* fix: faster message restore and skip panel animation on refresh
- Use useLayoutEffect for localStorage restore (runs before paint)
- Track visibility changes to only animate panel when toggling, not on page load
- Use cn() utility for cleaner conditional className
* fix: reset animation state after completion for re-animation support
* revert: remove unnecessary animation reset timer
- Add isRestored state to track when localStorage restoration completes
- Show example panel only after confirming no saved messages exist
- Skip message animations for restored messages
- Default tool calls and reasoning blocks to collapsed for restored messages
- Update biome schema version from 2.3.8 to 2.3.10
- Add radix parameter to parseInt in mcp-server
- Remove unnecessary React fragment in model-config-dialog
- Fix unused variable errors (err -> _err)
- Auto-format code with biome
* fix(mcp-server): add graceful shutdown to prevent zombie processes
Add lifecycle handlers to properly exit the MCP server when the parent
application closes:
- Listen for stdin close/end events (primary method for all platforms)
- Handle SIGINT/SIGTERM signals
- Handle stdout broken pipe errors
- Export shutdown() function from http-server to clean up resources
* chore(mcp-server): bump version to 0.1.11
Some models (Kimi K2, DeepSeek, Qwen text models) don't support image/vision
input. The AI SDK silently drops unsupported image parts, causing confusing
responses where the model acts as if no image was uploaded.
Added supportsImageInput() function to detect unsupported models by name,
and return a 400 error with clear guidance when users try to upload images
to these models.
Closes#469
* docs: reorganize docs into en/cn/ja folders
- Move documentation files into language-specific folders (en, cn, ja)
- Add Chinese and Japanese translations for all docs
- Extract Docker section from README to separate doc file
- Update README to link to new doc locations
* docs: fix links to new docs folder structure
* docs: update README and provider docs
* docs: fix broken import statements in cloudflare deploy guides
* docs: sync CN/JA READMEs with EN structure and fix all paths
- Remove About link and sponsor notice icon from chat panel header
- Remove language switcher (English | 中文 | 日本語) from all about pages
- Fix About link in settings dialog to use current language
- Remove unused sponsorTooltip translation key from all dictionaries
* fix(edit_diagram): implement cascade delete for children and edges
- Add automatic cascade deletion when deleting a cell
- Recursively delete all child cells (parent attribute references)
- Delete all edges referencing deleted cells (source/target)
- Skip silently if cell already deleted (handles AI redundant ops)
- Update prompts to inform AI about cascade behavior
Fixes#450
* fix: add root cell protection and sync MCP server cascade delete
- Add protection for root cells '0' and '1' to prevent full diagram wipe
- Sync MCP server with main app's cascade delete logic
- Both lib/utils.ts and packages/mcp-server now have identical delete behavior
* chore(mcp): bump version to 0.1.9
* fix(cascade-delete): recursively collect edge children (labels)
- Change from cellsToDelete.add(edgeId) to collectDescendants(edgeId)
- Fixes orphaned edge labels causing draw.io to crash/clear canvas
- Edge labels (parent=edgeId) are now deleted with their parent edge
* chore: clean up root folder by moving config files
- Move renovate.json to .github/renovate.json
- Move electron-builder.yml to electron/electron-builder.yml
- Move electron.d.ts to electron/electron.d.ts
- Delete proxy.ts (unused dead code)
- Update package.json dist scripts with --config flag
- Use tsconfig.json files array for electron.d.ts (bypasses exclude)
Reduces git-tracked root files from 23 to 19.
