You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Upgrade to pymongo 3.2.2 and mongoengine 0.10.6 so StackStorm now also supports and works with
MongoDB 3.x. (improvement)
Make sure policies which are disabled are not applied. (bug fix)
Reported by Brian Martin.
Allow user to specify an action which is performed on an execution (delay, cancel) when a
concurrency policy is used and a defined threshold is reached. For backward compatibility, delay is a default behavior, but now user can also specify cancel and an execution will
be canceled instead of delayed when a threshold is reached.
Update action runner to use two internal green thread pools - one for regular (non-workflow) and
one for workflow actions. Both pool sizes are user-configurable. This should help increase the
throughput of a single action runner when the system is not over-utilized. It can also help
prevent deadlocks which may occur when using delay policies with action-chain workflows.
(improvement)
Update CLI commands to make sure that all of them support --api-key option. (bug-fix)
Add support for sorting execution list results, allowing access to oldest items. (improvement)
Allow administrator to configure maximum limit which can be specified using ?limit
query parameters when making API calls to get all / list endpoints. For backward compatibility
and safety reasons, the default value still is 100. (improvement)
Update st2-register-content script to exit with non-zero on failure (e.g. invalid resource
metadata, etc.) by default. For backward compatibility reasons, --register-fail-on-failure
flag was left there, but it now doesn't do anything since this is the default behavior. For ease
of migrations, users can revert to the old behavior by using new --register-no-fail-on-failure flag. (improvement)
Allow Python runner actions to return execution status (success, failure) by returning a tuple
from the run() method. First item in the tuple is a flag indicating success (True / False) and the second one is the result. Previously, user could only cause action to fail by
throwing an exception or exiting which didn't allow for a result to be returned. With this new
approach, user can now also return an optional result with a failure. (new feature)
Include a chatops alias sample in examples pack that shows how to use format option to
display chatops messages in custom formatted way. (improvement)
Fix Internal Server Error when an undefined jinja variable is used in action alias ack field.
We now send a http status code 201 but also explicitly say we couldn't render the ack
field. The ack is anyways a nice-to-have message which is not critical. Previously, we still
kicked off the execution but sent out Internal Server Error which might confuse the user
whether execution was kicked off or not. (bug-fix)
Include testing for chatops format_execution_result python action. The tests cover various
action types. (improvement)
Include a field elapsed_seconds in execution API response for GET calls. The clients using
the API can now use elapsed_seconds without having to repeat computation. (improvement)
Update st2-register-content script so it validates new style configs in /opt/stackstorm/configs/ directory when using --register-configs flag if a pack contains
a config schema (config.schema.yaml). (improvement)
Implement custom YAQL function st2kv in Mistral to get key-value pair from StackStorm's
datastore. (new-feature)