diff --git a/docs/providers/anthropic.md b/docs/providers/anthropic.md
index 8222b9c03b2..de974315273 100644
--- a/docs/providers/anthropic.md
+++ b/docs/providers/anthropic.md
@@ -41,8 +41,8 @@ openclaw onboard --anthropic-api-key "$ANTHROPIC_API_KEY"
 - You can override per-message (`/think:<level>`) or in model params:
   `agents.defaults.models["anthropic/<model>"].params.thinking`.
 - Related Anthropic docs:
-  - https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking
-  - https://platform.claude.com/docs/en/build-with-claude/extended-thinking
+  - [Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/adaptive-thinking)
+  - [Extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking)
 
 ## Prompt caching (Anthropic API)
 
diff --git a/docs/providers/openai.md b/docs/providers/openai.md
index 70b1c469078..c77d954c96f 100644
--- a/docs/providers/openai.md
+++ b/docs/providers/openai.md
@@ -73,8 +73,8 @@ default (`openaiWsWarmup: true`) when WebSocket transport is used.
 
 Related OpenAI docs:
 
-- Realtime API with WebSocket: https://platform.openai.com/docs/guides/realtime-websocket
-- Streaming API responses (SSE): https://platform.openai.com/docs/guides/streaming-responses
+- [Realtime API with WebSocket](https://platform.openai.com/docs/guides/realtime-websocket)
+- [Streaming API responses (SSE)](https://platform.openai.com/docs/guides/streaming-responses)
 
 ```json5
 {