* chore: regenerate package-lock.json to fix CI
* fix: regenerate package-lock.json with cross-platform deps
- Add 'Use Your API Key' button to open model config dialog
- Add ByteDance Doubao sponsorship message with registration link
- Update quota limit messages to be warmer and friendlier
- Add dev panel button to test quota toast
- Update i18n translations for EN, ZH, JA
* feat: add doubao provider and ByteDance sponsorship
- Add doubao provider using DeepSeek SDK with Volcengine base URL
- Add ByteDance Doubao sponsorship acknowledgment to about pages
- Update all README files (EN/CN/JA) with K2-thinking model info
- Update ai-providers.md with doubao configuration
- Keep both gateway and doubao providers after merge
* style: auto-format with Biome
* feat: add doubao and sglang to provider config panel
* fix: add doubao and sglang to validate-model API and logo maps
* docs: update ByteDance sponsorship note in all README versions
* docs: add Doubao logo to sponsorship note
* fix: use raw GitHub URL for Doubao logo in READMEs
* fix: separate link and image in sponsorship note
* fix: use PNG instead of SVG for Doubao logo
* fix: use current branch for PNG URL (will update to main after merge)
* docs: reorganize Deployment section and update image URLs to main
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
- Change from single key (PK only) to composite key (PK + SK)
- PK = user ID, SK = date for per-day history tracking
- Remove two-step daily reset logic (SK handles day separation)
- Rename dailyReqCount/dailyTokenCount to reqCount/tokenCount
- Remove TTL (data never expires per user request)
- Simplify checkAndIncrementRequest to single atomic update
- Fix recordTokenUsage to handle new items explicitly
New table: next-ai-drawio-quota-v2
- Use head.sha instead of head_ref for checkout (works for forks)
- For fork PRs: fail with helpful message if formatting needed
- For same-repo PRs: auto-commit and push as before
* chore: bump version to 0.4.7
* style: auto-format with Biome
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
- Use fixed port 61337 in production instead of random ports (10000-65535)
- localStorage is origin-specific, so random ports caused settings loss
- Add locale save/restore since language is URL-based
- Fixes#399
- Button now shows 'Test' by default instead of persisting 'Verified' state
- Verified status is still shown via green badge in provider header
- Updated OpenAI suggested models list with latest GPT-5.x series
- Add warning banner to settings window HTML
- Add CSS styling for deprecation notice (light/dark mode)
- Direct users to use AI Model Configuration button in chat panel
Fixes#374 - Models were confused by the `type` field name and sent
`operation` instead. This change:
- Renames DiagramOperation.type to DiagramOperation.operation across
all files (MCP server, web app, hooks, components, system prompts)
- Adds JSON examples in tool descriptions to show correct format
- Updates all test data to use the new field name
Affected files:
- lib/utils.ts
- app/api/chat/route.ts
- hooks/use-diagram-tool-handlers.ts
- components/chat-message-display.tsx
- lib/system-prompts.ts
- packages/mcp-server/src/diagram-operations.ts
- packages/mcp-server/src/index.ts
- scripts/test-diagram-operations.mjs
MCP server version bumped to 0.1.6
* fix: use full IP for userId to prevent quota collision
- Remove .slice(0, 8) from base64 encoded IP
- Each IP now has unique userId (no /16 collision)
- Affects: quota tracking, Langfuse tracing
* refactor: extract getUserIdFromRequest to shared utility
- Create lib/user-id.ts with shared function
- Fix misleading 'privacy' comment (base64 is not privacy)
- Remove duplicate code from chat and log-feedback routes
Switch from blocklist to whitelist approach - only export spans named
'chat' or starting with 'ai.' to filter out Next.js infrastructure noise
(HEAD, fetch, POST requests).
- Fixed bug where daily quota counts weren't resetting on new day
(if_not_exists only works for missing attributes, not day changes)
- Changed to two-phase approach: reset if new day, then increment
- Added QUOTA_TIMEZONE env var for local midnight reset (e.g., Asia/Tokyo)
- Added timezone validation with UTC fallback
- Move DEV_XML_PRESETS constants to new file
- Create DevXmlSimulator component with all simulator logic
- Add preset dropdown with 5 test cases including HTML escape test
- Set default interval to 1ms and chunk size to 10 chars
- Simplify chat-panel.tsx by removing ~130 lines of inline code
- Add HTML escaping (<, >) in convertToLegalXml for attribute values
- Update isMxCellXmlComplete to handle any LLM provider's wrapper tags
- Add wrapper tag stripping in wrapWithMxFile for DeepSeek/Anthropic tags
- Update autoFixXml to escape both < and > in attribute values
Fixes 'Malformed XML detected in final output' error when AI generates
diagrams with HTML content in value attributes like <b>Title</b>.
