feat: add multi-provider LLM support with thinking configurations

Models added:
- OpenAI: GPT-5.2, GPT-5.1, GPT-5, GPT-5 Mini, GPT-5 Nano, GPT-4.1
- Anthropic: Claude Opus 4.5/4.1, Claude Sonnet 4.5/4, Claude Haiku 4.5
- Google: Gemini 3 Pro/Flash, Gemini 2.5 Flash/Flash Lite
- xAI: Grok 4, Grok 4.1 Fast (Reasoning/Non-Reasoning)

Configs updated:
- Add unified thinking_level for Gemini (maps to thinking_level for Gemini 3,
  thinking_budget for Gemini 2.5; handles Pro's lack of "minimal" support)
- Add OpenAI reasoning_effort configuration
- Add NormalizedChatGoogleGenerativeAI for consistent response handling

Fixes:
- Fix Bull/Bear researcher display truncation
- Replace ChromaDB with BM25 for memory retrieval

pyproject.toml

@@ -8,7 +8,6 @@ dependencies = [
     "akshare>=1.16.98",
     "backtrader>=1.9.78.123",
     "chainlit>=2.5.5",
-    "chromadb>=1.0.12",
     "eodhd>=1.0.32",
     "feedparser>=6.0.11",
     "finnhub-python>=2.4.23",
@@ -23,6 +22,7 @@ dependencies = [
     "praw>=7.8.1",
     "pytz>=2025.2",
     "questionary>=2.1.0",
+    "rank-bm25>=0.2.2",
     "redis>=6.2.0",
     "requests>=2.32.4",
     "rich>=14.0.0",