Tool calls support from mainline (#723)

* Tool calls support from mainline

* update cmake

* revert api for /completions

* Fix broken thinking process for gpt-oss

* add missing args and fix webui bugs

* add missing args and fix webui bugs2

* Fix reasoning format error

* add usage

* change default post_sampling_probs to true

* add back generated_text

* Remove server endpoints tests

* add log

* Chat fixes

* Remove logs

* webui: revert extra handling of thinking process

---------

Co-authored-by: firecoperana <firecoperana>
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
firecoperana
2025-09-01 00:38:49 -05:00
committed by GitHub
parent 8de297b795
commit d7882c3cf8
87 changed files with 13581 additions and 2224 deletions

View File

@@ -1,13 +1,10 @@
#include "json-partial.h"
#include <json-partial.h>
#include "ggml.h"
#include "log.h"
#include "../ggml/include/ggml.h"
#include "../examples/server/utils.hpp"
#include "json.hpp"
#include <string>
#include <json.hpp>
using json = nlohmann::ordered_json;
enum common_json_stack_element_type {
@@ -129,7 +126,7 @@ bool common_json_parse(
return true;
} catch (const std::exception & ex) {
// No, needs healing.
LOG_VERBOSE("Failed to parse up to error", {{"error", ex.what()}, {"content", std::string(it, temptative_end)}});
LOG("Failed to parse up to error: %s: <<<%s>>>\n", ex.what(), std::string(it, temptative_end).c_str());
}
auto can_parse = [](const std::string & str) {
try {