mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-27 08:21:30 +00:00
Fix thinking blocks with quotes + add handling [THINK]...[/THINK] blocks (#16326)
* fix: prevent reasoning blocks with quotes from being truncated * chore: update webui build output * feat: Improve thinking content parsing * test: Adds ChatMessage component stories for different thinking blocks * chore: update webui build output * fix: ChatMessage story fix --------- Co-authored-by: Aleksander Grygier <aleksander.grygier@gmail.com>
This commit is contained in:
Binary file not shown.
@@ -1,7 +1,8 @@
|
||||
/**
|
||||
* Parses thinking content from a message that may contain <think> tags
|
||||
* Parses thinking content from a message that may contain <think> tags or [THINK] tags
|
||||
* Returns an object with thinking content and cleaned message content
|
||||
* Handles both complete <think>...</think> blocks and incomplete <think> blocks (streaming)
|
||||
* Handles both complete blocks and incomplete blocks (streaming)
|
||||
* Supports formats: <think>...</think> and [THINK]...[/THINK]
|
||||
* @param content - The message content to parse
|
||||
* @returns An object containing the extracted thinking content and the cleaned message content
|
||||
*/
|
||||
@@ -9,12 +10,11 @@ export function parseThinkingContent(content: string): {
|
||||
thinking: string | null;
|
||||
cleanContent: string;
|
||||
} {
|
||||
const incompleteMatch = content.includes('<think>') && !content.includes('</think>');
|
||||
const incompleteThinkMatch = content.includes('<think>') && !content.includes('</think>');
|
||||
const incompleteThinkBracketMatch = content.includes('[THINK]') && !content.includes('[/THINK]');
|
||||
|
||||
if (incompleteMatch) {
|
||||
// Remove the entire <think>... part from clean content
|
||||
if (incompleteThinkMatch) {
|
||||
const cleanContent = content.split('</think>')?.[1]?.trim();
|
||||
// Extract everything after <think> as thinking content
|
||||
const thinkingContent = content.split('<think>')?.[1]?.trim();
|
||||
|
||||
return {
|
||||
@@ -23,12 +23,40 @@ export function parseThinkingContent(content: string): {
|
||||
};
|
||||
}
|
||||
|
||||
const completeMatch = content.includes('</think>');
|
||||
if (incompleteThinkBracketMatch) {
|
||||
const cleanContent = content.split('[/THINK]')?.[1]?.trim();
|
||||
const thinkingContent = content.split('[THINK]')?.[1]?.trim();
|
||||
|
||||
if (completeMatch) {
|
||||
return {
|
||||
thinking: content.split('</think>')?.[0]?.trim(),
|
||||
cleanContent: content.split('</think>')?.[1]?.trim()
|
||||
cleanContent,
|
||||
thinking: thinkingContent
|
||||
};
|
||||
}
|
||||
|
||||
const completeThinkMatch = content.match(/<think>([\s\S]*?)<\/think>/);
|
||||
const completeThinkBracketMatch = content.match(/\[THINK\]([\s\S]*?)\[\/THINK\]/);
|
||||
|
||||
if (completeThinkMatch) {
|
||||
const thinkingContent = completeThinkMatch[1]?.trim() ?? '';
|
||||
const cleanContent = `${content.slice(0, completeThinkMatch.index ?? 0)}${content.slice(
|
||||
(completeThinkMatch.index ?? 0) + completeThinkMatch[0].length
|
||||
)}`.trim();
|
||||
|
||||
return {
|
||||
thinking: thinkingContent,
|
||||
cleanContent
|
||||
};
|
||||
}
|
||||
|
||||
if (completeThinkBracketMatch) {
|
||||
const thinkingContent = completeThinkBracketMatch[1]?.trim() ?? '';
|
||||
const cleanContent = `${content.slice(0, completeThinkBracketMatch.index ?? 0)}${content.slice(
|
||||
(completeThinkBracketMatch.index ?? 0) + completeThinkBracketMatch[0].length
|
||||
)}`.trim();
|
||||
|
||||
return {
|
||||
