common : delegate assistant continuation to underlying template handlers (#23089)

* common : delegate assistant continuation to template handler

* server : implement echo parameter to exclude assistant prefill in the response

* server : fix tests for prefill

* server : use existing llama template

* cont : clean up
This commit is contained in:
Aldehir Rojas 2026-05-17 07:36:05 -04:00 committed by GitHub
parent a6d6183dbc
commit 39cf5d6191
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 1112 additions and 191 deletions

View file

@ -785,7 +785,7 @@ common_peg_parser common_chat_peg_builder::prefix(const std::string & s, const s
if (delimiter.empty()) {
return literal(s);
}
return literal(s.substr(0, s.rfind(delimiter)));
return literal(s.substr(0, s.find(delimiter)));
}
common_peg_parser common_chat_peg_builder::optspace(const std::string & tag) {