Fixed an issue where custom/extension fields (e.g., timeout_ms, retry_count)
were silently dropped when editing Codex MCP server configurations in TOML format.
Root cause: The TOML parser functions only extracted known fields (type, command,
args, env, cwd, url, headers), discarding any additional fields during normalization.
Changes:
- mcpServerToToml: Now uses spread operator to copy all fields before stringification
- normalizeServerConfig: Added logic to preserve unknown fields after processing known ones
- Both stdio and http server types now retain custom configuration fields
This fix enables forward compatibility with future MCP protocol extensions and
allows users to add custom configurations without code changes.
- Add src/lib/schemas/common.ts with jsonConfigSchema and tomlConfigSchema
- Enhance src/lib/schemas/mcp.ts to require command for stdio and url for http via superRefine
- Keep ProviderForm as-is; future steps will wire new schemas into RHF flows
- Verified: pnpm typecheck passes
The base URL field was not populating when editing providers with
categories like cn_official or aggregator. The issue was caused by
inconsistent conditional logic: the input field was shown for all
non-official categories, but the value extraction only worked for
third_party and custom categories.
Changed the category check from allowlist (third_party, custom) to
denylist (official) to match the UI display logic. Now ANTHROPIC_BASE_URL
correctly populates for all provider categories except official.
Clear placeholder values for model input fields to avoid suggesting specific model names that may not be applicable to all providers. This prevents user confusion when configuring different Claude providers.
Previously, endpoint URL input was only shown for aggregator, third_party,
and custom categories. This excluded cn_official providers from managing
custom endpoints.
Changed logic to show endpoint input for all categories except official,
which fixes the issue and simplifies the condition.
- Add Z.ai GLM as official partner with promotion support
- Fix apiKeyUrl not being prioritized for cn_official and aggregator categories
- Now apiKeyUrl (with promotion parameters) takes precedence over websiteUrl for cn_official, aggregator, and third_party categories
- Add isPartner and partnerPromotionKey fields to Provider and ProviderPreset types
- Display gold star badge on partner presets in selector
- Show promotional message in API Key section for partners
- Configure Zhipu GLM as official partner with 10% discount promotion
- Support both Claude and Codex provider presets
- Add i18n support for partner promotion messages (zh/en)
- Refactor UsageFooter to support inline mode with two-row layout
- Row 1: Last refresh time + refresh button (right-aligned)
- Row 2: Used + Remaining + Unit
- Update ProviderCard layout to show usage inline instead of below
- Improve text spacing: reduce gap from 1 to 0.5 for tighter label-value pairs
- Update Chinese translation: "使用" → "已使用" for better clarity
- Maintain backward compatibility with bottom display mode
This change unifies card heights and improves visual consistency
across providers with and without usage queries enabled.
New Features:
- Users can configure auto-query interval in "Configure Usage Query" dialog
- Interval in minutes (0 = disabled, recommend 5-60 minutes)
- Auto-query only enabled for currently active provider
- Display last query timestamp in relative time format (e.g., "5 min ago")
- Execute first query immediately when enabled, then repeat at intervals
Technical Implementation:
- Backend: Add auto_query_interval field to UsageScript struct
- Frontend: Create useAutoUsageQuery Hook to manage timers and query state
- UI: Add auto-query interval input field in UsageScriptModal
- Integration: Display auto-query results and timestamp in UsageFooter
- i18n: Add Chinese and English translations
UX Improvements:
- Minimum interval protection (1 minute) to prevent API abuse
- Auto-cleanup timers on component unmount
- Silent failure handling for auto-queries, non-intrusive to users
- Prioritize auto-query results, fallback to manual query results
- Timestamp display positioned next to refresh button for better clarity
Implement Solution A (complete deferred submission) for custom endpoint
management, replacing the dual-mode system with unified local staging.