thinking: thinkingContent,
|
||||
cleanContent
|
||||
};
|
||||
}
|
||||
|
||||
@@ -39,26 +67,33 @@ export function parseThinkingContent(content: string): {
|
||||
}
|
||||
|
||||
/**
|
||||
* Checks if content contains an opening <think> tag (for streaming)
|
||||
* Checks if content contains an opening thinking tag (for streaming)
|
||||
* Supports both <think> and [THINK] formats
|
||||
* @param content - The message content to check
|
||||
* @returns True if the content contains an opening <think> tag
|
||||
* @returns True if the content contains an opening thinking tag
|
||||
*/
|
||||
export function hasThinkingStart(content: string): boolean {
|
||||
return content.includes('<think>') || content.includes('<|channel|>analysis');
|
||||
return (
|
||||
content.includes('<think>') ||
|
||||
content.includes('[THINK]') ||
|
||||
content.includes('<|channel|>analysis')
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* Checks if content contains a closing </think> tag (for streaming)
|
||||
* Checks if content contains a closing thinking tag (for streaming)
|
||||
* Supports both </think> and [/THINK] formats
|
||||
* @param content - The message content to check
|
||||
* @returns True if the content contains a closing </think> tag
|
||||
* @returns True if the content contains a closing thinking tag
|
||||
*/
|
||||
export function hasThinkingEnd(content: string): boolean {
|
||||
return content.includes('</think>');
|
||||
return content.includes('</think>') || content.includes('[/THINK]');
|
||||
}
|
||||
|
||||
/**
|
||||
* Extracts partial thinking content during streaming
|
||||
* Used when we have <think> but not yet </think>
|
||||
* Supports both <think> and [THINK] formats
|
||||
* Used when we have opening tag but not yet closing tag
|
||||
* @param content - The message content to extract partial thinking from
|
||||
* @returns An object containing the extracted partial thinking content and the remaining content
|
||||
*/
|
||||
@@ -66,23 +101,41 @@ export function extractPartialThinking(content: string): {
|
||||
thinking: string | null;
|
||||
remainingContent: string;
|
||||
} {
|
||||
const startIndex = content.indexOf('<think>');
|
||||
if (startIndex === -1) {
|
||||
const thinkStartIndex = content.indexOf('<think>');
|
||||
const thinkEndIndex = content.indexOf('</think>');
|
||||
|
||||
const bracketStartIndex = content.indexOf('[THINK]');
|
||||
const bracketEndIndex = content.indexOf('[/THINK]');
|
||||
|
||||
const useThinkFormat =
|
||||
thinkStartIndex !== -1 && (bracketStartIndex === -1 || thinkStartIndex < bracketStartIndex);
|
||||
const useBracketFormat =
|
||||
bracketStartIndex !== -1 && (thinkStartIndex === -1 || bracketStartIndex < thinkStartIndex);
|
||||
|
||||
if (useThinkFormat) {
|
||||
if (thinkEndIndex === -1) {
|
||||
const thinkingStart = thinkStartIndex + '<think>'.length;
|
||||
|
||||
return {
|
||||
thinking: content.substring(thinkingStart),
|
||||
remainingContent: content.substring(0, thinkStartIndex)
|
||||
};
|
||||
}
|
||||
} else if (useBracketFormat) {
|
||||
if (bracketEndIndex === -1) {
|
||||
const thinkingStart = bracketStartIndex + '[THINK]'.length;
|
||||
|
||||
return {
|
||||
thinking: content.substring(thinkingStart),
|
||||
remainingContent: content.substring(0, bracketStartIndex)
|
||||
};
|
||||
}
|
||||
} else {
|
||||
return { thinking: null, remainingContent: content };
|
||||
}
|
||||
|
||||
const endIndex = content.indexOf('</think>');
|
||||
if (endIndex === -1) {
|
||||
// Still streaming thinking content
|
||||
