2 Commits

Author	SHA1	Message	Date
dtarkent2-sys	8c48c3cffd	WIP: local TradingAgents customizations through 2026-04-13 ... Bulk commit of accumulated local changes on the dtarkent2-sys fork. Spans agents, dataflows, llm_clients, graph orchestration, CLI, and docs. Primary work areas: - llm_clients/ — multi-LLM client layer (anthropic, google, openai, factory, base, validators) for swappable provider support - dataflows/alpaca_data.py — Alpaca integration alongside existing alpha_vantage and y_finance flows - agents/structured/ — portfolio, scoring, and tier1/2/3 layers - agents/analysts, researchers, risk_mgmt — local prompt and logic customizations - graph/ — orchestration tweaks (parallel_analysts, propagation, reflection, signal_processing, trading_graph) - alembic scaffolding inherited from prior commit - chainlit web UI design notes in docs/plans/ This is a single WIP snapshot to preserve work before any upstream merge. History can be cleaned up with interactive rebase later. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-13 22:01:00 -04:00
dtarkent2-sys	7ad9e1d1ce	feat: rebuild as structured Pydantic equity ranking engine ... Replace generic LLM debate system with a tiered, macro-aware equity ranking pipeline where every agent returns Pydantic structured output and scoring is deterministic Python — no prose drives downstream decisions. Architecture: Validation → Tier 1 (Macro+Liquidity parallel) → Tier 2 (8 agents parallel) → Scoring (Archetype+MasterScore) → Tier 3 (Bull/Bear debate + Risk + FinalDecision) → END Master Score: 25% business_quality + 20% macro + 15% institutional_flow + 10% valuation + 10% entry_timing + 10% earnings_revisions + 5% backlog + 5% crowding. Hard veto gates, confidence penalties, position role assignment all computed deterministically. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>	2026-03-09 21:30:46 +00:00