Revert "docs: add Zhipu AI (GLM-4) as a supported LLM provider"

docs: add Zhipu AI (GLM-4) as a supported LLM provider

fix: shorten short_description to meet HF 60-char limit

docs: update README to reflect new features and improved descriptions for HuggingClaw

docs: remind users to update datasets field after duplicating

feat: add datasets YAML metadata to restore linked spaces association

fix: remove tao-shen/HuggingClaw-data refs to prevent unwanted linked spaces

fix: revert to token auth with default "huggingclaw"

feat: default to no-auth mode — Control UI connects instantly

docs: simplify env vars table to top 3 entries

feat: add GATEWAY_TOKEN env var (default: huggingclaw)

remove: drop gateway password/token auth entirely — device auth only

fix: revert auth to password mode, add Telegram API auto-probe, background DNS

feat: derive dataset name from Space repo name to avoid conflicts

feat: auto-derive dataset repo name from HF_TOKEN when AUTO_CREATE_DATASET=true

security: change AUTO_CREATE_DATASET default to false

docs: add detailed env var table with examples, change sync interval to 60s

chore: replace gpt-4o-mini with gpt-5-nano everywhere

docs: update default model example in README to gpt-oss-20b:free

chore: default repo → HuggingClaw-data, default model → DeepSeek V3 (free)

Remove Telegram env vars, clean up README and .env.example

Simplify Why HuggingClaw: two paragraphs, two problems (persistence + DNS)

tags: HuggingFace and HuggingFace dataset (no space)

feat: add AUTO_CREATE_DATASET env var to control dataset auto-creation

feat: restore architecture diagram with Docker/Sync/DNS layout, yellow+red theme

refactor: use PNG banner, simplify architecture to OpenClaw + HF Space + HF Dataset

feat: professional README, .env.example, architecture diagram

feat: switch to password auth + project README

deploy: HuggingClaw with original Dockerfile

initial commit