npuContextWindowNote function
What an NPU engine says, once, when the context window its executor runs
with (window, read after the first turn) is not the maxTokens it was
asked for; null when they agree. An NPU bundle has one compiled KV cache,
and LiteRT-LM lowers max_num_tokens to the bundle's metadata (or, without
it, to the cache). When the metadata is above the cache (upstream #4184)
the window read here is the metadata's, and a context past the cache fails
natively; this note cannot see that case.
Implementation
@visibleForTesting
String? npuContextWindowNote({required int asked, required int window}) =>
window == asked
? null
: '[litertlm_dart] this NPU bundle runs with a context window '
'of $window tokens, not the maxTokens $asked asked for: it is '
'compiled for one KV cache size. Shown once per engine.';