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

Autoparser - complete refactoring of parser architecture (#18675)

Browse source 
* Autoparser - full single commit squish

* Final pre-merge changes: minor fixes, Kimi 2.5 model parser
This commit is contained in:
Piotr Wilkin (ilintar) 2026-03-06 21:01:00 +01:00 • committed by GitHub
parent 34df42f7be
commit 566059a26b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
63 changed files with 12967 additions and 10071 deletions
Download patch file Download diff file Expand all files Collapse all files

70
tools/server/server-task.cpp
View file

@ -1,12 +1,12 @@
#include "server-common.h"
#include "server-task.h"
#include "common.h"
#include "llama.h"
#include "chat.h"
#include "common.h"
#include "json-schema-to-grammar.h"
#include "llama.h"
#include "sampling.h"
#include "speculative.h"
#include "json-schema-to-grammar.h"
#include "server-common.h"
using json = nlohmann::ordered_json;
@ -157,7 +157,8 @@ json task_params::to_json(bool only_metrics) const {
common_chat_msg task_result_state::update_chat_msg(
const std::string & text_added,
bool is_partial,
std::vector<common_chat_msg_diff> & diffs) {
std::vector<common_chat_msg_diff> & diffs,
bool filter_tool_calls) {
generated_text += text_added;
auto msg_prv_copy = chat_msg;
SRV_DBG("Parsing chat message: %s\n", generated_text.c_str());
@ -168,7 +169,64 @@ common_chat_msg task_result_state::update_chat_msg(
if (!new_msg.empty()) {
new_msg.set_tool_call_ids(generated_tool_call_ids, gen_tool_call_id);
chat_msg = new_msg;
diffs = common_chat_msg_diff::compute_diffs(msg_prv_copy, new_msg.empty() ? msg_prv_copy : new_msg);
auto all_diffs = common_chat_msg_diff::compute_diffs(msg_prv_copy, chat_msg);
if (!filter_tool_calls) {
diffs = std::move(all_diffs);
} else {
for (auto & d : all_diffs) {
// If this is a new type of delta, flush all currently pending tool call names
for (size_t i = 0; i < chat_msg.tool_calls.size(); ++i) {
if (sent_tool_call_names.count(i) || chat_msg.tool_calls[i].name.empty()) {
continue;
}
if (d.tool_call_index != i || !d.tool_call_delta.arguments.empty()) {
common_chat_msg_diff header;
header.tool_call_index = i;
header.tool_call_delta.id = chat_msg.tool_calls[i].id;
header.tool_call_delta.name = chat_msg.tool_calls[i].name;
diffs.push_back(std::move(header));
sent_tool_call_names.insert(i);
}
}
if (d.tool_call_index == std::string::npos) {
diffs.push_back(std::move(d));
} else {
size_t i = d.tool_call_index;
if (sent_tool_call_names.count(i)) {
if (!d.tool_call_delta.arguments.empty()) {
d.tool_call_delta.name = "";
d.tool_call_delta.id = "";
diffs.push_back(std::move(d));
}
} else {
// Not sent yet.
if (!d.tool_call_delta.arguments.empty() || !is_partial) {
d.tool_call_delta.name = chat_msg.tool_calls[i].name;
d.tool_call_delta.id = chat_msg.tool_calls[i].id;
diffs.push_back(std::move(d));
sent_tool_call_names.insert(i);
} else {
// Suppress
}
}
}
}
// Final check at EOF
if (!is_partial) {
for (size_t i = 0; i < chat_msg.tool_calls.size(); ++i) {
if (!sent_tool_call_names.count(i) && !chat_msg.tool_calls[i].name.empty()) {
common_chat_msg_diff header;
header.tool_call_index = i;
header.tool_call_delta.id = chat_msg.tool_calls[i].id;
header.tool_call_delta.name = chat_msg.tool_calls[i].name;
diffs.push_back(std::move(header));
sent_tool_call_names.insert(i);
}
}
}
}
}
return chat_msg;
}