Skip to content

Retry eval tasks if API instability detected #9365

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
cte merged 1 commit into from
Nov 18, 2025
Merged

Retry eval tasks if API instability detected #9365

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 16 additions & 0 deletions packages/evals/src/cli/runTask.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -217,11 +217,23 @@ export const runTask = async ({ run, task, publish, logger }: RunTaskOptions) =>
"diff_error",
"condense_context",
"condense_context_error",
"api_req_retry_delayed",
"api_req_retried",
]

let isApiUnstable = false

client.on(IpcMessageType.TaskEvent, async (taskEvent) => {
const { eventName, payload } = taskEvent

if (
eventName === RooCodeEventName.Message &&
payload[0].message.say &&
["api_req_retry_delayed", "api_req_retried"].includes(payload[0].message.say)
) {
isApiUnstable = true
}

// Publish all events except for these to Redis.
if (!ignoreEvents.broadcast.includes(eventName)) {
await publish({ ...taskEvent, taskId: task.id })
Expand Down Expand Up @@ -388,4 +400,8 @@ export const runTask = async ({ run, task, publish, logger }: RunTaskOptions) =>
}

logger.close()

if (isApiUnstable) {
throw new Error("API is unstable, throwing to trigger a retry.")
Copy link
Contributor

@roomote roomote bot Nov 18, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

User-aborted tasks should not trigger retries. If a task is aborted (likely user-initiated at line 303-305), the retry will be triggered anyway when API instability is detected. Consider checking taskAbortedAt to prevent retrying intentionally cancelled tasks.

Fix it with Roo Code or mention @roomote and request a fix.

}
}
Loading