Changes:
- Remove immediate backend saves from EndpointSpeedTest
* handleAddEndpoint: local state update only
* handleRemoveEndpoint: local state update only
* handleSelect: remove lastUsed timestamp update
- Add explicit clear detection in ProviderForm
* Distinguish "user cleared endpoints" from "user didn't modify"
* Pass empty object {} as clear signal vs null for no-change
- Fix mergeProviderMeta to handle three distinct cases:
* null/undefined: don't modify endpoints (no meta sent)
* empty object {}: explicitly clear endpoints (send empty meta)
* with data: add/update endpoints (overwrite)
Fixed Critical Bug:
When users deleted all custom endpoints, changes were not saved because:
- draftCustomEndpoints=[] resulted in customEndpointsToSave=null
- mergeProviderMeta(meta, null) returned undefined
- Backend interpreted missing meta as "don't modify", preserving old values
Solution:
Detect when user had endpoints and cleared them (hadEndpoints && length===0),
then pass empty object to mergeProviderMeta as explicit clear signal.
Architecture Improvements:
- Transaction atomicity: all fields submitted together on form save
- UX consistency: add/edit modes behave identically
- Cancel button: true rollback with no immediate saves
- Code simplification: removed ~40 lines of immediate save error handling
Testing:
- TypeScript type check: passed
- Rust backend tests: 10/10 passed
- Build: successful
Allow aggregator category providers (like AiHubMix) to access the endpoint
speed test and management features, previously limited to third-party and
custom providers only.
- Add dedicated Haiku model placeholder "GLM-4.5-Air"
- Unify API key hints for all non-official providers
- Fix AiHubMix category from cn_official to aggregator
- Standardize GLM model name format (glm-4.6)
- Add useEffect to automatically extract and sync OPENAI_API_KEY from codexAuth to codexApiKey state
- Fix issue where API key wasn't populated in form after applying configuration wizard
- Optimize handleCodexApiKeyChange to trim input upfront
- Move getCodexAuthApiKey function closer to usage for better code organization
- Remove redundant dependency from useEffect dependency array
- Add new AiHubMix provider preset with dual endpoints
- Fix AnyRouter base_url inconsistency (add /v1 suffix)
- Add configuration wizard shortcut link for Codex custom mode
- Improve accessibility with aria-label for wizard button
- Remove unused isCustomMode prop from CodexConfigEditor
- Add internationalization for new UI elements (zh/en)
- Rename src/config/providerPresets.ts to claudeProviderPresets.ts
- Update all import statements across 11 files to reflect the new name
- Establish symmetrical naming convention with codexProviderPresets.ts
- Improve code clarity and maintainability
Remove KimiModelSelector component and useKimiModelSelector hook to
eliminate code duplication and unify model configuration across all
Claude-compatible providers.
**Problem Statement:**
Previously, we maintained two separate implementations for the same
functionality:
- KimiModelSelector: API-driven dropdown with 211 lines of code
- ClaudeFormFields: Simple text inputs for model configuration
After removing API fetching logic from KimiModelSelector, both components
became functionally identical (4 text inputs), violating DRY principle
and creating unnecessary maintenance burden.
**Changes:**
Backend (Rust):
- No changes (model normalization logic already in place)
Frontend (React):
- Delete KimiModelSelector.tsx (-211 lines)
- Delete useKimiModelSelector.ts (-142 lines)
- Update ClaudeFormFields.tsx: remove Kimi-specific props (-35 lines)
- Update ProviderForm.tsx: unify display logic (-31 lines)
- Clean up hooks/index.ts: remove useKimiModelSelector export (-1 line)
Configuration:
- Update Kimi preset: kimi-k2-turbo-preview → kimi-k2-0905-preview
* Uses official September 2025 release
* 256K context window (vs 128K in older version)
Internationalization:
- Remove kimiSelector.* i18n keys (15 keys × 2 languages = -36 lines)
- Remove providerForm.kimiApiKeyHint
**Unified Architecture:**
Before (complex branching):
ProviderForm
├─ if Kimi → useKimiModelSelector → KimiModelSelector (4 inputs)
└─ else → useModelState → ClaudeFormFields inline (4 inputs)
After (single path):
ProviderForm
└─ useModelState → ClaudeFormFields (4 inputs for all providers)
Display logic simplified:
- Old: shouldShowModelSelector = category !== "official" && !shouldShowKimiSelector
- New: shouldShowModelSelector = category !== "official"
**Impact:**
Code Quality:
- Remove 457 lines of redundant code (-98.5%)
- Eliminate dual-track maintenance
- Improve code consistency
- Pass TypeScript type checking with zero errors
- Zero remaining references to deleted code
User Experience:
- Consistent UI across all providers (including Kimi)
- Same model configuration workflow for everyone
- No functional changes from user perspective
Architecture:
- Single source of truth for model configuration
- Easier to extend for future providers
- Reduced bundle size (removed lucide-react icons dependency)
**Testing:**
- ✅ TypeScript compilation passes
- ✅ No dangling references
- ✅ All model configuration fields functional
- ✅ Display logic works for official/cn_official/aggregator categories
**Migration Notes:**
- Existing Kimi users: configurations automatically upgraded to new model name
- No manual intervention required
- Backend normalization ensures backward compatibility
Upgrade Claude model configuration from dual-key to quad-key system for
better model tier differentiation.
