mirror of
https://github.com/DayuanJiang/next-ai-draw-io.git
synced 2026-09-01 17:10:24 +08:00
8fb9ef20bd8e343e41a8073f1d7ed4260935cf05
9 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
dayuan.jiang
|
8fb9ef20bd |
fix: raise the output budget so reasoning models reach the tool call
A reasoning model spends the output budget in order: thinking first, then prose, then the tool call. With 16000 the thinking alone can consume all of it, so the turn ends with finishReason "length" before display_diagram is ever called. The canvas stays empty and nothing surfaces in the UI, because no tool call means no tool error, and the client never reads finishReason. Measured on openrouter deepseek/deepseek-v4-flash, the model from the report: - max_tokens=800 with reasoning on returns reasoning_tokens=800, empty content, finish_reason length. So reasoning is billed against this budget, not exempt. - refining an existing diagram (19k chars of XML in the input) produced 49142 chars of reasoning, zero tool calls, finishReason "length" at 16000 - the same request at 40000 finished and called edit_diagram with 12 operations 64000 cannot just be sent to every model: bedrock claude-3-haiku caps at 4096, nova-lite at 10000, and the openrouter deepseek-r1 endpoint counts input and output against one 64000 ceiling. All three name the real limit in the 400, so parse it and retry once. Verified: nova-lite logs "64000 rejected, retrying with 10000" and then completes its tool call. Also expose the budget in Settings. It is sent as a header rather than read from env only, so desktop users can raise it themselves without an env file. vercel.json goes back to the 300s it had before #238 traded it for $2-4/month. That is now Vercel's own default, and billing pauses while the function waits on the model, so the saving that motivated 120s no longer applies. edgeone.json is left alone: its 120 may be that platform's actual ceiling. |
||
|
astordu
|
f5ea5a0edd |
feat: add personal My Templates library alongside Quick Examples (#773)
* 增加了ralph自动化编程梳理 * feat: US-001 - 为模板库建立独立的 IndexedDB 存储层 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: US-002 - 在空聊天状态用我的模板库替换官方示例 - 将 ChatLobby 中的 Quick Examples 替换为 TemplatePanel - 当没有历史会话时，展示完整的模板库面板 - 当有历史会话时，展示可折叠的 "My Templates" 区域 - 使用 TemplatePanel 组件展示用户的个人模板库 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: US-004 - Provide template creation flow - Create TemplateCreateDialog component with form fields for prompt, title, description, tags, and pinned - Add i18n translations for template creation UI in en, zh, zh-Hant, ja - Update TemplatePanel to integrate the create dialog - Support initialPrompt prop for pre-filling from current input - Validate required prompt field (empty prompt not allowed) - Auto-generate default title from first 20 chars of Pin templates appear at top of list Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: US-005 - 为模板卡片提供编辑、删除和复制操作 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: US-006 - Send template directly on click and record usage statistics - Implement click-to-send template functionality with confirmation dialog - Add clickCount and runCount increment logic - Display runCount and lastUsedAt on template card - Add i18n translations for confirmation dialog (en, zh, zh-Hant, ja) - Pass onSendTemplate and currentInput props through component hierarchy Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: US-007 - Support template search, pin and default sorting - Add search bar to TemplatePanel with real-time filtering by title, description, and tags - Add pin/unpin toggle button on template cards (uses Bookmark icon with fill indicator) - Search uses existing searchTemplates function from template-storage - Sort uses existing sortTemplates function (pinned desc, runCount desc, lastUsedAt desc, updatedAt desc) - Show empty state with Search icon when search returns no results - List re-sorts immediately after pin/unpin toggle - Add i18n keys: searchPlaceholder, searchNoResults, pin, unpin for all 4 languages Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: US-008 - Support saving current input as template Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: US-009 - Support saving historical user message as template - Add "Save as Template" button to user messages - Pre-fill prompt with original user message text - Only show on user messages,- Dialog opens TemplateCreateDialog on click - Template appears in list immediately after saving Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: US-010 - Support template