Skip to content

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

Rust

fix: preserve DeepSeek V4 thinking history

bellman54d785d0c0b9
diff --git a/rust/crates/api/src/providers/openai_compat.rs b/rust/crates/api/src/providers/openai_compat.rs
index d5291b8e..43c8a4b2 100644
--- a/rust/crates/api/src/providers/openai_compat.rs
+++ b/rust/crates/api/src/providers/openai_compat.rs
@@ -1115,6 +1115,13 @@ fn build_chat_completion_request_for_base_url(
payload[key] = value.clone();
}
+ // DeepSeek V4 Pro/Flash thinking mode requires this provider-specific opt-in
+ // and also requires assistant reasoning history to be echoed as `reasoning_content`.
+ // Apply it after extra_body so callers cannot accidentally override the required shape.
+ if model_requires_reasoning_content_in_history(wire_model) {
+ payload["thinking"] = json!({"type": "enabled"});
+ }
+
payload
}
@@ -1172,16 +1179,19 @@ pub fn translate_message(message: &InputMessage, model: &str) -> Vec<Value> {
InputContentBlock::ToolResult { .. } => {}
}
}
- let include_reasoning =
- model_requires_reasoning_content_in_history(model) && !reasoning.is_empty();
- if text.is_empty() && tool_calls.is_empty() && !include_reasoning {
+ let needs_reasoning = model_requires_reasoning_content_in_history(model);
+ if text.is_empty() && tool_calls.is_empty() && reasoning.is_empty() {
Vec::new()
} else {
let mut msg = serde_json::json!({
"role": "assistant",
- "content": (!text.is_empty()).then_some(text),
});
- if include_reasoning {
+ if !text.is_empty() {
+ msg["content"] = json!(text);
+ } else if !needs_reasoning {
+ msg["content"] = Value::Null;
+ }
+ if needs_reasoning {
msg["reasoning_content"] = json!(reasoning);
}
// Only include tool_calls when non-empty: some providers reject
@@ -1796,6 +1806,31 @@ mod tests {
assert_eq!(assistant["content"], json!("answer"));
}
+ #[test]
+ fn deepseek_v4_assistant_with_only_tool_calls_omits_content_and_includes_reasoning() {
+ let request = MessageRequest {
+ model: "deepseek-v4-pro".to_string(),
+ max_tokens: 100,
+ messages: vec![InputMessage {
+ role: "assistant".to_string(),
+ content: vec![InputContentBlock::ToolUse {
+ id: "call_1".to_string(),
+ name: "get_weather".to_string(),
+ input: json!({"city": "Paris"}),
+ }],
+ }],
+ stream: false,
+ ..Default::default()
+ };
+
+ let payload = build_chat_completion_request(&request, OpenAiCompatConfig::openai());
+ let assistant = &payload["messages"][0];
+
+ assert!(assistant.get("content").is_none());
+ assert_eq!(assistant["reasoning_content"], json!(""));
+ assert_eq!(assistant["tool_calls"].as_array().map(Vec::len), Some(1));
+ }
+
#[test]
fn deepseek_v4_flash_request_includes_reasoning_content_for_assistant_history() {
// Given an assistant history turn containing thinking.
@@ -1982,6 +2017,49 @@ mod tests {
assert_eq!(payload["reasoning_effort"], json!("high"));
}
+ #[test]
+ fn deepseek_v4_request_includes_thinking_parameter() {
+ let payload = build_chat_completion_request(
+ &MessageRequest {
+ model: "deepseek-v4-pro".to_string(),
+ max_tokens: 1024,
+ messages: vec![InputMessage::user_text("hello")],
+ ..Default::default()
+ },
+ OpenAiCompatConfig::openai(),
+ );
+ assert_eq!(payload["thinking"], json!({"type": "enabled"}));
+ assert_eq!(payload["model"], json!("deepseek-v4-pro"));
+
+ let mut extra_body = BTreeMap::new();
+ extra_body.insert("thinking".to_string(), json!({"type": "disabled"}));
+ let payload_with_override = build_chat_completion_request(
+ &MessageRequest {
+ model: "openai/deepseek-v4-flash".to_string(),
+ max_tokens: 1024,
+ messages: vec![InputMessage::user_text("hello")],
+ extra_body,
+ ..Default::default()
+ },
+ OpenAiCompatConfig::openai(),
+ );
+ assert_eq!(
+ payload_with_override["thinking"],
+ json!({"type": "enabled"})
+ );
+
+ let non_deepseek_payload = build_chat_completion_request(
+ &MessageRequest {
+ model: "gpt-4o".to_string(),
+ max_tokens: 64,
+ messages: vec![InputMessage::user_text("hello")],
+ ..Default::default()
+ },
+ OpenAiCompatConfig::openai(),
+ );
+ assert!(non_deepseek_payload.get("thinking").is_none());
+ }
+
#[test]
fn reasoning_effort_omitted_when_not_set() {
let payload = build_chat_completion_request(
diff --git a/rust/crates/api/tests/openai_compat_integration.rs b/rust/crates/api/tests/openai_compat_integration.rs
index d8744675..980f0063 100644
--- a/rust/crates/api/tests/openai_compat_integration.rs
+++ b/rust/crates/api/tests/openai_compat_integration.rs
@@ -159,6 +159,11 @@ async fn send_message_preserves_deepseek_reasoning_content_before_text() {
},
]
);
+
+ let captured = state.lock().await;
+ let request = captured.first().expect("server should capture request");
+ let body: serde_json::Value = serde_json::from_str(&request.body).expect("json body");
+ assert_eq!(body["thinking"], json!({"type": "enabled"}));
}
#[tokio::test]