feat(health): report idle-suspended embedder as IDLE, not DEGRADED#10
Merged
couragehong merged 1 commit intoJun 2, 2026
Merged
Conversation
The idle ticker stops llama-server after RUNED_IDLE_TIMEOUT to free model memory; the next Embed RPC resurrects it. Health previously mapped any down backend to STATUS_DEGRADED, so a status check looked broken during a normal idle-suspend instead of signalling a benign, self-healing pause. - proto: add HealthResponse STATUS_IDLE - backend: track why the child is down (idle-suspend via Stop vs crash or failed restart) and expose Serving(); only the idle ticker's Stop() yields IDLE, while a crash or a failed (re)start stays DEGRADED - server: Health maps Serving() -> IDLE/DEGRADED/OK, with an IDLE message - test: mapping + real-lifecycle coverage for the new states Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
esifea
approved these changes
Jun 2, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The idle ticker stops llama-server after RUNED_IDLE_TIMEOUT to free model memory; the next Embed RPC resurrects it. Health previously mapped any down backend to STATUS_DEGRADED, so a status check looked broken during a normal idle-suspend instead of signalling a benign, self-healing pause.