Exclude Venice provider via OpenRouter extra_body routing

Switch to hermes-3-405b for tool calling; cap arxiv to 5 results with 1 retry

Fix context overflow: truncate content to 3k chars, reduce results; switch to nemotron-120b

Add litellm dep; use openrouter/ prefix with qwen3-8b:free

Use base_url approach with gemma-3-27b-it:free; no LiteLLM prefix stripping

Add OpenRouter model fallback chain (5 free models) to survive rate limits

Fix OpenRouter: remove base_url, let LiteLLM route via openrouter/ prefix

Switch LLM to OpenRouter (gemini-2.0-flash); drop direct Gemini dependency

Fix: switch to Docker SDK, lazy embedder loading, bug fixes

Initial commit