feat(mcp): add context length guard to prevent oversized requests

* feat: add X-Client-ID header for claw402 monitoring

* feat(mcp): add context length guard to prevent oversized requests

- Add MaxContext field to Config (default 0 = no limit)
- Add WithMaxContext() option for setting model context limits
- Add context_guard.go: token estimation + message truncation
- Integrate guard into both BuildMCPRequestBody and BuildRequestBodyFromRequest
- Support both map[string]string and map[string]any message formats
- Truncates oldest non-system messages when estimated tokens exceed limit
- Always preserves system messages and keeps at least 1 non-system message
- Logs warning when truncation occurs for debugging

Usage: mcp.NewDeepSeekClient(mcp.WithMaxContext(131072))

mcp/options.go

@@ -86,6 +86,19 @@ func WithMaxTokens(maxTokens int) ClientOption {
 	}
 }
 
+// WithMaxContext sets the model's max context window in tokens.
+// When set (> 0), the client will automatically truncate oldest non-system
+// messages if the estimated token count exceeds this limit.
+//
+// Usage example:
+//
+//	client := mcp.NewClient(mcp.WithMaxContext(131072)) // DeepSeek 128K
+func WithMaxContext(maxContext int) ClientOption {
+	return func(c *Config) {
+		c.MaxContext = maxContext
+	}
+}
+
 // WithTemperature sets temperature parameter
 //
 // Usage example: