common/parser: add proper reasoning tag prefill reading (#20424)
* Implement proper prefill extraction * Refactor cli parameters, update docs, move reasoning budget sampler part to common/reasoning-budget.cpp * Update tools/server/server-task.cpp * refactor: move grammars to variant, remove grammar_external, handle exception internally * Make code less C++y Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Piotr Wilkin (ilintar)
committed by
GitHub
GitHub
parent
c1258830b2
commit
5e54d51b19
@@ -145,7 +145,7 @@ static void test_example_native(testing & t) {
|
||||
common_reasoning_format reasoning_format;
|
||||
json json_schema;
|
||||
bool parallel_tool_calls;
|
||||
bool thinking_forced_open;
|
||||
std::string generation_prompt;
|
||||
std::string input;
|
||||
|
||||
// Expect
|
||||
@@ -157,14 +157,8 @@ static void test_example_native(testing & t) {
|
||||
auto build_parser = [](const test_case & tc) {
|
||||
return build_chat_peg_parser([&](common_chat_peg_builder & p) {
|
||||
auto reasoning_in_content = (tc.reasoning_format == COMMON_REASONING_FORMAT_NONE);
|
||||
auto reasoning = p.eps();
|
||||
if (tc.thinking_forced_open) {
|
||||
// If thinking is forced open, expect a closing tag
|
||||
reasoning = p.reasoning(p.until("</think>")) + "</think>" + p.space();
|
||||
} else {
|
||||
// Otherwise, optionally accept thinking wrapped in tags
|
||||
reasoning = p.optional("<think>" + p.reasoning(p.until("</think>")) + "</think>" + p.space());
|
||||
}
|
||||
// Always use optional TAG_BASED pattern; generation_prompt is prepended to input
|
||||
auto reasoning = p.optional("<think>" + p.reasoning(p.until("</think>")) + "</think>" + p.space());
|
||||
|
||||
// tool calling parser
|
||||
if (tc.tools.is_array() && !tc.tools.empty()) {
|
||||
@@ -190,78 +184,91 @@ static void test_example_native(testing & t) {
|
||||
|
||||
std::vector<test_case> test_cases = std::vector<test_case>{
|
||||
{
|
||||
/* .name = */ "content with thinking_forced_open = false",
|
||||
/* .name = */ "content with reasoning (no generation_prompt)",
|
||||
/* .tools = */ {},
|
||||
/* .tool_choice = */ COMMON_CHAT_TOOL_CHOICE_NONE,
|
||||
/* .reasoning_format = */ COMMON_REASONING_FORMAT_AUTO,
|
||||
/* .json_schema = */ {},
|
||||
/* .parallel_tool_calls = */ false,
|
||||
/* .thinking_forced_open = */ false,
|
||||
/* .generation_prompt = */ "",
|
||||
/* .input = */ ("<think>The user said hello, I must say hello back</think>\nHello"),
|
||||
/* .expect_reasoning = */ "The user said hello, I must say hello back",
|
||||
/* .expect_content = */ "Hello",
|
||||
/* .expect_tool_calls = */ {},
|
||||
},
|
||||
{
|
||||
/* .name = */ "content with thinking_forced_open = false and no reasoning",
|
||||
/* .name = */ "content without reasoning (no generation_prompt)",
|
||||
/* .tools = */ {},
|
||||
/* .tool_choice = */ COMMON_CHAT_TOOL_CHOICE_NONE,
|
||||
/* .reasoning_format = */ COMMON_REASONING_FORMAT_AUTO,
|
||||
/* .json_schema = */ {},
|
||||
/* .parallel_tool_calls = */ false,
|
||||
/* .thinking_forced_open = */ false,
|
||||
/* .generation_prompt = */ "",
|
||||
/* .input = */ ("Hello"),
|
||||
/* .expect_reasoning = */ "",
|
||||
/* .expect_content = */ "Hello",
|
||||
/* .expect_tool_calls = */ {},
|
||||
},
|
||||
{
|
||||
/* .name = */ "content with thinking_forced_open = false and reasoning_format = none",
|
||||
/* .name = */ "content with reasoning_format = none (tags appear in content)",
|
||||
/* .tools = */ {},
|
||||
/* .tool_choice = */ COMMON_CHAT_TOOL_CHOICE_NONE,
|
||||
/* .reasoning_format = */ COMMON_REASONING_FORMAT_NONE,
|
||||
/* .json_schema = */ {},
|
||||
/* .parallel_tool_calls = */ false,
|
||||
/* .thinking_forced_open = */ true,
|
||||
/* .generation_prompt = */ "",
|
||||
/* .input = */ ("<think>The user said hello, I must say hello back</think>\nHello"),
|
||||
/* .expect_reasoning = */ "",
|
||||
/* .expect_content = */ "<think>The user said hello, I must say hello back</think>\nHello",
|
||||
/* .expect_tool_calls = */ {},
|
||||
},
|
||||
{
|
||||
/* .name = */ "content with thinking_forced_open = true",
|
||||
/* .name = */ "content with reasoning generation_prompt",
|
||||
/* .tools = */ {},
|
||||
/* .tool_choice = */ COMMON_CHAT_TOOL_CHOICE_NONE,
|
||||
/* .reasoning_format = */ COMMON_REASONING_FORMAT_AUTO,
|
||||
/* .json_schema = */ {},
