mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-05-22 03:10:03 +00:00
* webui: Move static build output from `tools/server/public` to `build/ui` directory * refactor: Move to `tools/ui` * refactor: rename CMake variables and preprocessor defines - Rename LLAMA_BUILD_WEBUI -> LLAMA_BUILD_UI (old kept as deprecated) - Rename LLAMA_USE_PREBUILT_WEBUI -> LLAMA_USE_PREBUILT_UI (old kept as deprecated) - Backward compat: old vars auto-forward to new ones with DEPRECATION warning - Rename internal vars: WEBUI_SOURCE -> UI_SOURCE, WEBUI_SOURCE_DIR -> UI_SOURCE_DIR, etc. - Rename HF bucket: LLAMA_WEBUI_HF_BUCKET -> LLAMA_UI_HF_BUCKET - Emit both LLAMA_BUILD_WEBUI and LLAMA_BUILD_UI preprocessor defines - Emit both LLAMA_WEBUI_DEFAULT_ENABLED and LLAMA_UI_DEFAULT_ENABLED * refactor: rename CLI flags (--webui -> --ui) with backward compat - Add --ui/--no-ui (old --webui/--no-webui kept as deprecated aliases) - Add --ui-config (old --webui-config kept as deprecated alias) - Add --ui-config-file (old --webui-config-file kept as deprecated alias) - Add --ui-mcp-proxy/--no-ui-mcp-proxy (old --webui-mcp-proxy kept as deprecated) - Add new env vars: LLAMA_ARG_UI, LLAMA_ARG_UI_CONFIG, LLAMA_ARG_UI_CONFIG_FILE, LLAMA_ARG_UI_MCP_PROXY - C++ struct fields: params.ui, params.ui_config_json, params.ui_mcp_proxy added alongside old fields - Backward compat: old fields synced to new ones in g_params_to_internals * refactor: update C++ server internals with backward compat - Rename json_webui_settings -> json_ui_settings (both kept in server_context_meta) - Rename params.webui usage -> params.ui (both synced, old still works) - JSON API emits both "ui"/"ui_settings" and "webui"/"webui_settings" keys - Server routes use params.ui_mcp_proxy || params.webui_mcp_proxy - Preprocessor guards use #if defined(LLAMA_BUILD_UI) || defined(LLAMA_BUILD_WEBUI) * refactor: rename CI/CD workflows, artifacts, and build script - Rename webui-build.yml -> ui-build.yml; artifact webui-build -> ui-build - Rename webui-publish.yml -> ui-publish.yml; var HF_BUCKET_WEBUI_STATIC_OUTPUT -> HF_BUCKET_UI_STATIC_OUTPUT - Rename server-webui.yml -> server-ui.yml; job webui-build/checks -> ui-build/checks - Update server.yml: job/artifact refs webui-build -> ui-build - Update release.yml: all webui-build/publish refs -> ui-build/publish; HF_TOKEN_WEBUI_STATIC_OUTPUT -> HF_TOKEN_UI_STATIC_OUTPUT - Update server-self-hosted.yml: webui-build -> ui-build - Update build-self-hosted.yml: HF_WEBUI_VERSION -> HF_UI_VERSION - Rename webui-download.cmake -> ui-download.cmake (internal refs updated) - Update labeler.yml: server/webui -> server/ui path label * docs: update CODEOWNERS and server README docs - Update CODEOWNERS: team ggml-org/llama-webui -> ggml-org/llama-ui, path /tools/server/webui/ -> /tools/ui/ - Update server README.md: CLI tables show --ui flags with deprecated --webui aliases - Update server README-dev.md: "WebUI" -> "UI", paths updated to tools/ui/ * fix: Small fixes for UI build * fix: CMake.txt syntax * chore: Formatting * fix: `.editorconfig` for llama-ui * chore: Formatting * refactor: Use `APP_NAME` in Error route * refactor: Cleanup * refactor: Single migration service * make llama-ui a linkable target * fix: UI Build output * fix: Missing change * fix: separate llama-ui npm build output into build/tools/ui/dist subfolder + use cmake npm build instead of downloading ui-build.yml artifacts in CI * refactor: UI workflows cleanup --------- Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
207 lines
6.3 KiB
Svelte
207 lines
6.3 KiB
Svelte
<script module lang="ts">
|
|
import { defineMeta } from '@storybook/addon-svelte-csf';
|
|
import ChatMessage from '$lib/components/app/chat/ChatMessages/ChatMessage/ChatMessage.svelte';
|
|
|
|
const { Story } = defineMeta({
|
|
title: 'Components/ChatScreen/ChatMessage',
|
|
component: ChatMessage,
|
|
parameters: {
|
|
layout: 'centered'
|
|
}
|
|
});
|
|
|
|
// Mock messages for different scenarios
|
|
const userMessage: DatabaseMessage = {
|
|
id: '1',
|
|
convId: 'conv-1',
|
|
type: 'message',
|
|
timestamp: Date.now() - 1000 * 60 * 5,
|
|
role: 'user',
|
|
content: 'What is the meaning of life, the universe, and everything?',
|
|
parent: '',
|
|
thinking: '',
|
|
children: []
|
|
};
|
|
|
|
const assistantMessage: DatabaseMessage = {
|
|
id: '2',
|
|
convId: 'conv-1',
|
|
type: 'message',
|
|
timestamp: Date.now() - 1000 * 60 * 3,
|
|
role: 'assistant',
|
|
content:
|
|
'The answer to the ultimate question of life, the universe, and everything is **42**.\n\nThis comes from Douglas Adams\' "The Hitchhiker\'s Guide to the Galaxy," where a supercomputer named Deep Thought calculated this answer over 7.5 million years. However, the question itself was never properly formulated, which is why the answer seems meaningless without context.',
|
|
parent: '1',
|
|
thinking: '',
|
|
children: []
|
|
};
|
|
|
|
const assistantWithReasoning: DatabaseMessage = {
|
|
id: '3',
|
|
convId: 'conv-1',
|
|
type: 'message',
|
|
timestamp: Date.now() - 1000 * 60 * 2,
|
|
role: 'assistant',
|
|
content: "Here's the concise answer, now that I've thought it through carefully for you.",
|
|
parent: '1',
|
|
thinking:
|
|
"Let's consider the user's question step by step:\\n\\n1. Identify the core problem\\n2. Evaluate relevant information\\n3. Formulate a clear answer\\n\\nFollowing this process ensures the final response stays focused and accurate.",
|
|
children: []
|
|
};
|
|
const rawOutputMessage: DatabaseMessage = {
|
|
id: '6',
|
|
convId: 'conv-1',
|
|
type: 'message',
|
|
timestamp: Date.now() - 1000 * 60,
|
|
role: 'assistant',
|
|
content:
|
|
'<|channel|>analysis<|message|>User greeted me. Initiating overcomplicated analysis: Is this a trap? No, just a normal hello. Respond calmly, act like a helpful assistant, and do not start explaining quantum physics again. Confidence 0.73. Engaging socially acceptable greeting protocol...<|end|>Hello there! How can I help you today?',
|
|
parent: '1',
|
|
thinking: '',
|
|
children: []
|
|
};
|
|
|
|
let processingMessage = $state({
|
|
id: '4',
|
|
convId: 'conv-1',
|
|
type: 'message',
|
|
timestamp: 0, // No timestamp = processing
|
|
role: 'assistant',
|
|
content: '',
|
|
parent: '1',
|
|
thinking: '',
|
|
children: []
|
|
});
|
|
|
|
let streamingMessage = $state({
|
|
id: '5',
|
|
convId: 'conv-1',
|
|
type: 'message',
|
|
timestamp: 0, // No timestamp = streaming
|
|
role: 'assistant',
|
|
content: '',
|
|
parent: '1',
|
|
thinking: '',
|
|
children: []
|
|
});
|
|
</script>
|
|
|
|
<Story
|
|
name="User"
|
|
args={{
|
|
message: userMessage
|
|
}}
|
|
play={async () => {
|
|
const { settingsStore } = await import('$lib/stores/settings.svelte');
|
|
settingsStore.updateConfig('showRawOutputSwitch', false);
|
|
}}
|
|
/>
|
|
|
|
<Story
|
|
name="Assistant"
|
|
args={{
|
|
class: 'max-w-[56rem] w-[calc(100vw-2rem)]',
|
|
message: assistantMessage
|
|
}}
|
|
play={async () => {
|
|
