feat(providers): an OpenAI-compatible preset for any vLLM, LM Studio or gateway URL

Step 8 of the provider refactor plan, a new provider made of one record.
'custom' runs on @ai-sdk/openai-compatible with <think> extraction, merges
system messages (open-source chat templates reject several), has no default
URL (so a key alone does not count as connected, and the chat endpoint is
shown under the URL field) and lists models from its /models. Server side:
CUSTOM_API_KEY and CUSTOM_BASE_URL, ADMIN_CUSTOM_* in the admin panel.
env.example and the three provider docs gained a section; the picker count
in the e2e test is 25 and a new e2e test walks through the preset. The
behavior snapshot gained the new provider's 146 rows; its two 'No AI provider
configured' rows list CUSTOM_API_KEY now.

env.example

@@ -1,6 +1,6 @@
 # AI Provider Configuration
 # AI_PROVIDER: Which provider to use
-# Options: bedrock, openai, anthropic, google, vertexai, azure, ollama, openrouter, aihubmix, deepseek, siliconflow, sglang, gateway, edgeone, doubao, modelscope, glm, qwen, qiniu, kimi, minimax, novita, mimo, atlascloud
+# Options: bedrock, openai, anthropic, google, vertexai, azure, ollama, openrouter, aihubmix, deepseek, siliconflow, sglang, gateway, edgeone, doubao, modelscope, glm, qwen, qiniu, kimi, minimax, novita, mimo, atlascloud, custom
 # Default: bedrock
 AI_PROVIDER=bedrock
 
@@ -94,6 +94,10 @@ AI_MODEL=global.anthropic.claude-sonnet-4-5-20250929-v1:0
 # SGLANG_API_KEY=your-sglang-api-key
 # SGLANG_BASE_URL=http://127.0.0.1:8000/v1  # Your SGLang endpoint
 
+# Any other OpenAI-compatible API (vLLM, LM Studio, LiteLLM, a gateway)
+# CUSTOM_API_KEY=your-api-key                # Any non-empty value if the server ignores keys
+# CUSTOM_BASE_URL=http://127.0.0.1:8000/v1   # Required: the API's base URL
+
 # ModelScope Configuration
 # MODELSCOPE_API_KEY=ms-...
 # MODELSCOPE_BASE_URL=https://api-inference.modelscope.cn/v1  # Optional: Custom endpoint