import and export Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: remove local-only dirs from git tracking (.agents, .cursor, scripts, screenshots) These directories contain local IDE configs, agent scripts, and dev tooling that should not be part of the upstream repository. Added them to .gitignore to prevent future accidental commits. * chore: remove AGENTS.md from git tracking * fix: add missing i18n keys for template export/import (en/zh/zh-Hant/ja) * fix: review fixes for my-templates PR - Fix fragile querySelector("form") with id-based lookup - Add objectStoreNames.contains guards for IndexedDB upgrades - Remove duplicate TemplateSchema, import from template-storage - Revert contributor-specific .gitignore additions - Fix broken i18n placeholders and missing translations (zh/ja/zh-Hant) - Remove unused setFiles prop from ChatLobby - Remove tags feature (unnecessary complexity) - Improve template card layout: overlay icons on hover, align stats - Add break-all and overflow-hidden for long prompt text in dialogs - Move incrementClickCount into sendTemplate for accurate tracking - Use Intl.RelativeTimeFormat for locale-aware relative time * feat: restore Quick Examples panel and add lobby panel visibility settings Bring back the ExamplePanel as a third collapsible section in ChatLobby alongside Recent Chats and My Templates. Add toggle switches in Settings to show/hide each lobby panel, persisted via localStorage. * fix: template send race condition, import defaults, and empty title bug - Use flushSync instead of setTimeout(0) in handleSendTemplate to ensure React state is flushed before form submission - Explicitly validate and default all fields in importTemplates to prevent undefined counters from malformed import JSON - Fall back to existing title in edit dialog instead of writing undefined * fix: address Copilot review comments and remove PRD file - Fix fallback formatLastUsed returning "Not used yet" for recent usage - Remove dead mounted flag in TemplatePanel useEffect - Respect panel visibility settings in no-history lobby state - Reject empty/whitespace titles in import validation - Trim title/prompt in importTemplates with default title fallback - Remove tasks/prd-template-library-replaces-examples.md from repo * fix: remove double sort, dead code, redundant stats, and break-all CSS - Remove redundant sortTemplates call in loadTemplates (already sorted by getAllTemplates) - Remove unused createEmptyTemplateInput and sortTemplates import - Show "Not used yet" only once for unused templates instead of twice - Use break-words instead of break-all on prompt textareas --------- Co-authored-by: 杜雷 <dreamfly@126.com> Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Co-authored-by: dayuan.jiang <jdy.toh@gmail.com> |
||
|
Dayuan Jiang
|
e7453e86a6 |
feat: add custom system message setting for AI personalization (#728)
* feat: add custom system message setting for AI personalization Allow users to enter custom instructions via a textarea in Settings that get appended to the AI's system prompt. Includes server-side validation (type check + 5000 char limit), localStorage persistence, and i18n support for all 4 locales. * fix: add accessibility htmlFor/id pairing on custom system message textarea |
||
|
yujinze
|
afddba364b |
Add VLM-based diagram validation (#602)
* [Feature] Add VLM-based diagram validation Add automatic VLM (Vision Language Model) validation after display_diagram tool execution. The system captures a screenshot of the rendered diagram, sends it to a VLM for visual analysis, and uses feedback to improve diagram quality through the existing retry mechanism. Changes: - Add /api/validate-diagram endpoint for VLM validation - Add diagram-validator.ts for client-side validation orchestration - Add validation-prompts.ts for VLM system prompts - Add ValidationCard component to display validation status in chat - Add PNG capture functionality to diagram context - Integrate validation into tool handlers with retry support (max 3) - Add "Improve with Suggestions" button for manual regeneration - Add settings toggle to enable/disable VLM validation - Add getValidationModel() helper in ai-providers.ts * refactor(validation): use AI SDK structured outputs and address review feedback - Replace generateText + manual JSON parsing with generateObject and Zod schema for type-safe structured validation output - Use AbortSignal.timeout() instead of Promise.race for cleaner timeout handling - Add timeout validation with minimum 1000ms to handle malformed env values - Remove