feat: portfolio re-evaluation GitHub Action + structured LLM timeout

feat: increase max_tokens to 65536 + add project showcase HTML page

fix: Kelly per-verdict caps, more noise words, higher token limit, Pydantic warning

fix: bump structured output token limit to 8192 + add noise words

feat: Sprint 9 — Execution & Quality Control

feat: integrate LangSmith observability (Sprint 8 Epic 1)

fix: add LLM model fallback chain to prevent 429 rate-limit failures

feat: major architecture refactor with yFinance screener, scoring, and insider feeds

chore: default LLM to gemma-3-27b for superior comprehension and stability

chore: default LLM to llama-3.1-8b after performance evaluation

fix: swap OpenRouter LLM to Llama-3.1-8B to prevent connection timeouts during extraction

update model to solar-pro-3:free (expires march 23)

update agent with new routing, chart generation, and zombie filter

Fix: Add debugging to find the missing API Key

Fix: Add debugging to find the missing API Key

Initial Deploy (Clean)