Document chain_number kwarg

Author: penelopeysm

docs/src/api.md

@@ -71,8 +71,9 @@ Common keyword arguments for regular and parallel sampling are:
 - `progress` (default: `AbstractMCMC.PROGRESS[]` which is `true` initially): toggles progress logging. See the section on [Progress logging](#progress-logging) below for more details.
 - `chain_type` (default: `Any`): determines the type of the returned chain
 - `callback` (default: `nothing`): if `callback !== nothing`, then
-  `callback(rng, model, sampler, sample, iteration)` is called after every sampling step,
+  `callback(rng, model, sampler, sample, iteration; kwargs...)` is called after every sampling step,
   where `sample` is the most recent sample of the Markov chain and `iteration` is the current iteration
+   - Keyword arguments `kwargs...` are passed down from the call to `sample(...)`. If you are performing multiple-chain sampling, then `kwargs` _additionally_ contains a `chain_number` keyword argument, which runs from 1 to the number of chains. This is not present when performing single-chain sampling.
 - `num_warmup` (default: `0`): number of "warm-up" steps to take before the first "regular" step, 
    i.e. number of times to call [`AbstractMCMC.step_warmup`](@ref) before the first call to 
    [`AbstractMCMC.step`](@ref).