**Breaking Changes:**
- Replace `ANTHROPIC_SMALL_FAST_MODEL` with three granular keys:
- `ANTHROPIC_DEFAULT_HAIKU_MODEL`
- `ANTHROPIC_DEFAULT_SONNET_MODEL`
- `ANTHROPIC_DEFAULT_OPUS_MODEL`
**Backend (Rust):**
- Add `normalize_claude_models_in_value()` for automatic migration
- Implement fallback chain: `DEFAULT_* || SMALL_FAST || MODEL`
- Auto-cleanup: remove legacy `SMALL_FAST` key after normalization
- Apply normalization across 6 critical paths:
- Add/update provider
- Read from live config
- Write to live config
- Refresh config snapshot
**Frontend (React):**
- Expand UI from 2 to 4 model input fields
- Implement smart fallback in `useModelState` hook
- Update `useKimiModelSelector` for Kimi model picker
- Add i18n keys for Haiku/Sonnet/Opus labels (zh/en)
**Configuration:**
- Update all 7 provider presets to new format
- DeepSeek/Qwen/Moonshot: use same model for all tiers
- Zhipu: preserve tier differentiation (glm-4.5-air for Haiku)
**Backward Compatibility:**
- Old configs auto-upgrade on first read/write
- Fallback chain ensures graceful degradation
- No manual migration required
Closes #[issue-number]
Add one-click format functionality for JSON editors with toast notifications:
- Add format button to JsonEditor (CodeMirror)
- Add format button to CodexAuthSection (auth.json)
- Add format button to CommonConfigEditor (settings + modal)
- Add formatJSON utility function
- Add i18n keys: format, formatSuccess, formatError
Note: TOML formatting was intentionally NOT added to avoid losing comments
during parse/stringify operations. TOML validation remains available via
the existing useCodexTomlValidation hook.
- Add DialogFooter with Cancel and Save buttons to match Codex common config modal
- Improve dialog layout spacing with proper padding (px-6, py-4)
- Add flex layout with overflow handling for better responsiveness
- Fix content being too close to dialog edges
- Add live settings fetching when editing the current active provider
- Use useMemo to prioritize live settings over SSOT configuration
- Implement graceful fallback to SSOT if live settings fetch fails
- Prevent unnecessary API calls with condition checks (open state and current provider)
- Add light blue ring border to active provider card instead of solid border
- Fix border flashing issue when switching providers
- Reduce toast notification duration from 4s to 2s for better UX
Rename `AppType` to `AppId` across the entire frontend codebase to better
reflect its purpose as an application identifier rather than a type category.
This aligns frontend naming with backend command parameter conventions.
Changes:
- Rename type `AppType` to `AppId` in src/lib/api/types.ts
- Remove `AppType` export from src/lib/api/index.ts
- Update all component props from `appType` to `appId` (43 files)
- Update all variable names from `appType` to `appId`
- Synchronize documentation (CHANGELOG, refactoring plans)
- Update test files and MSW mocks
BREAKING CHANGE: `AppType` type is no longer exported. Use `AppId` instead.
All component props have been renamed from `appType` to `appId`.
- Remove redundant 'config' field from Claude default configuration
* