fix(deepseek): ensure reasoning_content placeholder for R1 tool calls

- Added aliases 'reasoning' and 'thought' to reasoning_content field for better client compatibility.
- Implemented automatic 'Thinking...' placeholder injection for deepseek-reasoner history messages that contain tool_calls but lack reasoning_content.
- Restored strict parameter sanitation for deepseek-reasoner.

src/models/mod.rs

@@ -38,7 +38,7 @@ pub struct ChatMessage {
     pub role: String, // "system", "user", "assistant", "tool"
     #[serde(flatten)]
     pub content: MessageContent,
-    #[serde(skip_serializing_if = "Option::is_none")]
+    #[serde(alias = "reasoning", alias = "thought", skip_serializing_if = "Option::is_none")]
     pub reasoning_content: Option<String>,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub tool_calls: Option<Vec<ToolCall>>,
@@ -192,7 +192,7 @@ pub struct ChatStreamChoice {
 pub struct ChatStreamDelta {
     pub role: Option<String>,
     pub content: Option<String>,
-    #[serde(skip_serializing_if = "Option::is_none")]
+    #[serde(alias = "reasoning", alias = "thought", skip_serializing_if = "Option::is_none")]
     pub reasoning_content: Option<String>,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub tool_calls: Option<Vec<ToolCallDelta>>,