mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-19 11:57:07 +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:
@@ -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