vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-08-15 03:15:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

chat : add new template for DeepSeek V4 Flash 0731 (#26398)

Browse source 
* common/chat: update DeepSeek V4 templates

Align the DeepSeek V4 templates with the official encoders while keeping parser behavior out of this change.

- Default drop_thinking for DeepSeek V4 history so prior thinking is omitted unless preserve_reasoning is requested or tools are present.
- Add structured output response-format instructions to the V4 templates and pass the schema into template rendering.
- Add a separate Flash 0731 template for the updated high and max reasoning effort mapping.
- Cover reasoning effort, drop_thinking, structured output prompts, preserved reasoning, continuations, and empty tool arguments in template rendering tests.

Official references:
https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash/blob/main/encoding/encoding_dsv4.py
https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731/blob/main/encoding/encoding_dsv4.py

Assisted-by: Codex

* Fix deepseek v4 0731 template selection

* remove unneeded lower normalization

* Fix DSML parser to consume the tool call separator

* address aldehir requests

* address aldehir comment
This commit is contained in:
Thiago Padilha 2026-08-03 19:59:11 -03:00 • committed by GitHub
parent 94bc47f280
commit 0ef6e55edb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 363 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

172
tests/test-chat.cpp
View file

@ -3987,6 +3987,7 @@ static void test_template_output_peg_parsers(bool detailed_debug) {
.expect_tool_calls({
{ "special_function", R"({"arg1": 1})", {} },
})
.expect_reconstruction()
.run();
// Tool call with negative number
@ -4212,6 +4213,7 @@ static void test_template_output_peg_parsers(bool detailed_debug) {
.expect_tool_calls({
{ "special_function", R"({"arg1": 1})", {} },
})
.expect_reconstruction()
.run();
// Tool call with multiple params (mixed types)
@ -4268,6 +4270,24 @@ static void test_template_output_peg_parsers(bool detailed_debug) {
.run();
}
{
// The DSML separator belongs to the tool call block, not assistant content.
auto tst = peg_tester("models/templates/deepseek-ai-DeepSeek-V4-Flash-0731.jinja", detailed_debug);
tst.test(
"\n\n"
"<｜DSML｜tool_calls>\n"
"<｜DSML｜invoke name=\"special_function\">\n"
"<｜DSML｜parameter name=\"arg1\" string=\"false\">1</｜DSML｜parameter>\n"
"</｜DSML｜invoke>\n"
"</｜DSML｜tool_calls>")
.enable_thinking(false)
.reasoning_format(COMMON_REASONING_FORMAT_DEEPSEEK)
.tools({ special_function_tool })
.expect(message_assist_call)
.expect_reconstruction()
.run();
}
// GLM-4.6 tests - format: <tool_call>function_name\n<arg_key>...</arg_key>\n<arg_value>...</arg_value>\n</tool_call>
{
auto tst = peg_tester("models/templates/GLM-4.6.jinja", detailed_debug);
@ -6359,6 +6379,7 @@ static void test_template_generation_prompt() {
std::vector<common_chat_msg> messages;
bool add_generation_prompt = true;
common_chat_continuation continue_final_message = COMMON_CHAT_CONTINUATION_NONE;
bool enable_thinking = true;
};
auto basic = [&]() {
@ -6390,6 +6411,7 @@ static void test_template_generation_prompt() {
inputs.messages = opts.messages;
inputs.add_generation_prompt = opts.add_generation_prompt;
inputs.continue_final_message = opts.continue_final_message;
inputs.enable_thinking = opts.enable_thinking;
auto params = common_chat_templates_apply(tmpls.get(), inputs);
@ -6488,6 +6510,156 @@ static void test_template_generation_prompt() {
check(tmpls, continuation_reasoning(), "<｜Assistant｜><think>I'm");
}
const std::string deepseek_v4_reasoning_effort_max = "Reasoning Effort: Absolute maximum";
const std::string deepseek_v4_flash_0731_reasoning_effort_max = "Reasoning Effort: Beyond maximum";
{
auto tmpls = read_templates("models/templates/deepseek-ai-DeepSeek-V4.jinja");
check(tmpls, basic(), "<｜Assistant｜><think>");
check(tmpls, continuation_content(), "<｜Assistant｜><think>I'm thinking</think>Hello, ");
