cillin
16b54d5ccc
Migrate all agent roles from Legacy to EvoAgent architecture: - fundamentals_analyst, technical_analyst, sentiment_analyst, valuation_analyst - risk_manager, portfolio_manager Key changes: - EvoAgent now supports Portfolio Manager compatibility methods (_make_decision, get_decisions, get_portfolio_state, load_portfolio_state, update_portfolio) - Add UnifiedAgentFactory for centralized agent creation - ToolGuard with batch approval API and WebSocket broadcast - Legacy agents marked deprecated (AnalystAgent, RiskAgent, PMAgent) - Remove backend/agents/compat.py migration shim - Add run_id alongside workspace_id for semantic clarity - Complete integration test coverage (13 tests) - All smoke tests passing for 6 agent roles Constraint: Must maintain backward compatibility with existing run configs Constraint: Memory support must work with EvoAgent (no fallback to Legacy) Rejected: Separate PM implementation for EvoAgent | unified approach cleaner Confidence: high Scope-risk: broad Directive: EVO_AGENT_IDS env var still respected but defaults to all roles Not-tested: Kubernetes sandbox mode for skill execution
60 lines
2.1 KiB
Plaintext
60 lines
2.1 KiB
Plaintext
# Copy this file to `.env` for local development.
|
|
# Keep `.env` untracked and never paste real secrets into tracked files.
|
|
|
|
# ================== General Configuration | 通用配置 ==================
|
|
TICKERS=AAPL,MSFT,GOOGL,AMZN,NVDA,META,TSLA,AMD,NFLX,AVGO,PLTR,COIN
|
|
|
|
# Financial Data API
|
|
# At least `FINANCIAL_DATASETS_API_KEY` is required when using `FIN_DATA_SOURCE=financial_datasets`.
|
|
# `FINNHUB_API_KEY` is recommended for `FIN_DATA_SOURCE=finnhub` and required for live mode.
|
|
FIN_DATA_SOURCE=finnhub
|
|
ENABLED_DATA_SOURCES=financial_datasets,finnhub,yfinance,local_csv
|
|
FINANCIAL_DATASETS_API_KEY=
|
|
FINNHUB_API_KEY=
|
|
POLYGON_API_KEY=
|
|
MARKET_DB_PATH=
|
|
|
|
# Model API
|
|
OPENAI_API_KEY=
|
|
OPENAI_BASE_URL=
|
|
MODEL_NAME=qwen3-max-preview
|
|
EXPLAIN_ENRICH_USE_LLM=false
|
|
EXPLAIN_ENRICH_MODEL_PROVIDER=
|
|
EXPLAIN_ENRICH_MODEL_NAME=
|
|
EXPLAIN_RANGE_USE_LLM=
|
|
|
|
# Memory module
|
|
MEMORY_API_KEY=
|
|
|
|
# Experimental EvoAgent rollout for selected analysts only.
|
|
# Example: EVO_AGENT_IDS=fundamentals_analyst,risk_manager,portfolio_manager
|
|
EVO_AGENT_IDS=
|
|
|
|
# ================== Agent-Specific Model Configuration | Agent特定模型配置 ==================
|
|
AGENT_SENTIMENT_ANALYST_MODEL_NAME=deepseek-v3.2-exp
|
|
AGENT_TECHNICAL_ANALYST_MODEL_NAME=glm-4.6
|
|
AGENT_FUNDAMENTALS_ANALYST_MODEL_NAME=qwen3-max-preview
|
|
AGENT_VALUATION_ANALYST_MODEL_NAME=Moonshot-Kimi-K2-Instruct
|
|
AGENT_RISK_MANAGER_MODEL_NAME=qwen3-max-preview
|
|
AGENT_PORTFOLIO_MANAGER_MODEL_NAME=qwen3-max-preview
|
|
|
|
# ================== Advanced Configuration | 高阶配置 ==================
|
|
|
|
# Skill Sandbox Mode | 技能沙盒执行模式
|
|
# none = direct execution (default, development only) | 直接执行（默认，仅开发环境）
|
|
# docker = Docker container isolation | Docker 容器隔离
|
|
# kubernetes = Kubernetes Pod isolation (reserved) | Kubernetes Pod 隔离（预留）
|
|
SKILL_SANDBOX_MODE=none
|
|
|
|
# Docker Sandbox Settings (only used when SKILL_SANDBOX_MODE=docker) | Docker 沙盒配置
|
|
SKILL_SANDBOX_IMAGE=python:3.11-slim
|
|
SKILL_SANDBOX_MEMORY_LIMIT=512m
|
|
SKILL_SANDBOX_CPU_LIMIT=1.0
|
|
SKILL_SANDBOX_NETWORK=none
|
|
SKILL_SANDBOX_TIMEOUT=60
|
|
|
|
MAX_COMM_CYCLES=2
|
|
MARGIN_REQUIREMENT=0.5
|
|
DATA_START_DATE=2022-01-01
|
|
AUTO_UPDATE_DATA=true
|