fix: make model integrity downloads reliable - #49
Merged
Conversation
✅ Deploy Preview for voca-gateway canceled.
|
There was a problem hiding this comment.
Mr-Sunglasses has reached the 50-credit limit for trial accounts. To continue receiving code reviews, upgrade your plan.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Multi-file model installs were not a safe transaction: after one worker failed, cleanup could run while other thread-backed downloads were still writing and recreate a partial model directory. Repository-wide request bursts and silent short responses made the integrity path unnecessarily flaky. Pin harvesting also refreshed unrelated models and could combine a new revision with a stale checksum.
Summary
Verification
just test— ruff, WPS, mypy, locked package/audit checks, 550 tests, and Compose config passeduv run scripts/verify-model-pins.py— 60 checked, 0 mismatched, 0 skippedwhisper.cpp:ggml-apex-hinglish-q5_0.bin— completed at 574,041,195 bytes with the committed SHA-256 pinuv run scripts/harvest-model-pins.py— 0 missing pinnable models and no pin-file diffPrivacy and security