check(tmpls, continuation_reasoning(), "<｜Assistant｜><think>I'm");
auto continuation_content_no_thinking = continuation_content();
continuation_content_no_thinking.messages = { system_msg, message_user, simple_assist_msg("Hello, ") };
continuation_content_no_thinking.enable_thinking = false;
check(tmpls, continuation_content_no_thinking, "<｜Assistant｜></think>Hello, ");
common_chat_templates_inputs max_inputs;
max_inputs.messages = { system_msg, message_user };
max_inputs.chat_template_kwargs["reasoning_effort"] = R"("max")";
auto max_params = common_chat_templates_apply(tmpls.get(), max_inputs);
assert_contains(max_params.prompt, deepseek_v4_reasoning_effort_max);
auto high_inputs = max_inputs;
high_inputs.chat_template_kwargs["reasoning_effort"] = R"("high")";
auto high_params = common_chat_templates_apply(tmpls.get(), high_inputs);
assert_not_contains(high_params.prompt, deepseek_v4_reasoning_effort_max);
auto low_inputs = max_inputs;
low_inputs.chat_template_kwargs["reasoning_effort"] = R"("low")";
auto low_params = common_chat_templates_apply(tmpls.get(), low_inputs);
assert_not_contains(low_params.prompt, deepseek_v4_reasoning_effort_max);
common_chat_templates_inputs default_effort_inputs;
default_effort_inputs.messages = { system_msg, message_user };
auto default_effort_params = common_chat_templates_apply(tmpls.get(), default_effort_inputs);
assert_not_contains(default_effort_params.prompt, deepseek_v4_reasoning_effort_max);
auto non_thinking_max_inputs = max_inputs;
non_thinking_max_inputs.enable_thinking = false;
auto non_thinking_max_params = common_chat_templates_apply(tmpls.get(), non_thinking_max_inputs);
assert_not_contains(non_thinking_max_params.prompt, deepseek_v4_reasoning_effort_max);
common_chat_templates_inputs response_format_inputs;
response_format_inputs.messages = { system_msg, message_user };
response_format_inputs.tools = { get_time_tool };
response_format_inputs.json_schema =
R"({"type":"object","properties":{"answer":{"type":"string"}}})";
auto response_format_params = common_chat_templates_apply(tmpls.get(), response_format_inputs);
const auto tools_pos = response_format_params.prompt.find("## Tools");
const auto response_format_pos = response_format_params.prompt.find(
"## Response Format:\n\nYou MUST strictly adhere to the following schema to reply:\n");
if (tools_pos == std::string::npos || response_format_pos == std::string::npos || tools_pos > response_format_pos) {
LOG_ERR("Expected response format after tools\nActual: %s\n", response_format_params.prompt.c_str());
common_log_flush(common_log_main());
throw std::runtime_error("Test failed");
}
assert_contains(response_format_params.prompt, R"("answer": {"type": "string"})");
response_format_inputs.json_schema = "{}";
auto json_object_params = common_chat_templates_apply(tmpls.get(), response_format_inputs);
assert_contains(json_object_params.prompt,
"## Response Format:\n\nYou MUST strictly adhere to the following schema to reply:\n{}");
common_chat_msg assistant_history;
assistant_history.role = "assistant";
assistant_history.content = "Previous answer";
assistant_history.reasoning_content = "Previous reasoning";
common_chat_msg user_followup;
user_followup.role = "user";
user_followup.content = "Follow up";
common_chat_templates_inputs default_history_inputs;
default_history_inputs.messages = { message_user, assistant_history, user_followup };
auto default_history_params = common_chat_templates_apply(tmpls.get(), default_history_inputs);
assert_contains(default_history_params.prompt, "<｜Assistant｜></think>Previous answer");
auto drop_thinking_inputs = default_history_inputs;
drop_thinking_inputs.chat_template_kwargs["drop_thinking"] = "false";
auto drop_thinking_params = common_chat_templates_apply(tmpls.get(), drop_thinking_inputs);
assert_contains(drop_thinking_params.prompt, "<｜Assistant｜><think>Previous reasoning</think>Previous answer");
auto preserve_reasoning_inputs = default_history_inputs;
