When ttl is not specificed in policy, one gets 500 with {"error":"ttl must be \u003e= 10,000 ms"}
Since ~40 min all my requests with 'executionTimeout': 120000 get this error with HTTP status 500.
here is my repro
curl -v -X POST "https://api.runpod.ai/v1/XXX/run" -H "Authorization: Bearer XXX" -H "Content-Type: application/json" -d '{"input": {"XXX": "XXX"}, "policy": {"executionTimeout": 120000}}'
this used to work previously
also disagrees with https://docs.runpod.io/serverless/endpoints/send-requests#execution-policies ""ttl": int // Time in milliseconds. Must be greater than or equal to 10 seconds. Default is 24 hours. Maximum is one week."
Send a request | RunPod Documentation
Learn how to construct a JSON request body to send to your custom endpoint, including optional inputs for webhooks, execution policies, and S3-compatible storage, to optimize job execution and resource management.
3 Replies
setting ttl in policy explicitly fixed the issue for me
having this same exact issue
broke our production bot 💀
Default is 24 hours. Maximum is one week. didn't get followed I think?someone contacted me privately and said they are fixing the issue
They told me that fix has been deployed.