unused xml parameter from validateRenderedDiagram API - Remove parseValidationResponse function (now handled by schema) - Clear validationStates on session switch and new chat to prevent memory leak - Update 100ms render delay comment to clarify best-effort heuristic - Remove unused useEffect import from ValidationCard - Fix optional chaining lint warning in ValidationCard - Add unit tests for formatValidationFeedback function * refactor(validation): use AI SDK experimental_useObject hook instead of raw fetch - Change API endpoint from generateObject to streamObject for useObject compatibility - Create useValidateDiagram hook using AI SDK's experimental_useObject for reactive validation - Update useDiagramToolHandlers to accept validation function as parameter - Update chat-panel to use new useValidateDiagram hook - Remove validateRenderedDiagram function from lib/diagram-validator.ts (now in hook) - Export ValidationResultSchema from API route for client-side use * fix(validation): extract schema to shared file for client/server compatibility Move ValidationResultSchema to lib/validation-schema.ts to avoid importing server-side modules (ai-providers) into client-side code. This fixes the Turbopack build error caused by the hook importing from the API route. * fix(validation): use 'Valid' instead of 'Complete' for validation success Change ValidationCard success label from 'Complete' to 'Valid' to avoid conflicting with ToolCallCard's 'Complete' badge in E2E tests. This fixes the diagram-generation E2E test that expects a specific count of 'Complete' badges. * fix(validation): add aria-hidden to icons to prevent duplicate ID warning * fix: improve VLM validation with bug fixes and i18n - Fix race condition in pendingValidationRef (reject previous pending validation) - Fix response format consistency (use streaming for all responses) - Remove dead code (unused lastRequestRef and ValidationRequest interface) - Consolidate duplicate types (re-export from validation-schema.ts) - Add 'success_with_warnings' status for valid diagrams with warnings - Fix tool card auto-collapse (only collapse once, respect user toggle) - Set VLM validation default to disabled - Add i18n support for diagram validation settings (en/zh/ja) - Mark feature as experimental in settings UI * fix: resolve TypeScript errors in electron-standalone - Add forwardRef support to ChatInput component with ChatInputRef type - Copy electron.d.ts to electron-standalone/electron folder - Exclude electron-standalone from root tsconfig type checking * fix: return empty string for valid result with no issues in formatValidationFeedback * feat(i18n): add validation strings for ValidationCard component - Add validation section to en.json, zh.json, ja.json dictionaries - Update ValidationCard to use useDictionary hook - Replace all hardcoded English strings with i18n keys --------- Co-authored-by: dayuan.jiang <jdy.toh@gmail.com> |
||
|
danqzq
|
c3d3afc202 | Remove redundant Close Protection setting | ||
|
Maifee Ul Asad
|
b7eaf46555 |
[Feature] Add setting for Enter/Ctrl+Enter to send messages (#550)
* i18n: add translations for send shortcut setting * feat: configurable keyboard shortcut for sending messages * refactor,review: using storage key for send shortcut * Increase the width of the trigger in the settings dialog. Previously, at 160px, it hide the letter “d” from the word “Send.” * Update components/chat-input.tsx Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * fix: from review, ctrl send support for mac * refactor: from review, reduce local storage read * fix: make send shortcut setting reactive without page refresh --------- Co-authored-by: Biki Kalita <86558912+Biki-dev@users.noreply.github.com> Co-authored-by: Dayuan Jiang <34411969+DayuanJiang@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: dayuan.jiang <jdy.toh@gmail.com> |
||
|
Dayuan Jiang
|
4dc774d03f |
feat: add chat session history with IndexedDB persistence (#500)
