GeneralBots/botserver
2
1
Fork 0
Code Issues Pull requests Projects Releases 323 Packages Wiki Activity Actions

feat: handle 429 rate limit in OpenAI non-stream generate
All checks were successful
BotServer CI / build (push) Successful in 11m7s
Details

Browse source
This commit is contained in:
Rodrigo Rodriguez (Pragmatismo) 2026-03-10 15:26:10 -03:00
parent f34d401c2e
commit 786d404938
1 changed files with 6 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
src/llm/mod.rs
View file

@ -303,6 +303,12 @@ impl LLMProvider for OpenAIClient {
let status = response.status(); let status = response.status();
if status != reqwest::StatusCode::OK { if status != reqwest::StatusCode::OK {
let error_text = response.text().await.unwrap_or_default(); let error_text = response.text().await.unwrap_or_default();
// Handle 429 rate limit with user-friendly message
if status == reqwest::StatusCode::TOO_MANY_REQUESTS {
return Ok("Server is busy, please try again in a few seconds...".to_string());
}
error!("LLM generate error: {}", error_text); error!("LLM generate error: {}", error_text);
return Err(format!("LLM request failed with status: {}", status).into()); return Err(format!("LLM request failed with status: {}", status).into());
} }