- Add CSS design system tokens (surfaces, borders, animations) to globals.css
- Update dialog.tsx with rounded-2xl, shadow-dialog, refined close button
- Enhance input.tsx with rounded-xl and refined focus states
- Refactor settings-dialog with SettingItem pattern and consistent control sizing
- Refactor model-config-dialog with ConfigSection/ConfigCard helpers
- Replace emerald-* classes with success design tokens
- Remove unused ValidationButton component and scrollState
- Parse JSON error response from server to get actual used/limit values
- Previously showed 0/0 due to race condition (config fetch vs error)
- AI SDK puts full response body in error.message for non-OK responses
- Updated all quota toasts (request, token, TPM) to use server values
Third-party OpenAI-compatible proxies typically don't support the
/responses endpoint. Use .chat() for custom baseURLs while keeping
Responses API for official OpenAI to preserve reasoning model support.
Fixes#377
- Add extractCompleteMxCells() to extract only complete mxCell elements from partial XML
- Remove useEffect cleanup that was killing debounce timeouts on every re-render
- Wrap XML in <root> tags for proper DOMParser validation
Previously, diagrams only rendered after ALL XML finished streaming because:
1. useEffect cleanup cleared the 150ms debounce timeout on every message change
2. DOMParser rejected partial XML like '<mxCell id="2" value="...' (incomplete)
Now each complete mxCell renders progressively as it finishes streaming.
- Add dynamo-quota-manager.ts for atomic quota checks using ConditionExpression
- Enforce daily request limit, daily token limit, and TPM limit
- Return 429 with quota details (type, used, limit) when exceeded
- Quota is opt-in: only enabled when DYNAMODB_QUOTA_TABLE env var is set
- Remove client-side quota enforcement (server is now source of truth)
- Simplify use-quota-manager.tsx to only display toasts
- Add @aws-sdk/client-dynamodb dependency
Previously, continuation mode (for truncated XML) had unlimited client-side
retries, relying only on server stepCountIs(5) limit. This could cause
excessive API calls (495 observed) when XML truncation kept occurring.
Added MAX_CONTINUATION_RETRY_COUNT=2 to limit continuation attempts:
- After 2 failed continuation attempts, shows error toast and stops
- Resets on successful completion or user-initiated message
- Also resets when quota limits are hit
In multi-step tool flows, messages array contains assistant messages
from previous steps. Using messages[messages.length - 1] would record
the assistant's response as trace input instead of the user's question.
- Use Responses API instead of Chat Completions API for OpenAI
(.chat() -> default call) to support reasoning events
- Add o4 to reasoning model detection
- Change default reasoningSummary from 'detailed' to 'auto'
(not all models support 'detailed')
- Update types to match AI SDK: 'auto' | 'detailed'
- Upgrade ai package from ^5.0.89 to ^6.0.1
- Upgrade @ai-sdk/* provider packages to latest v3/v4
- Update convertToModelMessages call to async (new API)
- Fix usage.cachedInputTokens to usage.inputTokenDetails?.cacheReadTokens
- Add ~40 new translation keys for model-config-dialog and model-selector
- Support English, Chinese, and Japanese translations
- Replace all hardcoded strings with dictionary lookups
* chore: bump version to 0.4.6
* style: auto-format with Biome
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
* 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)
* chore: bump version to 0.4.5 and add desktop app to README
* style: auto-format with Biome
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
* fix(mcp): sync browser state before get_diagram to prevent data loss
- Add syncRequested flag to SessionState for browser sync coordination
- Add requestSync() and waitForSync() functions to http-server
- Browser polls for syncRequested flag and immediately pushes current state
- get_diagram now syncs fresh state from browser before returning
- edit_diagram requires get_diagram to be called within 30s to prevent stale edits
- Updated edit_diagram description to enforce workflow
* fix(mcp): make lastGetDiagramTime session-scoped and handle missing session in requestSync
- Move lastGetDiagramTime into currentSession object to prevent cross-session issues
