Skip to content

Replace enums with strings in the DB, JobSubmission.termination_reason, and Run.termination_reason #2949

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.

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

Merged
merged 5 commits into from
Aug 11, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
20 changes: 12 additions & 8 deletions src/dstack/_internal/core/models/runs.py
Original file line number Diff line number Diff line change
Expand Up @@ -350,15 +350,17 @@ class JobSubmission(CoreModel):
deployment_num: int = 0 # default for compatibility with pre-0.19.14 servers
submitted_at: datetime
last_processed_at: datetime
finished_at: Optional[datetime]
inactivity_secs: Optional[int]
finished_at: Optional[datetime] = None
inactivity_secs: Optional[int] = None
status: JobStatus
status_message: str = "" # default for backward compatibility
termination_reason: Optional[JobTerminationReason]
termination_reason_message: Optional[str]
exit_status: Optional[int]
job_provisioning_data: Optional[JobProvisioningData]
job_runtime_data: Optional[JobRuntimeData]
# termination_reason stores JobTerminationReason.
# str allows adding new enum members without breaking compatibility with old clients.
termination_reason: Optional[str] = None
termination_reason_message: Optional[str] = None
exit_status: Optional[int] = None
job_provisioning_data: Optional[JobProvisioningData] = None
job_runtime_data: Optional[JobRuntimeData] = None
error: Optional[str] = None
probes: list[Probe] = []

Expand Down Expand Up @@ -508,7 +510,9 @@ class Run(CoreModel):
last_processed_at: datetime
status: RunStatus
status_message: str = "" # default for backward compatibility
termination_reason: Optional[RunTerminationReason] = None
# termination_reason stores RunTerminationReason.
# str allows adding new enum members without breaking compatibility with old clients.
termination_reason: Optional[str] = None
run_spec: RunSpec
jobs: List[Job]
latest_job_submission: Optional[JobSubmission] = None
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -455,8 +455,7 @@ async def _wait_for_instance_provisioning_data(job_model: JobModel):

if job_model.instance.status == InstanceStatus.TERMINATED:
job_model.status = JobStatus.TERMINATING
# TODO use WAITING_INSTANCE_LIMIT_EXCEEDED after 0.19.x
job_model.termination_reason = JobTerminationReason.FAILED_TO_START_DUE_TO_NO_CAPACITY
job_model.termination_reason = JobTerminationReason.WAITING_INSTANCE_LIMIT_EXCEEDED
return

job_model.job_provisioning_data = job_model.instance.job_provisioning_data
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -574,7 +574,7 @@ def _should_retry_job(run: Run, job: Job, job_model: JobModel) -> Optional[datet

if (
last_provisioned_submission.termination_reason is not None
and last_provisioned_submission.termination_reason.to_retry_event()
and JobTerminationReason(last_provisioned_submission.termination_reason).to_retry_event()
in job.job_spec.retry.on_events
):
return common.get_current_datetime() - last_provisioned_submission.last_processed_at
Expand Down
Loading
Loading