Fix Dola SSE parsing: use for-await stream, handle STREAM_MSG_NOTIFY + STREAM_CHUNK + SSE_REPLY_END events

Add Dola provider (dola-fast / dola-pro) with reverse-engineered chat/completion endpoint

Add fast/thinking mode variants for all Qwen models + meta module

Update Exocore Gateway

Revert ANTHRO_MODEL_MAP and kimi.json to original

Add NVIDIA Kimi K2.6 API for Claude Code tool support

Add Claude integration via Puter driver API

Include data/ in repo and Dockerfile for configs/cookies