved strategies
/api/v1/strategies/config/{id}	GET	Fetch saved strategy
/api/v1/strategies/config/{id}	DELETE	Delete saved strategy
/api/v1/backtests	POST	Queue backtest task
/api/v1/backtests/{task_id}	GET	Poll backtest results
/api/v1/portfolio/portfolio?mode=live	GET	Fetch portfolio stats

Authentication

Method	When Used
JWT Bearer	DEPTHSIGHT_JWT_TOKEN env var set (testing against production)
Trusted Slack Bypass	Default — sends X-Slack-Secret, X-User-Email, Authorization: Bearer slack_bot_trusted_bypass

Binance Public API

Endpoint	Function	Purpose
api.binance.com/api/v3/ticker/24hr	fetch_binance_ticker()	24h price + volume data
api.binance.com/api/v3/klines	fetch_binance_history()	24 hourly candles for sparkline

Mock Data Fallback

When the backend API is unreachable, the bot falls back to realistic mock data:

Card	Mock Strategy
Backtest	Random walk equity curve (random.uniform(-0.015, 0.025)), KPIs in realistic ranges (WR 53-65%, DD 7-15%, PF 1.6-2.3, Sharpe 1.2-2.0)
Portfolio	3 default bots ("BTC Momentum v2", "ETH Breakout Pro", "SOL DCA Grid"), 7-day PnL with daily variance
Market Analysis	RSI 45-68, trend/volatility inferred from price change, generated AI insight text

---

Deployment

Environment Variables

Variable	Default	Description
SLACK_BOT_TOKEN	—	Slack Bot User OAuth Token (xoxb-...)
SLACK_APP_TOKEN	—	Slack App-Level Token (xapp-...)
DEPTHSIGHT_API_URL	http://localhost:8000/api/v1	Backend API base URL
API_KEY_SECRET	—	Shared secret for trusted Slack auth
DEPTHSIGHT_JWT_TOKEN	—	Optional JWT for production testing
MCP_MEMORY_HOST	127.0.0.1	MCP memory server host
MCP_MEMORY_PORT	8100	MCP memory server port
PLAYWRIGHT_BROWSERS_PATH	—	Chromium path for card rendering

Running

# Install dependencies
pip install -r requirements.txt
playwright install chromium

# Start the bot
python -m slack_agent.app

The bot connects via Socket Mode (no public HTTP endpoint needed). It uses asyncio throughout, with asyncio.create_task() for background card rendering and polling.

---

Why This Wins

Feature	What We Show
Rich Visual Cards	HTML/CSS → Playwright → PNG — not plain Slack Block Kit
Multi-Card Gallery	Backtest, Market Analysis, Portfolio, Trade Alert — four distinct card types
Real-Time Alerts	Trade signals with animated pulsing dots, confidence bars, unrealized PnL
AI Integration	Full AI assistant chat via @mentions and DMs
Self-Healing	Mock data fallback when backend is unreachable
Socket Mode	No public endpoint needed, works behind NAT
Thread Context	Active thread tracking keeps multi-turn conversations coherent