preserve_reasoning_inputs.chat_template_kwargs["preserve_reasoning"] = "true";
auto preserve_reasoning_params = common_chat_templates_apply(tmpls.get(), preserve_reasoning_inputs);
assert_contains(preserve_reasoning_params.prompt, "<｜Assistant｜><think>Previous reasoning</think>Previous answer");
assert_equals(true, common_chat_templates_get_caps(tmpls.get()).at("supports_preserve_reasoning"));
auto no_preserve_reasoning_inputs = default_history_inputs;
no_preserve_reasoning_inputs.chat_template_kwargs["preserve_reasoning"] = "false";
auto no_preserve_reasoning_params = common_chat_templates_apply(tmpls.get(), no_preserve_reasoning_inputs);
assert_contains(no_preserve_reasoning_params.prompt, "<｜Assistant｜></think>Previous answer");
common_chat_msg empty_tool_call = simple_assist_msg("", "", "empty_args", "{}");
common_chat_templates_inputs empty_tool_inputs;
empty_tool_inputs.messages = { message_user, empty_tool_call };
empty_tool_inputs.tools = { empty_args_tool };
auto empty_tool_params = common_chat_templates_apply(tmpls.get(), empty_tool_inputs);
assert_contains(empty_tool_params.prompt,
"<｜DSML｜invoke name=\"empty_args\">\n\n</｜DSML｜invoke>");
}
{
auto tmpls = read_templates("models/templates/deepseek-ai-DeepSeek-V4-Flash-0731.jinja");
check(tmpls, basic(), "<｜Assistant｜><think>");
check(tmpls, continuation_content(), "<｜Assistant｜><think>I'm thinking</think>Hello, ");
check(tmpls, continuation_reasoning(), "<｜Assistant｜><think>I'm");
auto continuation_content_no_thinking = continuation_content();
continuation_content_no_thinking.messages = { system_msg, message_user, simple_assist_msg("Hello, ") };
continuation_content_no_thinking.enable_thinking = false;
check(tmpls, continuation_content_no_thinking, "<｜Assistant｜></think>Hello, ");
common_chat_templates_inputs high_inputs;
high_inputs.messages = { system_msg, message_user };
high_inputs.chat_template_kwargs["reasoning_effort"] = R"("high")";
auto high_params = common_chat_templates_apply(tmpls.get(), high_inputs);
assert_contains(high_params.prompt, deepseek_v4_reasoning_effort_max);
auto max_inputs = high_inputs;
max_inputs.chat_template_kwargs["reasoning_effort"] = R"("max")";
auto max_params = common_chat_templates_apply(tmpls.get(), max_inputs);
assert_contains(max_params.prompt, deepseek_v4_flash_0731_reasoning_effort_max);
auto low_inputs = high_inputs;
low_inputs.chat_template_kwargs["reasoning_effort"] = R"("low")";
auto low_params = common_chat_templates_apply(tmpls.get(), low_inputs);
assert_not_contains(low_params.prompt, deepseek_v4_reasoning_effort_max);
assert_not_contains(low_params.prompt, deepseek_v4_flash_0731_reasoning_effort_max);
common_chat_templates_inputs default_effort_inputs;
default_effort_inputs.messages = { system_msg, message_user };
auto default_effort_params = common_chat_templates_apply(tmpls.get(), default_effort_inputs);
assert_not_contains(default_effort_params.prompt, deepseek_v4_reasoning_effort_max);
assert_not_contains(default_effort_params.prompt, deepseek_v4_flash_0731_reasoning_effort_max);
auto non_thinking_max_inputs = max_inputs;
non_thinking_max_inputs.enable_thinking = false;
auto non_thinking_max_params = common_chat_templates_apply(tmpls.get(), non_thinking_max_inputs);
assert_not_contains(non_thinking_max_params.prompt, deepseek_v4_flash_0731_reasoning_effort_max);
common_chat_templates_inputs response_format_inputs;
response_format_inputs.messages = { system_msg, message_user };
response_format_inputs.tools = { get_time_tool };
response_format_inputs.json_schema =
R"({"type":"object","properties":{"answer":{"type":"string"}}})";
auto response_format_params = common_chat_templates_apply(tmpls.get(), response_format_inputs);
assert_contains(response_format_params.prompt,
"## Response Format:\n\nYou MUST strictly adhere to the following schema to reply:\n");
assert_contains(response_format_params.prompt, R"("answer": {"type": "string"})");
}
{
auto tmpls = read_templates("models/templates/openbmb-MiniCPM5-1B.jinja");
check(tmpls, basic(), "<|im_start|>assistant\n<think>\n");