const thinkingStart = startIndex + '<think>'.length;
|
||||
return {
|
||||
thinking: content.substring(thinkingStart),
|
||||
remainingContent: content.substring(0, startIndex)
|
||||
};
|
||||
}
|
||||
|
||||
// Complete thinking block found
|
||||
const parsed = parseThinkingContent(content);
|
||||
|
||||
return {
|
||||
thinking: parsed.thinking,
|
||||
remainingContent: parsed.cleanContent
|
||||
|
||||
@@ -59,6 +59,60 @@
|
||||
thinking: '',
|
||||
children: []
|
||||
});
|
||||
|
||||
// Message with <think> format thinking content
|
||||
const thinkTagMessage: DatabaseMessage = {
|
||||
id: '6',
|
||||
convId: 'conv-1',
|
||||
type: 'message',
|
||||
timestamp: Date.now() - 1000 * 60 * 2,
|
||||
role: 'assistant',
|
||||
content:
|
||||
"<think>\nLet me analyze this step by step:\n\n1. The user is asking about thinking formats\n2. I need to demonstrate the <think> tag format\n3. This content should be displayed in the thinking section\n4. The main response should be separate\n\nThis is a good example of reasoning content.\n</think>\n\nHere's my response after thinking through the problem. The thinking content above should be displayed separately from this main response content.",
|
||||
parent: '1',
|
||||
thinking: '',
|
||||
children: []
|
||||
};
|
||||
|
||||
// Message with [THINK] format thinking content
|
||||
const thinkBracketMessage: DatabaseMessage = {
|
||||
id: '7',
|
||||
convId: 'conv-1',
|
||||
type: 'message',
|
||||
timestamp: Date.now() - 1000 * 60 * 1,
|
||||
role: 'assistant',
|
||||
content:
|
||||
'[THINK]\nThis is the DeepSeek-style thinking format:\n\n- Using square brackets instead of angle brackets\n- Should work identically to the <think> format\n- Content parsing should extract this reasoning\n- Display should be the same as <think> format\n\nBoth formats should be supported seamlessly.\n[/THINK]\n\nThis is the main response content that comes after the [THINK] block. The reasoning above should be parsed and displayed in the thinking section.',
|
||||
parent: '1',
|
||||
thinking: '',
|
||||
children: []
|
||||
};
|
||||
|
||||
// Streaming message for <think> format
|
||||
let streamingThinkMessage = $state({
|
||||
id: '8',
|
||||
convId: 'conv-1',
|
||||
type: 'message',
|
||||
timestamp: 0, // No timestamp = streaming
|
||||
role: 'assistant',
|
||||
content: '',
|
||||
parent: '1',
|
||||
thinking: '',
|
||||
children: []
|
||||
});
|
||||
|
||||
// Streaming message for [THINK] format
|
||||
let streamingBracketMessage = $state({
|
||||
id: '9',
|
||||
convId: 'conv-1',
|
||||
type: 'message',
|
||||
timestamp: 0, // No timestamp = streaming
|
||||
role: 'assistant',
|
||||
content: '',
|
||||
parent: '1',
|
||||
thinking: '',
|
||||
children: []
|
||||
});
|
||||
</script>
|
||||
|
||||
<Story
|
||||
@@ -144,3 +198,115 @@
|
||||
await new Promise(resolve => setTimeout(resolve, 100));
|
||||
}}
|
||||
/>
|
||||
|
||||
<Story
|
||||
name="ThinkTagFormat"
|
||||
args={{
|
||||
class: 'max-w-[56rem] w-[calc(100vw-2rem)]',
|
||||
message: thinkTagMessage
|
||||
}}
|
||||
/>
|
||||
|
||||
<Story
|
||||
name="ThinkBracketFormat"
|
||||
args={{
|
||||
class: 'max-w-[56rem] w-[calc(100vw-2rem)]',
|
||||
message: thinkBracketMessage
|
||||
}}
|
||||
/>
|
||||
|
||||
<Story
|
||||
name="StreamingThinkTag"
|
||||
args={{
|
||||
message: streamingThinkMessage
|
||||
}}
|
||||
parameters={{
|
||||
test: {
|
||||
timeout: 30000
|
||||
}
|
||||
}}
|
||||
asChild
|
||||
play={async () => {
|
||||
// Phase 1: Stream <think> reasoning content
|
||||
const thinkingContent =
|
||||
