Files
nofx/docker-compose.yml
T
Liu Xiang Qian f8edc0ec11 fix: add AI_MAX_TOKENS environment variable to prevent response truncation
## Problem
AI responses were being truncated due to a hardcoded max_tokens limit of 2000,
causing JSON parsing failures. The error occurred when:
1. AI's thought process analysis was cut off mid-response
2. extractDecisions() incorrectly extracted MACD data arrays from the input prompt
3. Go failed to unmarshal numbers into Decision struct
Error message:
```
json: cannot unmarshal number into Go value of type decision.Decision
JSON内容: [-867.759, -937.406, -1020.435, ...]
```
## Solution
- Add MaxTokens field to mcp.Client struct
- Read AI_MAX_TOKENS from environment variable (default: 2000)
- Set AI_MAX_TOKENS=4000 in docker-compose.yml for production use
- This provides enough tokens for complete analysis with the 800-line trading strategy prompt
## Testing
- Verify environment variable is read correctly
- Confirm AI responses are no longer truncated
- Check decision logs for complete JSON output
2025-11-05 09:31:58 +08:00

52 lines
1.4 KiB
YAML
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
services:
# Backend service (API and core logic)
nofx:
build:
context: .
dockerfile: ./docker/Dockerfile.backend
container_name: nofx-trading
restart: unless-stopped
ports:
- "${NOFX_BACKEND_PORT:-8080}:8080"
volumes:
- ./config.json:/app/config.json:ro
- ./config.db:/app/config.db
- ./beta_codes.txt:/app/beta_codes.txt:ro
- ./decision_logs:/app/decision_logs
- ./prompts:/app/prompts
- /etc/localtime:/etc/localtime:ro # Sync host time
environment:
- TZ=${NOFX_TIMEZONE:-Asia/Shanghai} # Set timezone
- AI_MAX_TOKENS=4000 # AI响应的最大token数(默认2000,建议4000-8000
networks:
- nofx-network
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:8080/api/health"]
interval: 30s
timeout: 10s
retries: 3
start_period: 60s
# Frontend service (static serving and proxy)
nofx-frontend:
build:
context: .
dockerfile: ./docker/Dockerfile.frontend
container_name: nofx-frontend
restart: unless-stopped
ports:
- "${NOFX_FRONTEND_PORT:-3000}:80"
networks:
- nofx-network
depends_on:
- nofx
healthcheck:
test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost/health"]
interval: 30s
timeout: 10s
retries: 3
start_period: 5s
networks:
nofx-network:
driver: bridge