gahow/xserv
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

style: format Rust workspace

Browse Source
This commit is contained in:
Gahow Wang
2026-06-18 18:11:58 +08:00
parent 013465fc06
commit 531cd3fe08
57 changed files with 4045 additions and 1204 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
crates/xserv-server/src/api.rs
View File

@@ -72,7 +72,10 @@ impl ChatTemplate {
let source = std::fs::read_to_string(&jinja_path)
.unwrap_or_else(|e| panic!("failed to read {}: {e}", jinja_path.display()));
eprintln!("[chat-template] loaded from {}", jinja_path.display());
return Self { source, model_type: model_type.to_string() };
return Self {
source,
model_type: model_type.to_string(),
};
}
// 2. Try tokenizer_config.json → chat_template field
@@ -82,7 +85,10 @@ impl ChatTemplate {
if let Ok(v) = serde_json::from_str::<serde_json::Value>(&data) {
if let Some(ct) = v.get("chat_template").and_then(|v| v.as_str()) {
eprintln!("[chat-template] loaded from tokenizer_config.json");
return Self { source: ct.to_string(), model_type: model_type.to_string() };
return Self {
source: ct.to_string(),
model_type: model_type.to_string(),
};
}
}
}
@@ -90,7 +96,10 @@ impl ChatTemplate {
// 3. No template found — use empty source, will fall back to hardcoded
eprintln!("[chat-template] no Jinja template found, using hardcoded fallback");
Self { source: String::new(), model_type: model_type.to_string() }
Self {
source: String::new(),
model_type: model_type.to_string(),
}
}
pub fn render(&self, messages: &[Message]) -> String {
@@ -206,7 +215,10 @@ fn build_prompt_gpt_oss(messages: &[Message]) -> String {
prompt.push_str("<|start|>system<|message|>");
prompt.push_str("You are ChatGPT, a large language model trained by OpenAI.\n");
prompt.push_str("Knowledge cutoff: 2024-06\n");
prompt.push_str(&format!("Current date: {}\n\n", strftime_now("%Y-%m-%d".to_string())));
prompt.push_str(&format!(
"Current date: {}\n\n",
strftime_now("%Y-%m-%d".to_string())
));
prompt.push_str("Reasoning: low\n\n");
prompt.push_str("# Valid channels: analysis, commentary, final. Channel must be included for every message.");
prompt.push_str("<|end|>");
@@ -334,13 +346,11 @@ async fn chat_non_stream(state: Arc<AppState>, req: ChatRequest) -> Response {
"completion_tokens": completion_token_count,
"total_tokens": prompt_token_count + completion_token_count
}
})).into_response()
}))
.into_response()
}
fn chat_stream(
state: Arc<AppState>,
req: ChatRequest,
) -> Response {
fn chat_stream(state: Arc<AppState>, req: ChatRequest) -> Response {
let id = format!("chatcmpl-{}", Uuid::new_v4());
let model_name = state.model_name.clone();
let created = unix_timestamp();
@@ -356,7 +366,8 @@ fn chat_stream(
if prompt_tokens.len() >= max_seq_len {
return bad_request(format!(
"prompt is {} tokens, exceeds max_seq_len {}",
prompt_tokens.len(), max_seq_len
prompt_tokens.len(),
max_seq_len
));
}
let max_tokens = req.max_tokens.min(max_seq_len - prompt_tokens.len());
@@ -413,7 +424,9 @@ fn chat_stream(
}
});
Sse::new(ReceiverStream::new(sse_rx)).keep_alive(KeepAlive::default()).into_response()
Sse::new(ReceiverStream::new(sse_rx))
.keep_alive(KeepAlive::default())
.into_response()
}
fn validate_request(req: &ChatRequest, model_name: &str) -> Option<Response> {
@@ -436,8 +449,13 @@ fn validate_request(req: &ChatRequest, model_name: &str) -> Option<Response> {
/// prior handler panicked) and returns a clean 503 instead of panicking when the
/// engine thread is gone, so one dead engine doesn't cascade into every request.
fn submit_to_engine(state: &AppState, req: GenerateRequest) -> Result<(), Response> {
let sender = state.engine_sender.lock().unwrap_or_else(|e| e.into_inner());
sender.send(req).map_err(|_| service_unavailable("inference engine is not available"))
let sender = state
.engine_sender
.lock()
.unwrap_or_else(|e| e.into_inner());
sender
.send(req)
.map_err(|_| service_unavailable("inference engine is not available"))
}
fn service_unavailable(message: impl Into<String>) -> Response {