'Let me work through this problem systematically:\n\n1. First, I need to understand what the user is asking\n2. Then I should consider different approaches\n3. I need to evaluate the pros and cons\n4. Finally, I should provide a clear recommendation\n\nThis step-by-step approach will ensure accuracy.';
|
||||
|
||||
let currentContent = '<think>\n';
|
||||
streamingThinkMessage.content = currentContent;
|
||||
|
||||
for (let i = 0; i < thinkingContent.length; i++) {
|
||||
currentContent += thinkingContent[i];
|
||||
streamingThinkMessage.content = currentContent;
|
||||
await new Promise((resolve) => setTimeout(resolve, 5));
|
||||
}
|
||||
|
||||
// Close the thinking block
|
||||
currentContent += '\n</think>\n\n';
|
||||
streamingThinkMessage.content = currentContent;
|
||||
await new Promise((resolve) => setTimeout(resolve, 200));
|
||||
|
||||
// Phase 2: Stream main response content
|
||||
const responseContent =
|
||||
"Based on my analysis above, here's the solution:\n\n**Key Points:**\n- The approach should be systematic\n- We need to consider all factors\n- Implementation should be step-by-step\n\nThis ensures the best possible outcome.";
|
||||
|
||||
for (let i = 0; i < responseContent.length; i++) {
|
||||
currentContent += responseContent[i];
|
||||
streamingThinkMessage.content = currentContent;
|
||||
await new Promise((resolve) => setTimeout(resolve, 10));
|
||||
}
|
||||
|
||||
streamingThinkMessage.timestamp = Date.now();
|
||||
}}
|
||||
>
|
||||
<div class="w-[56rem]">
|
||||
<ChatMessage message={streamingThinkMessage} />
|
||||
</div>
|
||||
</Story>
|
||||
|
||||
<Story
|
||||
name="StreamingThinkBracket"
|
||||
args={{
|
||||
message: streamingBracketMessage
|
||||
}}
|
||||
parameters={{
|
||||
test: {
|
||||
timeout: 30000
|
||||
}
|
||||
}}
|
||||
asChild
|
||||
play={async () => {
|
||||
// Phase 1: Stream [THINK] reasoning content
|
||||
const thinkingContent =
|
||||
'Using the DeepSeek format now:\n\n- This demonstrates the [THINK] bracket format\n- Should parse identically to <think> tags\n- The UI should display this in the thinking section\n- Main content should be separate\n\nBoth formats provide the same functionality.';
|
||||
|
||||
let currentContent = '[THINK]\n';
|
||||
streamingBracketMessage.content = currentContent;
|
||||
|
||||
for (let i = 0; i < thinkingContent.length; i++) {
|
||||
currentContent += thinkingContent[i];
|
||||
streamingBracketMessage.content = currentContent;
|
||||
await new Promise((resolve) => setTimeout(resolve, 5));
|
||||
}
|
||||
|
||||
// Close the thinking block
|
||||
currentContent += '\n[/THINK]\n\n';
|
||||
streamingBracketMessage.content = currentContent;
|
||||
await new Promise((resolve) => setTimeout(resolve, 200));
|
||||
|
||||
// Phase 2: Stream main response content
|
||||
const responseContent =
|
||||
"Here's my response after using the [THINK] format:\n\n**Observations:**\n- Both <think> and [THINK] formats work seamlessly\n- The parsing logic handles both cases\n- UI display is consistent across formats\n\nThis demonstrates the enhanced thinking content support.";
|
||||
|
||||
for (let i = 0; i < responseContent.length; i++) {
|
||||
currentContent += responseContent[i];
|
||||
streamingBracketMessage.content = currentContent;
|
||||
await new Promise((resolve) => setTimeout(resolve, 10));
|
||||
}
|
||||
|
||||
streamingBracketMessage.timestamp = Date.now();
|
||||
}}
|
||||
>
|
||||
<div class="w-[56rem]">
|
||||
<ChatMessage message={streamingBracketMessage} />
|
||||
</div>
|
||||
</Story>
|
||||
|
||||
Reference in New Issue
Block a user