const { settingsStore } = await import('$lib/stores/settings.svelte');
|
|
settingsStore.updateConfig('showRawOutputSwitch', false);
|
|
}}
|
|
/>
|
|
|
|
<Story
|
|
name="AssistantWithReasoning"
|
|
args={{
|
|
class: 'max-w-[56rem] w-[calc(100vw-2rem)]',
|
|
message: assistantWithReasoning
|
|
}}
|
|
play={async () => {
|
|
const { settingsStore } = await import('$lib/stores/settings.svelte');
|
|
settingsStore.updateConfig('showRawOutputSwitch', false);
|
|
}}
|
|
/>
|
|
|
|
<Story
|
|
name="RawLlmOutput"
|
|
args={{
|
|
class: 'max-w-[56rem] w-[calc(100vw-2rem)]',
|
|
message: rawOutputMessage
|
|
}}
|
|
play={async () => {
|
|
const { settingsStore } = await import('$lib/stores/settings.svelte');
|
|
settingsStore.updateConfig('showRawOutputSwitch', true);
|
|
}}
|
|
/>
|
|
|
|
<Story
|
|
name="WithReasoningContent"
|
|
args={{
|
|
message: streamingMessage
|
|
}}
|
|
asChild
|
|
play={async () => {
|
|
const { settingsStore } = await import('$lib/stores/settings.svelte');
|
|
settingsStore.updateConfig('showRawOutputSwitch', false);
|
|
// Phase 1: Stream reasoning content in chunks
|
|
let reasoningText =
|
|
'I need to think about this carefully. Let me break down the problem:\n\n1. The user is asking for help with something complex\n2. I should provide a thorough and helpful response\n3. I need to consider multiple approaches\n4. The best solution would be to explain step by step\n\nThis approach will ensure clarity and understanding.';
|
|
|
|
let reasoningChunk = 'I';
|
|
let i = 0;
|
|
while (i < reasoningText.length) {
|
|
const chunkSize = Math.floor(Math.random() * 5) + 3; // Random 3-7 characters
|
|
const chunk = reasoningText.slice(i, i + chunkSize);
|
|
reasoningChunk += chunk;
|
|
|
|
// Update the reactive state directly
|
|
streamingMessage.thinking = reasoningChunk;
|
|
|
|
i += chunkSize;
|
|
await new Promise((resolve) => setTimeout(resolve, 50));
|
|
}
|
|
|
|
const regularText =
|
|
"Based on my analysis, here's the solution:\n\n**Step 1:** First, we need to understand the requirements clearly.\n\n**Step 2:** Then we can implement the solution systematically.\n\n**Step 3:** Finally, we test and validate the results.\n\nThis approach ensures we cover all aspects of the problem effectively.";
|
|
|
|
let contentChunk = '';
|
|
i = 0;
|
|
|
|
while (i < regularText.length) {
|
|
const chunkSize = Math.floor(Math.random() * 5) + 3; // Random 3-7 characters
|
|
const chunk = regularText.slice(i, i + chunkSize);
|
|
contentChunk += chunk;
|
|
|
|
// Update the reactive state directly
|
|
streamingMessage.content = contentChunk;
|
|
|
|
i += chunkSize;
|
|
await new Promise((resolve) => setTimeout(resolve, 50));
|
|
}
|
|
|
|
streamingMessage.timestamp = Date.now();
|
|
}}
|
|
>
|
|
<div class="w-[56rem]">
|
|
<ChatMessage message={streamingMessage} />
|
|
</div>
|
|
</Story>
|
|
|
|
<Story
|
|
name="Processing"
|
|
args={{
|
|
message: processingMessage
|
|
}}
|
|
play={async () => {
|
|
const { settingsStore } = await import('$lib/stores/settings.svelte');
|
|
settingsStore.updateConfig('showRawOutputSwitch', false);
|
|
// Import the chat store to simulate loading state
|
|
const { chatStore } = await import('$lib/stores/chat.svelte');
|
|
|
|
// Set loading state to true to trigger the processing UI
|
|
chatStore.isLoading = true;
|
|
|
|
// Simulate the processing state hook behavior
|
|
// This will show the "Generating..." text and parameter details
|
|
await new Promise((resolve) => setTimeout(resolve, 100));
|
|
}}
|
|
/>
|