ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-03 02:20:01 +00:00
Code Issues Packages Projects Releases Wiki Activity

Tool calls support from mainline (#723)

Browse Source 
* 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
Download Patch File Download Diff File Expand all files Collapse all files

11
examples/server/webui/src/components/ChatMessage.tsx
View File

@@ -55,21 +55,24 @@ export default function ChatMessage({
const { content, thought, isThinking }: SplitMessage = useMemo(() => {
if (msg.content === null || msg.role !== 'assistant') {
return { content: msg.content };
}
}
const REGEX_THINK_OPEN = /<think>|<\|channel\|>analysis<\|message\|>/;
const REGEX_THINK_CLOSE = /<\/think>|<\|end\|>/;
let actualContent = '';
let thought = '';
let isThinking = false;
let thinkSplit = msg.content.split('<think>', 2);
let thinkSplit = msg.content.split(REGEX_THINK_OPEN, 2);
actualContent += thinkSplit[0];
while (thinkSplit[1] !== undefined) {
// <think> tag found
thinkSplit = thinkSplit[1].split('</think>', 2);
thinkSplit = thinkSplit[1].split(REGEX_THINK_CLOSE, 2);
thought += thinkSplit[0];
isThinking = true;
if (thinkSplit[1] !== undefined) {
// </think> closing tag found
isThinking = false;
thinkSplit = thinkSplit[1].split('<think>', 2);
thinkSplit = thinkSplit[1].split(REGEX_THINK_OPEN, 2);
actualContent += thinkSplit[0];
}
}

3
examples/server/webui/src/utils/app.context.tsx
View File

@@ -215,6 +215,7 @@ export const AppContextProvider = ({
messages,
stream: true,
cache_prompt: true,
reasoning_format: 'none',
samplers: config.samplers,
temperature: config.temperature,
dynatemp_range: config.dynatemp_range,
@@ -261,7 +262,7 @@ export const AppContextProvider = ({
if (chunk.error) {
throw new Error(chunk.error?.message || 'Unknown error');
}
const addedContent = chunk.choices[0].delta.content;
const addedContent = chunk.choices?.[0]?.delta?.content;
const lastContent = pendingMsg.content || '';
if (addedContent) {
pendingMsg = {

13
examples/server/webui/src/utils/misc.ts
View File

@@ -80,13 +80,22 @@ export function normalizeMsgsForAPI(messages: Readonly<Message[]>) {
* recommended for DeepsSeek-R1, filter out content between <think> and </think> tags
*/
export function filterThoughtFromMsgs(messages: APIMessage[]) {
console.debug({ messages });
return messages.map((msg) => {
if (msg.role !== 'assistant') {
return msg;
}
// assistant message is always a string
const contentStr = msg.content as string;
return {
role: msg.role,
content:
msg.role === 'assistant'
? msg.content.split('</think>').at(-1)!.trim()
: msg.content,
? contentStr
.split(/<\/think>|<\|end\|>/)
.at(-1)!
.trim()
: contentStr,
} as APIMessage;
});
}