- requestSync now returns boolean indicating if request was made
- Only wait for sync if session exists (avoids false-positive from undefined state)
* chore: bump version to 0.4.4
* style: auto-format with Biome
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
* feat(mcp): add XML validation and auto-fix to MCP server
- Add xml-validation.ts with validateAndFixXml function
- Integrate validation into display_diagram tool (fails if unfixable)
- Integrate validation into edit_diagram tool (auto-fix each operation)
- Fix bug: typo fixes now run before foreign tag removal
- Fix bug: use before/after comparison instead of regex .test()
* style: auto-format with Biome
* chore(mcp): bump version to 0.1.3
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
* feat: add get_shape_library tool for AI icon discovery
- Add server-side tool that returns shape library documentation
- AI can fetch icon/shape names on-demand before generating diagrams
- Includes path traversal protection and input sanitization
- Library index embedded in tool description for discoverability
- Supports 33 libraries: AWS, Azure, GCP, Kubernetes, Cisco, etc.
* fix: improve get_shape_library error handling and imports
- Move fs/path imports to top of file (avoid dynamic imports per call)
- Distinguish file-not-found vs other errors in catch block
- Include invalid input in validation error message
- Log unexpected errors for debugging
* docs: add get_shape_library to system prompt tool list
- Add Tool4 (get_shape_library) to available tools section
- Add usage guidance in 'Choose the right tool' section
- Update AWS icons note to reference get_shape_library for icon discovery
* fix: display get_shape_library tool output in chat UI
* fix: correct state check for get_shape_library output display
* fix: make get_shape_library output respect fold state
* style: auto-format with Biome
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
- Add showSaveDialog state to DiagramContext for shared state
- Add mouse tracking to only respond to save events when mouse is over draw.io panel
- Prevents save dialog from opening when clicking Send in chat panel
- Add DialogDescription to SaveDialog for accessibility
- Lift showSaveDialog state to DiagramContext for sharing between components
- Add onSave handler to DrawIoEmbed that opens the save dialog
- Add guard (isSavingRef) with 1s delay to prevent repeated save events from draw.io
- Add deprecation notice to custom download button tooltip
Closes#93, Closes#290
* feat: add MCP server package for npx distribution
- Self-contained MCP server with embedded HTTP server
- Real-time browser preview via draw.io iframe
- Tools: start_session, display_diagram, edit_diagram, get_diagram, export_diagram
- Port retry limit (6002-6020) and session TTL cleanup (1 hour)
- Published as @next-ai-drawio/mcp-server on npm
* chore: bump version to 0.1.2
* docs: add MCP server section to README (preview feature)
* docs: add multi-client installation instructions for MCP server
* fix: exclude packages from Next.js build
* docs: use @latest instead of -y flag for npx (match Playwright MCP style)
* chore: bump version to 0.4.3 and add release notes
* chore: remove release notes
* feat: add MCP server notice to example panel
* refactor: replace text-based edit_diagram with ID-based operations
- Add applyDiagramOperations() function using DOMParser for ID lookup
- New schema: operations array with type (update/add/delete), cell_id, new_xml
- Update chat-panel.tsx handler for new operations format
- Update OperationsDisplay component to show operation type and cell_id
- Simplify system prompts with new ID-based examples
- Add ID validation for add operations
- Add warning for edges referencing deleted cells
* fix: add ID validation to update operation and remove dead code
- Add ID mismatch validation to update operation (consistency with add)
- Remove orphaned replaceXMLParts function (~300 lines of dead code)
- Update cell_id schema description for clarity
- Add unit tests for applyDiagramOperations (11 tests)
The hasValidDiagramXml filter was deleting valid messages that had minor
XML issues. Error handling in handleDisplayChart now catches all errors,
so filtering is no longer needed - invalid XML just won't load the diagram
but the conversation is preserved.
