Change OpenRouter model to Gemma 3n E4B IT

Fix OpenRouter model: use deepseek-chat-v3 (was invalid model)

Rotate between LLM providers instead of consecutive retries

Increase LLM retry delays and add fallback delay for all errors

Update default models: Gemini stable + OpenRouter GPT fallback

Add 10s delay between provider fallbacks after rate limit (429)

Increase exponential backoff from 3s to 5s base

Fix: Increase rate limit delays and fix revision detection

Fix: Add rate limit handling with retry and delays

Rename financials to fundamentals for schema consistency

Initial commit: Instant SWOT Agent