Standardized input/output contract for all agents, enabling pluggable composition and benchmarking. - AgentInput/AgentOutput Pydantic schemas (5-tier rating, confidence, targets) - BaseAgent abstract class with analyze(input) -> output contract - AgentRegistry for pluggable agent discovery - Existing analysts refactored to implement BaseAgent - Agent benchmarking: compare outputs across different LLM backends Closes #264 |
||
|---|---|---|
| .. | ||
| base_analysts.py | ||
| fundamentals_analyst.py | ||
| market_analyst.py | ||
| news_analyst.py | ||
| social_media_analyst.py | ||