Add auto3d models test <engine> health check - #107
Merged
Conversation
Loads an engine and runs one tiny (methane) forward pass to verify it works in the current environment, surfacing the common setup problems up front: a missing torchani for the ANI engines, a failed/blocked aimnet registry download, or a broken custom model file. Exits 0 on success, 3 if a dependency is missing, 5 if the model loads but produces non-finite output. Also fixes the `models info` unknown-engine hint to list the real engine names (ModelFactory.available_models) instead of the upper-cased internal dict keys. Docs + tests included.
isayev
added a commit
that referenced
this pull request
Jul 11, 2026
Add auto3d models test <engine> health check
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Picks up a deferred CLI item from the parity review: a
modelshealth-check command.auto3d models test <engine>loads the engine and runs a single tiny (methane) forward pass, surfacing common environment problems up front instead of mid-run:torchanifor ANI engines → exit 3 (DependencyError)Supports
--gpu/--no-gpuand--gpu-idx. Also fixes themodels infounknown-engine hint to list real engine names (ModelFactory.available_models()) rather than upper-cased internal dict keys.Docs (README,
docs/source/cli.rst, CHANGELOG) and fast CLI tests included (model load mocked). Fast gate: 674 passed; ruff clean onsrc/.Still deferred: wiring
progress.py's liveOptimizationDisplayinto the run loop — that needs a dedicated design for cross-process progress reporting without disturbing the spawn/CUDA isolation, so it's intentionally not in this PR.