v1.1 autonomous upgrade: continuous curation, risk engine, scheduler hardening, systemd service

README.md

@@ -1,33 +1,50 @@
 # alpaca-llm-bot-v1
 
-Autonomous 2-hour trading loop powered by:
+Autonomous LLM trading system (paper-first) powered by:
 - Alpaca trading API
 - Ollama local model inference
 - Searx web data ingestion
 - FastAPI dark dashboard
+- APScheduler autonomous loops
 
-## Safety defaults
-- `PAPER_MODE=true`
-- max order notional `$5`
-- confidence gate `>= 0.55` before order placement
+## Autonomous behavior
+- Curates market/news context every `CURATE_INTERVAL_MINUTES` (default 30)
+- Runs trade decision cycle every `TRADE_INTERVAL_HOURS` (default 2)
+- LLM decides buy/sell/hold per symbol
+- Executes only if confidence >= `MIN_CONFIDENCE`
+- Hard risk caps:
+  - max `$5` order notional (default)
+  - max daily notional cap
+  - max open positions cap
+  - market-open gate
 
 ## Quick start
 ```bash
 cp .env.example .env
 # fill ALPACA_API_KEY / ALPACA_API_SECRET
-chmod +x run.sh
-./run.sh
+python3 -m venv .venv
+source .venv/bin/activate
+pip install -r requirements.txt
+uvicorn app:app --host 0.0.0.0 --port 8089
 ```
 
-Open dashboard:
+Dashboard:
 - `http://<host>:8089/`
 
-Trigger immediate cycle:
+Manual triggers:
 ```bash
+curl -X POST http://127.0.0.1:8089/curate-now
 curl -X POST http://127.0.0.1:8089/run-now
 ```
 
-## Production notes
-- Put behind reverse proxy + auth
-- Keep paper mode until behavior validated
-- Add hard stop-loss and max daily drawdown before enabling live mode
+## Production service (systemd)
+```bash
+sudo cp systemd/alpaca-llm-bot-v1.service /etc/systemd/system/
+sudo systemctl daemon-reload
+sudo systemctl enable --now alpaca-llm-bot-v1
+sudo systemctl status alpaca-llm-bot-v1
+```
+
+## Important
+- Keep `PAPER_MODE=true` until you observe stable behavior.
+- This is experimental and not financial advice.