diff --git a/tools/server/webui/docs/flows/settings-flow.md b/tools/server/webui/docs/flows/settings-flow.md index 578e01e6e1..474aef01b0 100644 --- a/tools/server/webui/docs/flows/settings-flow.md +++ b/tools/server/webui/docs/flows/settings-flow.md @@ -139,6 +139,6 @@ sequenceDiagram Note over settingsStore: UI-only (not synced): rect rgb(255, 240, 240) - Note over settingsStore: systemMessage, custom (JSON)
showStatistics, enableContinueGeneration
autoMicOnEmpty, disableAutoScroll
apiKey, pdfAsImage, disableReasoningFormat + Note over settingsStore: systemMessage, custom (JSON)
showStatistics, enableContinueGeneration
autoMicOnEmpty, disableAutoScroll
apiKey, pdfAsImage, disableReasoningParsing, showRawOutputSwitch end ``` diff --git a/tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageAssistant.svelte b/tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageAssistant.svelte index 61c62220ed..f5c9a37bef 100644 --- a/tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageAssistant.svelte +++ b/tools/server/webui/src/lib/components/app/chat/ChatMessages/ChatMessageAssistant.svelte @@ -261,7 +261,7 @@ {onConfirmDelete} {onNavigateToSibling} {onShowDeleteDialogChange} - showRawOutputSwitch={currentConfig.disableReasoningFormat} + showRawOutputSwitch={currentConfig.showRawOutputSwitch} rawOutputEnabled={showRawOutput} onRawOutputToggle={(enabled) => (showRawOutput = enabled)} /> diff --git a/tools/server/webui/src/lib/components/app/chat/ChatSettings/ChatSettings.svelte b/tools/server/webui/src/lib/components/app/chat/ChatSettings/ChatSettings.svelte index decca7c52f..00e0b555ce 100644 --- a/tools/server/webui/src/lib/components/app/chat/ChatSettings/ChatSettings.svelte +++ b/tools/server/webui/src/lib/components/app/chat/ChatSettings/ChatSettings.svelte @@ -276,8 +276,13 @@ icon: Code, fields: [ { - key: 'disableReasoningFormat', - label: 'Enable raw LLM output switch', + key: 'disableReasoningParsing', + label: 'Disable reasoning content parsing', + type: 'checkbox' + }, + { + key: 'showRawOutputSwitch', + label: 'Enable raw output toggle', type: 'checkbox' }, { diff --git a/tools/server/webui/src/lib/constants/settings-config.ts b/tools/server/webui/src/lib/constants/settings-config.ts index de4685fe24..e8052b833d 100644 --- a/tools/server/webui/src/lib/constants/settings-config.ts +++ b/tools/server/webui/src/lib/constants/settings-config.ts @@ -6,7 +6,8 @@ export const SETTING_CONFIG_DEFAULT: Record = showSystemMessage: true, theme: 'system', showThoughtInProgress: false, - disableReasoningFormat: false, + disableReasoningParsing: false, + showRawOutputSwitch: false, keepStatsVisible: false, showMessageStats: true, askForTitleConfirmation: false, @@ -95,8 +96,10 @@ export const SETTING_CONFIG_INFO: Record = { max_tokens: 'The maximum number of token per output. Use -1 for infinite (no limit).', custom: 'Custom JSON parameters to send to the API. Must be valid JSON format.', showThoughtInProgress: 'Expand thought process by default when generating messages.', - disableReasoningFormat: - 'Enable raw LLM output switch to show unprocessed model output without backend parsing and frontend Markdown rendering to inspect streaming across different models.', + disableReasoningParsing: + 'Send reasoning_format=none to prevent server-side extraction of reasoning tokens into separate field', + showRawOutputSwitch: + 'Show toggle button to display messages as plain text instead of Markdown-formatted content', keepStatsVisible: 'Keep processing statistics visible after generation finishes.', showMessageStats: 'Display generation statistics (tokens/second, token count, duration) below each assistant message.', diff --git a/tools/server/webui/src/lib/services/chat.ts b/tools/server/webui/src/lib/services/chat.ts index 02fc6381c0..55af0ce816 100644 --- a/tools/server/webui/src/lib/services/chat.ts +++ b/tools/server/webui/src/lib/services/chat.ts @@ -90,7 +90,7 @@ export class ChatService { custom, timings_per_token, // Config options - disableReasoningFormat + disableReasoningParsing } = options; const normalizedMessages: ApiChatMessageData[] = messages @@ -127,7 +127,7 @@ export class ChatService { requestBody.model = options.model; } - requestBody.reasoning_format = disableReasoningFormat ? 'none' : 'auto'; + requestBody.reasoning_format = disableReasoningParsing ? 'none' : 'auto'; if (temperature !