chore: capture the stuck context probe and draft the pre-emption intent - #143
Merged
Merged
Conversation
Live server 2026-09-21, six hours of 503s: the context probe queued an image-to-text model mlx_lm cannot load (Model type glm_ocr not supported), waited the ten-minute readiness timeout, marked it load_failed, re-queued it and retried 32 times, each attempt holding the loading model charged at the whole budget so no client request fit. Three issues and one draft intent (a real request pre-empts idle work). Assisted-by: Claude Opus 5 (claude-opus-5)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Records only. iss-2609211334563318 (probe measures non-chat models, major), iss-2609211334570516 (a load that cannot succeed is retried by idle work for hours, holding the budget, major), iss-2609211334576018 (the 503 names no holder, minor); draft itd-2609211335097114 (a stuck model never holds the server hostage). Evidence: the live box logs of 2026-09-21, kept locally.
Assisted-by: Claude Opus 5 (claude-opus-5)