fix: add Tinker warmup step before integration tests#44
Open
Pratimakumari8 wants to merge 1 commit into
Open
Conversation
The Tinker proxy cold-starts on first inference because the tokenizer downloads on demand (>120s). The existing health check only confirms the API server is up, not that it is ready to serve inference requests. This adds a warmup step that sends a real inference request and retries until it succeeds (timeout 300s) before the OpenClaw gateway check and test run begin.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
The Tinker proxy cold-starts on first inference because the
tokenizer downloads on demand (>120s). The existing health
check only confirms the API server is up, not that it is
ready to serve inference requests.
This caused the E2E integration tests to fail immediately
after startup — the first real inference request would time
out while the tokenizer was still downloading.
Fix
Added a warmup step (step 2b) that sends a real inference
request to the CLaaS API and retries until it succeeds
(timeout 300s) before the OpenClaw gateway check and
test run begin.
Related
Closes #20