== undefined) requestBody.temperature = temperature; if (max_tokens !== undefined) { diff --git a/tools/server/webui/src/lib/services/parameter-sync.ts b/tools/server/webui/src/lib/services/parameter-sync.ts index ec39f29761..d0f682999b 100644 --- a/tools/server/webui/src/lib/services/parameter-sync.ts +++ b/tools/server/webui/src/lib/services/parameter-sync.ts @@ -69,12 +69,6 @@ export const SYNCABLE_PARAMETERS: SyncableParameter[] = [ type: 'boolean', canSync: true }, - { - key: 'disableReasoningFormat', - serverKey: 'disableReasoningFormat', - type: 'boolean', - canSync: true - }, { key: 'keepStatsVisible', serverKey: 'keepStatsVisible', type: 'boolean', canSync: true }, { key: 'showMessageStats', serverKey: 'showMessageStats', type: 'boolean', canSync: true }, { diff --git a/tools/server/webui/src/lib/stores/chat.svelte.ts b/tools/server/webui/src/lib/stores/chat.svelte.ts index 3005063b4b..03e05c4259 100644 --- a/tools/server/webui/src/lib/stores/chat.svelte.ts +++ b/tools/server/webui/src/lib/stores/chat.svelte.ts @@ -1456,7 +1456,7 @@ class ChatStore { // Config options needed by ChatService if (currentConfig.systemMessage) apiOptions.systemMessage = currentConfig.systemMessage; - if (currentConfig.disableReasoningFormat) apiOptions.disableReasoningFormat = true; + if (currentConfig.disableReasoningParsing) apiOptions.disableReasoningParsing = true; if (hasValue(currentConfig.temperature)) apiOptions.temperature = Number(currentConfig.temperature); diff --git a/tools/server/webui/src/lib/types/settings.d.ts b/tools/server/webui/src/lib/types/settings.d.ts index 38b3047dd0..d894245ec3 100644 --- a/tools/server/webui/src/lib/types/settings.d.ts +++ b/tools/server/webui/src/lib/types/settings.d.ts @@ -18,8 +18,8 @@ export interface SettingsChatServiceOptions { model?: string; // System message to inject systemMessage?: string; - // Disable reasoning format (use 'none' instead of 'auto') - disableReasoningFormat?: boolean; + // Disable reasoning parsing (use 'none' instead of 'auto') + disableReasoningParsing?: boolean; // Generation parameters temperature?: number; max_tokens?: number; diff --git a/tools/server/webui/tests/stories/ChatMessage.stories.svelte b/tools/server/webui/tests/stories/ChatMessage.stories.svelte index 5f4de7d476..a3579cf04e 100644 --- a/tools/server/webui/tests/stories/ChatMessage.stories.svelte +++ b/tools/server/webui/tests/stories/ChatMessage.stories.svelte @@ -93,7 +93,7 @@ }} play={async () => { const { settingsStore } = await import('$lib/stores/settings.svelte'); - settingsStore.updateConfig('disableReasoningFormat', false); + settingsStore.updateConfig('showRawOutputSwitch', false); }} /> @@ -105,7 +105,7 @@ }} play={async () => { const { settingsStore } = await import('$lib/stores/settings.svelte'); - settingsStore.updateConfig('disableReasoningFormat', false); + settingsStore.updateConfig('showRawOutputSwitch', false); }} /> @@ -117,7 +117,7 @@ }} play={async () => { const { settingsStore } = await import('$lib/stores/settings.svelte'); - settingsStore.updateConfig('disableReasoningFormat', false); + settingsStore.updateConfig('showRawOutputSwitch', false); }} /> @@ -129,7 +129,7 @@ }} play={async () => { const { settingsStore } = await import('$lib/stores/settings.svelte'); - settingsStore.updateConfig('disableReasoningFormat', true); + settingsStore.updateConfig('showRawOutputSwitch', true); }} /> @@ -141,7 +141,7 @@ asChild play={async () => { const { settingsStore } = await import('$lib/stores/settings.svelte'); - settingsStore.updateConfig('disableReasoningFormat', false); + settingsStore.updateConfig('showRawOutputSwitch', false); // Phase 1: Stream reasoning content in chunks let reasoningText = 'I need to think about this carefully. Let me break down the problem:\n\n1. The user is asking for help with something complex\n2. I should provide a thorough and helpful response\n3. I need to consider multiple approaches\n4. The best solution would be to explain step by step\n\nThis approach will ensure clarity and understanding.'; @@ -193,7 +193,7 @@ }} play={async () => { const { settingsStore } = await import('$lib/stores/settings.svelte'); - settingsStore.updateConfig('disableReasoningFormat', false); + settingsStore.updateConfig('showRawOutputSwitch', false); // Import the chat store to simulate loading state const { chatStore } = await import('$lib/stores/chat.svelte');