|
||||
/* .parallel_tool_calls = */ false,
|
||||
/* .thinking_forced_open = */ true,
|
||||
/* .generation_prompt = */ "<think>",
|
||||
/* .input = */ ("The user said hello, I must say hello back</think>\nHello"),
|
||||
/* .expect_reasoning = */ "The user said hello, I must say hello back",
|
||||
/* .expect_content = */ "Hello",
|
||||
/* .expect_tool_calls = */ {},
|
||||
},
|
||||
{
|
||||
/* .name = */ "content with thinking_forced_open = true and reasoning_format = none",
|
||||
/* .name = */ "content with reasoning generation_prompt and reasoning_format = none",
|
||||
/* .tools = */ {},
|
||||
/* .tool_choice = */ COMMON_CHAT_TOOL_CHOICE_NONE,
|
||||
/* .reasoning_format = */ COMMON_REASONING_FORMAT_NONE,
|
||||
/* .json_schema = */ {},
|
||||
/* .parallel_tool_calls = */ false,
|
||||
/* .thinking_forced_open = */ true,
|
||||
/* .generation_prompt = */ "",
|
||||
/* .input = */ ("The user said hello, I must say hello back</think>\nHello"),
|
||||
/* .expect_reasoning = */ "",
|
||||
/* .expect_content = */ "The user said hello, I must say hello back</think>\nHello",
|
||||
/* .expect_tool_calls = */ {},
|
||||
},
|
||||
{
|
||||
/* .name = */ "tools with tool_choice = auto and no parallel_tool_calls",
|
||||
/* .name = */ "content with closed reasoning generation_prompt (empty reasoning discarded)",
|
||||
/* .tools = */ {},
|
||||
/* .tool_choice = */ COMMON_CHAT_TOOL_CHOICE_NONE,
|
||||
/* .reasoning_format = */ COMMON_REASONING_FORMAT_AUTO,
|
||||
/* .json_schema = */ {},
|
||||
/* .parallel_tool_calls = */ false,
|
||||
/* .generation_prompt = */ "<think></think>",
|
||||
/* .input = */ ("Hello"),
|
||||
/* .expect_reasoning = */ "",
|
||||
/* .expect_content = */ "Hello",
|
||||
/* .expect_tool_calls = */ {},
|
||||
},
|
||||
{
|
||||
/* .name = */ "tools with reasoning generation_prompt",
|
||||
/* .tools = */ create_tools(),
|
||||
/* .tool_choice = */ COMMON_CHAT_TOOL_CHOICE_AUTO,
|
||||
/* .reasoning_format = */ COMMON_REASONING_FORMAT_AUTO,
|
||||
/* .json_schema = */ {},
|
||||
/* .parallel_tool_calls = */ false,
|
||||
/* .thinking_forced_open = */ true,
|
||||
/* .generation_prompt = */ "<think>",
|
||||
/* .input = */
|
||||
("I must get the weather in New York</think>\n"
|
||||
"<tool_call>["
|
||||
@@ -277,13 +284,13 @@ static void test_example_native(testing & t) {
|
||||
} },
|
||||
},
|
||||
{
|
||||
/* .name = */ "tools with tool_choice = auto and parallel_tool_calls",
|
||||
/* .name = */ "parallel tools with reasoning generation_prompt",
|
||||
/* .tools = */ create_tools(),
|
||||
/* .tool_choice = */ COMMON_CHAT_TOOL_CHOICE_AUTO,
|
||||
/* .reasoning_format = */ COMMON_REASONING_FORMAT_AUTO,
|
||||
/* .json_schema = */ {},
|
||||
/* .parallel_tool_calls = */ true,
|
||||
/* .thinking_forced_open = */ true,
|
||||
/* .generation_prompt = */ "<think>",
|
||||
/* .input = */
|
||||
("I must get the weather in New York and San Francisco and a 3 day forecast of each.</think>\nLet me "
|
||||
"search that for you."
|
||||
@@ -321,7 +328,7 @@ static void test_example_native(testing & t) {
|
||||
} },
|
||||
},
|
||||
{
|
||||
/* .name = */ "response_format with thinking_forced_open = true",
|
||||
/* .name = */ "response_format with reasoning generation_prompt",
|
||||
/* .tools = */ {},
|
||||
/* .tool_choice = */ COMMON_CHAT_TOOL_CHOICE_NONE,
|
||||
/* .reasoning_format = */ COMMON_REASONING_FORMAT_AUTO,
|
||||
@@ -333,7 +340,7 @@ static void test_example_native(testing & t) {
|
||||
{ "due_date", { { "type", "string" } } } } },
|
||||
{ "required", { "invoice_number", "amount", "due_date" } } },
|
||||
/* .parallel_tool_calls = */ false,
|
||||
/* .thinking_forced_open = */ true,
|
||||
/* .generation_prompt = */ "<think>",
|
||||
/* .input = */
|
||||
("I must produce the invoice in the requested format</think>\n"
|
||||
R"({"invoice_number": "INV-2025-001", "amount": 1250.50, "due_date": "2025-12-31"})"),
|
||||
@@ -361,7 +368,8 @@ static void test_example_native(testing & t) {
|
||||
t.log(line);
|
||||
}
|
||||
|
||||
common_peg_parse_context ctx(tc.input);
|
||||
std::string effective_input = tc.generation_prompt + tc.input;
|
||||
common_peg_parse_context ctx(effective_input);
|
||||
auto result = parser.parse(ctx);
|
||||
|
||||
t.assert_true("success", result.success());
|
||||
|
||||
Reference in New Issue
Block a user