When LLM generates invalid XML, the app previously saved corrupted messages
to localStorage, causing an unrecoverable crash loop on restart.
This fix validates messages when restoring from localStorage and filters out
any with invalid diagram XML. Users see a toast notification when corrupted
messages are removed.
Fixes#240
* feat: add minimal style mode toggle for faster diagram generation
- Add Minimal/Styled toggle switch in chat input UI
- When enabled, removes color/style instructions from system prompt
- Faster generation with plain black/white diagrams
- Improves XML auto-fix: handle foreign tags, extra closing tags, trailing garbage
- Fix isMxCellXmlComplete to strip Anthropic function-calling wrappers
- Add debug logging for truncation detection diagnosis
* fix: prevent false XML parse errors during streaming
- Escape unescaped & characters in convertToLegalXml() before DOMParser validation
- Only log console.error for final output, not during streaming updates
- Prevents Next.js dev mode error overlay from showing for expected streaming states
* refactor: simplify LLM XML format to output bare mxCells only
- Update wrapWithMxFile() to always add root cells (id=0, id=1) automatically
- LLM now generates only mxCell elements starting from id=2 (no wrapper tags)
- Update system prompts and tool descriptions with new format instructions
- Update cached responses to remove root cells and wrapper tags
- Update truncation detection to check for complete mxCell endings
- Update documentation in xml_guide.md
* fix: address PR review issues for XML format refactor
- Fix critical bug: inconsistent truncation check using old </root> pattern
- Fix stale error message referencing </root> tag
- Add isMxCellXmlComplete() helper for consistent truncation detection
- Improve regex patterns to handle any attribute order in root cells
- Update wrapWithMxFile JSDoc to document root cell removal behavior
* fix: handle non-self-closing root cells in wrapWithMxFile regex
* feat: add append_diagram tool for truncation continuation
When LLM output hits maxOutputTokens mid-generation, instead of
failing with an error loop, the system now:
1. Detects truncation (missing </root> in XML)
2. Stores partial XML and tells LLM to use new append_diagram tool
3. LLM continues generating from where it stopped
4. Fragments are accumulated until XML is complete
5. Server limits to 5 steps via stepCountIs(5)
Key changes:
- Add append_diagram tool definition in route.ts
- Add append_diagram handler in chat-panel.tsx
- Track continuation mode separately from error mode
- Continuation mode has unlimited retries (not counted against limit)
- Error mode still limited to MAX_AUTO_RETRY_COUNT (1)
- Update system prompts to document append_diagram tool
* fix: show friendly message and yellow badge for truncated output
- Add yellow 'Truncated' badge in UI instead of red 'Error' when XML is incomplete
- Show friendly error message for toolUse.input is invalid errors
- Built on top of append_diagram continuation feature
* refactor: remove debug logs and simplify truncation state
- Remove all debug console.log statements
- Remove isContinuationModeRef, derive from partialXmlRef.current.length > 0
* docs: fix append_diagram instructions for consistency
- Change 'Do NOT include' to 'Do NOT start with' (clearer intent)
- Add <mxCell id="0"> to prohibited start patterns
- Change 'closing tags </root></mxGraphModel>' to just '</root>' (wrapWithMxFile handles the rest)
* fix: handle malformed XML from DeepSeek gracefully
Add early XML validation with parsererror check before calling
replaceNodes to prevent application crashes when AI models
generate malformed XML with unescaped special characters.
Changes:
- Add toast import from sonner
- Parse and validate XML before processing
- Add parsererror detection to catch malformed XML early
- Wrap replaceNodes in try-catch for additional safety
- Add user-friendly toast notifications for all error cases
- Change console.log to console.error for validation failures
Fixes#220#230#231
* fix: prevent toast spam during streaming and merge silent failure fixes
- Only show error toasts after streaming completes (not during partial updates)
- Track which tool calls have shown errors to prevent duplicate toasts
- Merge clipboard copy error handling from PR #236
- Merge feedback submission error handling from PR #237
- Add comments explaining streaming vs completion behavior
* refactor: simplify toast deduplication with boolean flag
Based on code review feedback, simplified the approach from tracking
per-tool-call IDs in a Set to using a single boolean flag.
