Skip to content

feat(generator): add opt-in exploration recovery #1984

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
SchrodingersCattt wants to merge 2 commits into
base: master
Choose a base branch
from
Open

feat(generator): add opt-in exploration recovery #1984

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f067498
feat(generator): add opt-in exploration recovery
SchrodingersCattt Oct 2, 2026
bfbf228
fix(generator): harden exploration recovery
SchrodingersCattt Oct 10, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 21 additions & 0 deletions dpgen/generator/arginfo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -410,6 +410,14 @@ def model_devi_lmp_args() -> list[Argument]:
doc_model_devi_perc_candi_f = "See model_devi_adapt_trust_lo."
doc_model_devi_perc_candi_v = "See model_devi_adapt_trust_lo."
doc_model_devi_f_avg_relative = "Normalized the force model deviations by the RMS force magnitude along the trajectory. This key should not be used with use_relative."
doc_model_devi_recovery = (
"Opt-in recovery for failed exploration tasks. Set enabled=true to "
"validate task outputs. To salvage prefix frames from failed tasks, also "
"set salvage_prefix=true and choose nonzero max_failed_tasks and "
"max_failed_ratio budgets. Recovery requires a DPDispatcher build with "
"the failed-result policy API (continue_on_failure, raise_on_failure, "
"and include_failed_results)."
)
Comment thread
coderabbitai[bot] marked this conversation as resolved.
doc_model_devi_clean_traj = "If type of model_devi_clean_traj is bool type then it denote whether to clean traj folders in MD since they are too large. If it is Int type, then the most recent n iterations of traj folders will be retained, others will be removed."
doc_model_devi_merge_traj = "If model_devi_merge_traj is set as True, only all.lammpstrj will be generated, instead of lots of small traj files."
doc_model_devi_nopbc = "Assume open boundary condition in MD simulations."
Expand Down Expand Up @@ -498,6 +506,19 @@ def model_devi_lmp_args() -> list[Argument]:
optional=True,
doc=doc_model_devi_f_avg_relative,
),
Argument(
"model_devi_recovery",
Comment thread
coderabbitai[bot] marked this conversation as resolved.
dict,
optional=True,
default={
"enabled": False,
"max_failed_tasks": 0,
"max_failed_ratio": 0.0,
"salvage_prefix": False,
"min_valid_frames": 1,
},
doc=doc_model_devi_recovery,
),
Argument(
"model_devi_clean_traj",
[bool, int],
Expand Down
Loading
Loading