* feat(session): add chat session history with IndexedDB storage - Add session-storage.ts with IndexedDB wrapper using idb library - Add use-session-manager.ts hook for session state management - Add session-history-dropdown.tsx for session selection UI - Integrate session system into chat-panel.tsx - Auto-generate session titles from first user message - Auto-save sessions on message completion - Support session switching, deletion, and creation - Migrate existing localStorage data to IndexedDB - Add i18n translations for session history UI * feat(session): improve history dropdown and persist diagram history - Add time-based grouping (Today, Yesterday, This Week, Earlier) - Add thumbnail previews using Next.js Image component - Add staggered entrance animations with fade-in effects - Improve active session indicator with left border accent - Fix scrolling by using native overflow instead of ScrollArea - Persist diagram version history to IndexedDB sessions - Remove redundant diagram XML from localStorage - Add i18n strings for time group labels (en, ja, zh) * fix(session): prevent data loss on theme change and tab close - Add isDrawioReady effect to restore diagram after DrawIO remount - Add visibilitychange handler to save session when page becomes hidden - Fix missing currentSessionId in saveCurrentSession dependency array - Remove unused sanitizeMessages import from use-session-manager * fix(session): fix diagram save and migration data loss bugs - Add diagramHistory to save effect dependency array so diagram-only edits trigger saves (previously only message changes did) - Destructure stable sessionManager values to prevent unnecessary effect re-runs on every render - Add try-catch wrapper around debounced async save operation - Make saveSession() return boolean to indicate success/failure - Verify IndexedDB write succeeded before deleting localStorage data during migration (prevents data loss if write silently fails) - Keep localStorage data for retry if migration fails instead of marking as complete anyway * refactor(session): extract helpers to reduce code duplication - Add syncUIWithSession helper to consolidate 4 duplicate UI sync blocks - Add buildSessionData helper to consolidate 4 duplicate save logic blocks - Remove unused saveTimeoutRef and its cleanup effect - Net reduction of ~80 lines of duplicate code * style(ui): improve history dropdown and delete dialog styling - Change destructive color from coral to muted rose for refined look - Make session history panel taller (400px fixed height) - Fix popover alignment to prevent truncation - Style delete button with soft red outline instead of solid fill - Make delete dialog more compact (max-w-sm) * fix(session): reset refs on new chat and show recent sessions - Fix cached example diagrams not displaying after creating new session - Reset previousXML, lastProcessedXmlRef and processedToolCalls when messages become empty (new chat or session switch) - Add recent chats section in empty chat state with collapsible examples - Pass sessions and onSelectSession to ChatMessageDisplay - Add loadedMessageIdsRef to skip animations on session restore - Add debug console.log for diagram processing flow * feat(session): add search bar and improve history UI - Remove session history dropdown, use main panel instead - Add search bar to filter history chats by title - Show minutes (Xm ago) instead of "Just now" for recent sessions - Scroll to top when switching to new/empty chat - Remove title truncation limit for better searchability - Remove debug console.log statements * refactor: remove redundant code and fix nested button hydration error - Remove unused 'sessions' from deleteSession dependency array - Remove unused 'switchedTo' variable and simplify return type - Remove unused 'restoredMessageIdsRef' (always empty) - Fix nested button hydration error by using div with role=button - Simplify handleDeleteSession callback * fix(session): fix migration bug, improve metadata perf, truncate titles - Fix migration retry loop when localStorage has empty array - Use cursor-based iteration for getAllSessionMetadata - Truncate session titles to 100 chars with ellipsis * refactor: remove dead code and extract diagram length constant - Remove unused exports: getAllSessions, createNewSession, updateSessionTitle - Remove write-only CURRENT_SESSION_KEY and all localStorage calls - Remove dead messagesEndRef and unused scroll effect - Extract magic number 300 to MIN_REAL_DIAGRAM_LENGTH constant - Add isRealDiagram() helper function for semantic clarity |
||
|
Dayuan Jiang
|
85cb441e26 |
feat: multi-provider model configuration with UI/UX improvements (#355)
