Optimize Gemini key rotation by switching to key-level cooldowns only and adding GEMINI_PAID_API_KEY to rotation pool

Support new Gemini API key format starting with AQ. prefix

Optimize Gemini key rotation, implement two-tier evaluation, and strict allowlist validator

fix: remove vector_neut and other vector operators from prompts and fallbacks

fix: route sk-ant API keys directly to native Anthropic endpoint and add anthropic package to requirements.txt

fix: resolve 7 critical pipeline issues causing zero alpha submissions

Migrate to event-driven immediate submission, increase daily cap to 20, and rename SP500 to TOPSP500

allow multiple universes in settings and fallback mutations (TOP3000, TOP2000, TOP1000, TOP500, TOP200, SP500)

add settings diversity to LLM prompts and fallback mutations

fix: sanitize scientific notation format (1e-9) to standard decimal floats across generation and DB normalization phases, and update LLM prompts to prevent scientific notation output

Fix variable hallucination: restrict local fallback fields to verified ones, add prompt warnings, normalize variables on startup, and prevent infinite resets on unknown variable errors

Auto-start miner, enable SQLite WAL, implement local smooth countdown, and sort submittable archive by latest first

Implement evolutionary genetic loop, vector operator guardrails, automated orthogonalization, and smart retry backoffs

Implement expression/variable name validation, dynamic few-shot learning prompt injection, and fix pending checks sync bug

Realign submitted statuses, persist batch timer cooldown, and integrate categorized data fields library with Vector unit safeguards

Update fallback chain to use active Gemini model strings (3.1 Flash-Lite, 2.5 Flash, 2.5 Flash-Lite, 3.5 Flash, 2.5 Pro, and 3.1 Pro Preview)

Support multiple Gemini models dynamically and add stable Gemini models to fallback chain

Fix WorldQuant unknown variable 'ni' by mapping to 'income' and resolve AttributeError in simulation results parser

Restore advanced Gemini 3.5 Flash and Gemini 3.1 Pro model identifiers for native API and OpenRouter

Support GEMINI_API_KEY environment secret and correct model identifiers in agent.py

Replace invalid net_income/cash_flow variables with standard ni in DB and generator

Fix WorldQuant BRAIN API simulation payload settings and safe float Retry-After parsing

Fix overnight zero-progress: per-model cooldown, expanded fallback, robust metric parsing, session re-auth, throttle fix

Implement LLM backoff cooldown for rate limits (429) and optimize timeout

Upgrade Gemini models to Gemini 3.5 Flash and Gemini 3.1 Pro Preview

Support native Google Gemini API keys in fallback routing

Initialize Space with QuantForge Miner code and 24/7 integration config