thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

common : add commentary rules for gpt-oss-20b (#21286)

Browse source
This commit is contained in:
Aldehir Rojas 2026-04-02 08:59:59 -05:00 • committed by GitHub
parent e15efe007d
commit 223373742b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 124 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

15
common/chat.cpp
View file

@ -980,15 +980,19 @@ static common_chat_params common_chat_params_init_gpt_oss(const common_chat_temp
auto channel = p.literal("<|channel|>") + (p.literal("commentary") | p.literal("analysis"));
auto constrain_type = p.chars("[A-Za-z0-9_-]", 1, -1);
// Occasionally, gpt-oss-20b will prefix channels with this commentary
auto stray_commentary = p.optional(p.literal("<|channel|>commentary") + p.optional(p.literal(" to=assistant")));
auto start_analysis = stray_commentary + p.literal("<|channel|>analysis<|message|>");
if (extract_reasoning) {
p.rule("analysis", p.literal("<|channel|>analysis<|message|>") + p.reasoning(content) + end);
p.rule("analysis", start_analysis + p.reasoning(content) + end);
} else {
p.rule("analysis", p.content(p.literal("<|channel|>analysis<|message|>") + content + end));
p.rule("analysis", p.content(start_analysis + content + end));
}
auto analysis = p.ref("analysis");
auto preamble = p.rule("preamble", p.literal("<|channel|>commentary<|message|>") + p.content(content) + end);
auto final_msg = p.rule("final", p.literal("<|channel|>final<|message|>") + p.content(content));
auto final_msg = p.rule("final", stray_commentary + p.literal("<|channel|>final<|message|>") + p.content(content));
// Consume any unsolicited tool calls, e.g. builtin functions
auto unsolicited = p.rule("unsolicited", p.atomic(p.optional(channel) + p.literal(" to=") + content + end));
@ -996,7 +1000,7 @@ static common_chat_params common_chat_params_init_gpt_oss(const common_chat_temp
auto any = p.rule("any", preamble | analysis);
if (has_response_format) {
auto constraint = p.optional(p.space() + p.literal("<|constrain|>") + constrain_type);
auto constraint = p.optional(p.space() + p.optional(p.literal("<|constrain|>")) + constrain_type);
auto response_format = p.rule("response-format",
p.literal("<|channel|>final") + constraint + p.literal("<|message|>") +
p.content(p.schema(p.json(), "response-format-schema", inputs.json_schema)));
@ -1013,7 +1017,7 @@ static common_chat_params common_chat_params_init_gpt_oss(const common_chat_temp
const auto & params = function.at("parameters");
auto func_name = p.literal(" to=functions.") + p.tool_name(p.literal(name));
auto constraint = p.optional(p.space() + p.literal("<|constrain|>") + constrain_type);
auto constraint = p.optional(p.space() + p.optional(p.literal("<|constrain|>")) + constrain_type);
auto args = p.tool_args(p.schema(p.json(), "tool-" + name + "-schema", params));
// recipient in role header
@ -1054,6 +1058,7 @@ static common_chat_params common_chat_params_init_gpt_oss(const common_chat_temp
data.grammar_triggers = {
{ COMMON_GRAMMAR_TRIGGER_TYPE_PATTERN, "^\\s+to$" },
{ COMMON_GRAMMAR_TRIGGER_TYPE_PATTERN, "^<\\|channel\\|>(?:commentary|analysis)\\s+to=functions$" },
{ COMMON_GRAMMAR_TRIGGER_TYPE_PATTERN, "<\\|start\\|>assistant(\\s+to)" },
{ COMMON_GRAMMAR_TRIGGER_TYPE_PATTERN, "<\\|start\\|>assistant(<\\|channel\\|>(?:commentary|analysis)\\s+to)" }
};