looks like checks are all fine, so do you want to convert to "proper" PR and request reviews?

and you may want to close #955 of which this is now a duplicate

I'm not really sure what the best solution is. A few thoughts:

• I see tags as being defined on the class (not object) level, conceptually I think of them as describing algorithm properties, so I would prefer not to update them dynamically
• In the cases of the above mentioned (composition) algorithms, for the implementation (i.e. input validation of the forecasting horizon), the tag should be set to False, the composite doesn't require the forecasting horizon during fitting, it merely passes it on to the components, which have their own tag and raise an error accordingly if they require the forecasting horizon during fitting
• For documentation, when users may use tags for finding relevant models, setting it to False may be misleading, but conceptually still makes sense, as it refers to the composition algorithm, rather than a particular instance of the composite

Either way, I think this is a separate issue. I created one here: #981.

ok, agreed - let's split off the larger tags discussion, and just do a "safe" refactoring here.
Outstanding changes:

• the _SktimeForecaster removal is not tags related and should be done
• multiplexer tag should be changed to requires fh in fit (see above)

the test examples are now failing - they ran before.
Can you please check what's happening?

I think it's the multiplexer - the tutorial notebook passes the fh too late

I'd suggest:

• don't change the notebook, since Forecasting tutorial rework #972 is currently under review, and the change to notebook will just cause very fiddly merge issues
• instead, change the tag back, and open a new issue that it needs to be changed once Forecasting tutorial rework #972 is merged, together with the notebook

What do you think, @mloning?

@fkiraly Setting requires-fh-in-fit: to True is the cause for the failure of the multiplexer

@fkiraly Setting requires-fh-in-fit: to True is the cause for the failure of the multiplexer

You mean, to False, no? We want to set it back to True according to my suggestion - please confirm?

pinging @ninamiolane

@mloning this I ready for review :)