docs(env): drop stale LLM-key and provider-admin-token entries from .env.example

Provider credentials now live exclusively in the Model Registry and the
x-evoscientist-admin-token / provider-admin-token mechanism was removed;
no code reads these variables anymore.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

.env.example

@@ -1,42 +1,13 @@
 # EvoScientist — cp .env.example .env && fill in your keys
-
-# LLM provider (pick at least one)
-ANTHROPIC_API_KEY=           # console.anthropic.com
-OPENAI_API_KEY=              # platform.openai.com
-GOOGLE_API_KEY=              # aistudio.google.com/api-keys
-NVIDIA_API_KEY=              # build.nvidia.com
-
-# Direct providers (optional)
-MINIMAX_API_KEY=              # platform.minimaxi.com (China, default) or platform.minimax.io (Global)
-MINIMAX_BASE_URL=             # https://api.minimaxi.com/anthropic (default) or https://api.minimax.io/anthropic
-ZHIPU_API_KEY=                # open.bigmodel.cn (智谱)
-VOLCENGINE_API_KEY=           # volcengine.com (火山引擎)
-DASHSCOPE_API_KEY=            # dashscope.aliyuncs.com (阿里云)
-MOONSHOT_API_KEY=             # platform.moonshot.cn (月之暗面)
-KIMI_API_KEY=                 # kimi.com/code (Kimi 代码计划)
-
-# Aggregator platforms (optional)
-SILICONFLOW_API_KEY=          # siliconflow.cn
-OPENROUTER_API_KEY=           # openrouter.ai
-
-# Custom endpoints (optional)
-CUSTOM_OPENAI_API_KEY=       # OpenAI-compatible endpoint
-CUSTOM_OPENAI_BASE_URL=
-CUSTOM_ANTHROPIC_API_KEY=    # Anthropic-compatible endpoint
-CUSTOM_ANTHROPIC_BASE_URL=
-
-# Local models (optional)
-OLLAMA_BASE_URL=              # http://localhost:11434 (default)
+#
+# LLM providers, models, and API keys are managed exclusively through the
+# Model Registry (WebUI 大模型配置 / Config API); no provider credential is
+# read from environment variables. See
+# docs/unified-model-configuration-architecture.md.
 
 # Web search (optional)
 TAVILY_API_KEY=              # app.tavily.com
 
-# WebUI provider editor. Local processes running as the same OS user share
-# ~/.config/evoscientist/provider-admin-token automatically. For different
-# hosts, users, or containers, set the same random value on both processes.
-# Integrated `EvoSci` WebUI mode also passes a shared token automatically.
-EVOSCIENTIST_PROVIDER_ADMIN_TOKEN=
-
 # WebUI conversation workspace policy. EVOSCIENTIST_WORKSPACE_DIR is the
 # deployment root, not a per-conversation directory. In isolated modes each
 # conversation is stored under <root>/.evoscientist/conversations/<scope-id>/.