* feat: add multi-provider model configuration - Add model config dialog for managing multiple AI providers - Support for OpenAI, Anthropic, Google, Azure, Bedrock, OpenRouter, DeepSeek, SiliconFlow, Ollama, and AI Gateway - Add model selector dropdown in chat panel header - Add API key validation endpoint - Add custom model ID input with keyboard navigation - Fix hover highlight in Command component - Add suggested models for each provider including latest Claude 4.5 series - Store configuration locally in browser * feat: improve model config UI and move selector to chat input - Move model selector from header to chat input (left of send button) - Add per-model validation status (queued, running, valid, invalid) - Filter model selector to only show verified models - Add editable model IDs in config dialog - Add custom model input field alongside suggested models dropdown - Fix hover states on provider buttons and select triggers - Update OpenAI suggested models with GPT-5 series - Add alert-dialog component for delete confirmation * refactor: revert shadcn component changes, apply hover fix at usage site * feat: add AWS credentials support for Bedrock provider - Add AWS Access Key ID, Secret Access Key, Region fields for Bedrock - Show different credential fields based on provider type - Update validation API to handle Bedrock with AWS credentials - Add region selector with common AWS regions * fix: reset Test button after validation completes * fix: reset validation button to Test after success * fix: complete bedrock support and UI/UX improvements - Add bedrock to ALLOWED_CLIENT_PROVIDERS for client credentials - Pass AWS credentials through full chain (headers → API → provider) - Replace non-existent GPT-5 models with real ones (o1, o3-mini) - Add accessibility: aria-labels, focus-visible rings, inline errors - Add more AWS regions (Ohio, London, Paris, Mumbai, Seoul, São Paulo) - Fix setTimeout cleanup with useRef on component unmount - Fix TypeScript type consistency in getSelectedAIConfig fallback * chore: remove unused code - Remove unused setAccessCodeRequired state in chat-panel.tsx - Remove unused getSelectedModel export in model-config.ts * fix: UI/UX improvements for model configuration dialog - Add gradient header styling with icon badge - Change Configuration section icon from Key to Settings2 - Add duplicate model detection with warning banner and inline removal - Filter out already-added models from suggestions dropdown - Add type-to-confirm for deleting providers with 3+ models - Enhance delete confirmation dialog with warning icon - Improve model selector discoverability (show model name + chevron) - Add truncation for long model names with title tooltip - Remove AI provider settings from Settings dialog (now in Model Config) - Extract ValidationButton into reusable component * fix: prevent duplicate model IDs within same provider - Block adding model if ID already exists in provider - Block editing model ID to match existing model in provider * fix: improve duplicate model ID notifications - Add toast notification when trying to add duplicate model - Allow free typing when editing model ID, validate on blur - Show warning toast instead of blocking input * fix: improve duplicate model validation UX in config dialog - Add inline error display for duplicate model IDs - Show red border on input when error exists - Validate on blur with shake animation for edit errors - Prevent saving empty model names - Clear errors when user starts typing - Simplify error styling (small red text, no heavy chips) |
||
|
Dayuan Jiang
|
869391a029 |
refactor: eliminate code duplication (DRY principle) (#211)
## Problem Solved Previous refactoring added 105 lines (1476→1581) by extracting code into separate files without eliminating duplication. This refactor focuses on reducing code size through deduplication while maintaining file separation for maintainability. ## Summary - Reduced total lines from 1581 to 1519 (-62 lines, 3.9% reduction) - Eliminated duplicate patterns using generic helpers and factory functions - Maintained file structure for maintainability - Zero functional changes - same behavior ### Phase 1: DRY use-quota-manager.tsx - Created parseStorageCount() helper (eliminates 6x localStorage read duplication) - Created createQuotaChecker() factory (consolidates 3 check function bodies) - Created createQuotaIncrementer() factory (consolidates 3 increment function bodies) - Result: 242→247 lines (+5 lines, but fully DRY with eliminated duplication) ### Phase 2: DRY chat-panel.tsx (1176→1109 lines, -67 lines) #### 2.1: Extract checkAllQuotaLimits helper - Replaced 3 occurrences of 18-line quota check blocks - Saved 36 lines #### 2.2: Extract sendChatMessage helper - Replaced 3 occurrences of 21-line sendMessage+headers blocks - Saved 42 lines #### 2.3: Extract processFilesAndAppendContent helper - Replaced 2 occurrences of file processing loops - Handles PDF, text, and image files uniformly - Async helper with optional image parts parameter |