Support multiple API keys per provider with random selection for load
balancing. When AI_MODELS_CONFIG has multiple apiKeyEnv values for
a provider, requests will randomly select one available key.
- Update schema to accept apiKeyEnv as string or string array
- Add random key selection in resolveApiKey()
- Update validation to check at least one key exists
- Add tests for array format support
* fix: enable image support for Kimi K2.5 model
Kimi K2.5 supports image input but was incorrectly blocked by the
supportsImageInput check that excluded all Kimi models without
"vision" in the name. Updated the condition to only exclude the
older K2 model while allowing K2.5.
* fix: improve Kimi K2.5 image support logic and add tests
- Only block kimi-k2 specifically, not all Kimi models
- Add unit test for kimi-k2.5 image support
Replaces the hardcoded API endpoint with a function that retrieves
the correct base path for server model requests. Improves compatibility
with deployments where the API is not served from the root path.
Enables ref forwarding for improved integration with parent components
and libraries that require direct DOM access. Enhances flexibility and
maintainability by switching to a forwardRef implementation.
Previously, Ollama only used the OLLAMA_BASE_URL environment variable.
Now client-provided base URL from settings takes priority, allowing
users to configure custom Ollama endpoints (e.g., remote servers).
Fixes#652
Allows users to select Ollama as a provider from client settings.
Previously, Ollama was blocked with "Invalid provider" error even
though the UI supported it.
Fixes#652
Ollama is a local/self-hosted model that doesn't require API keys.
The SSRF protection was incorrectly blocking Ollama connections
when users provided a custom base URL without an API key.
Fixes#652
Add full Traditional Chinese support for Hong Kong/Taiwan users by
creating a zh-Hant dictionary and registering the locale across the
web app, metadata, and Electron desktop menu system.
This reverts commit e7c29fb410.
The PR introduced an IndexedDB error: 'Failed to execute transaction on IDBDatabase: The database connection is closing.'
* fix(electron): prevent beforeunload prompt by using autosave
- Enable draw.io autosave and handle autosave events to update chartXML
- Clear modified state after autosave to avoid beforeunload prompts
- Disable confirmExit in draw.io configuration
- Set modified=false and keepmodified=false URL parameters
- Fix session save condition to also save when only diagram exists
* fix: persist diagram-only saves and ref typing
* fix: harden persistence checks and export timeout
* feat(prompt): add language-aware response rules with english fallback
Added language handling rules for user interactions.
* refactor(prompt): simplify language matching instruction
* feat(electron): bundle draw.io for offline support
- Download draw.io static files during CI build (v29.3.5)
- Detect Electron and use local draw.io files instead of CDN
- Add offline=1 parameter to disable external service calls
- Skip /drawio path from i18n middleware redirect
- Add public/drawio/ to .gitignore (downloaded during build)
This allows the Electron app to work completely offline.
* chore: bump version to 0.4.12-beta.3 for offline test
* fix(electron): ad-hoc sign macOS app for bundled draw.io compatibility
* chore: bump version to 0.4.12-beta.4 for ad-hoc sign test
* fix(electron): disable electron-builder signing to use custom ad-hoc signing
* chore: bump version to 0.4.12-beta.5
* feat(mcp): update UI with project logo and modern dialog styles
- Replace Next.js logo with project favicon-white.svg
- Modernize modal dialogs with backdrop blur, animations, and DM Sans font
- Update button styles to match header design
- Change title to "Next AI Draw.io"
- Rename "Save" to "Download" for clarity
- Bump version to 0.1.15
* chore: remove dead code (unused download helpers and pendingManualSave)
Fixes#633 - browser showing infinite loading spinner when accessing
the MCP server URL without the session parameter.
When users access http://localhost:6002 directly (without ?mcp=xxx),
the page now auto-redirects to the most recent active session instead
of showing "No session" with an infinite loading spinner.
Upgrade wrangler from 4.58.0 to ^4.60.0 to fix the command injection
vulnerability (CWE-78) in the --commit-hash parameter of wrangler pages
deploy command.
Fixes#627
* enhancement: Add URL format hint to Base URL field (#593)
Add dynamic provider-specific format examples to Base URL field labels to clarify expected URL format. Includes missing defaultBaseUrl values for providers.
* fix: Use generic example URL instead of OpenAI URL for fallback
* [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>
* fix(quota): bypass quota for users with Bedrock credentials
The hasOwnApiKey check only looked for x-ai-api-key header, but Bedrock
users provide AWS credentials via x-aws-access-key-id instead. This
caused Bedrock users with their own credentials to still be subject to
quota limits.
* fix(quota): also bypass quota for Vertex AI users
* style: auto-format with Biome
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
cpSync with dereference:true does NOT convert symlinks to files.
This implements a custom copyDereferenced function that:
- Detects symlinks using lstatSync
- Follows them using statSync
- Copies actual file/directory content instead of symlink
Fixes macOS arm64 codesign failure with electron-builder 26.4.0
which now does ad-hoc signing and runs codesign --verify.