Changes:
- Replaced Set<string> with boolean ref for toast tracking
- Removed toolCallId and showToast parameters from handleDisplayChart
- Reset flag when streaming starts (simpler mental model)
- Same behavior: one toast per streaming session, no spam
Benefits:
- Fewer concepts (1 boolean vs Set + 2 parameters)
- No manual coordination between call sites
- Easier to understand and maintain
- ~15 fewer lines of tracking logic
* fix: only show toast for final malformed XML, not during streaming
- Remove errorToastShownRef tracking (no longer needed)
- Add showToast parameter to handleDisplayChart (default false)
- Pass false during streaming (XML may be incomplete)
- Pass true at completion (show toast if final XML is malformed)
- Simpler and more explicit error handling
When feedback submission to the API fails, revert the optimistic
UI update and show a toast notification to inform the user.
Changes:
- Add toast import from sonner
- Change console.warn to console.error for proper logging
- Add toast.error() notification when API call fails
- Revert optimistic UI update by removing feedback from state
Previously, feedback submission failures were completely silent.
Users would see the thumbs-up/down visual feedback but their
feedback was never recorded. This creates a false sense that
the feedback was successfully submitted.
Now users are immediately notified when submission fails and
can retry their feedback.
Add toast notification when clipboard copy operation fails,
so users know when their copy attempt was unsuccessful.
Changes:
- Add toast import from sonner
- Add toast.error() notification when clipboard copy fails
- Show clear message: "Failed to copy message. Please copy
manually or check clipboard permissions."
Previously, clipboard copy failures were only indicated by a
brief visual state change (setCopyFailedMessageId), which users
might miss. Now users receive persistent feedback when copy
operations fail.
* fix: improve Azure provider auto-detection and validation (#223)
- Fix detectProvider() to only detect Azure when it has complete config
(both AZURE_API_KEY and AZURE_RESOURCE_NAME or AZURE_BASE_URL)
- Add validation in validateProviderCredentials() for Azure to provide
clear error messages when configuration is incomplete
- Update docs/ai-providers.md to clarify Azure requires resource name
* docs: add Azure reasoning options to documentation
- Add MAX_AUTO_RETRY_COUNT (3) to prevent infinite retry loops
- Check token and TPM limits before each auto-retry
- Reset retry counter on user-initiated messages
- Show toast notification when limits are reached
Fixes issue where models returning invalid tool inputs caused 45+ API
requests due to sendAutomaticallyWhen having no retry limit or quota check.
Some models (e.g. minimax) copy placeholder text instead of generating
fresh XML, causing tool call validation failures and infinite loops.
Added ENABLE_HISTORY_XML_REPLACE env var (default: false) to control
this behavior.
Added full content of the Chain-of-Thought Prompting paper by Wei et al. from Google Research. This example file demonstrates how chain-of-thought reasoning improves LLM performance on complex reasoning tasks.
Add NEXT_PUBLIC_MAX_EXTRACTED_CHARS environment variable to allow
configuring the maximum characters extracted from PDF and text files.
Defaults to 150000 (150k chars) if not set.
Previously AZURE_RESOURCE_NAME was documented in env.example but not
actually used in the code. This caused Azure OpenAI configuration to fail
when users set AZURE_RESOURCE_NAME instead of AZURE_BASE_URL.
Changes:
- Read AZURE_RESOURCE_NAME from environment and pass to createAzure()
- resourceName constructs endpoint: https://{name}.openai.azure.com/openai/v1
- baseURL takes precedence over resourceName when both are set
- Updated env.example with clearer documentation
Fixes#208
Dayuan Jiang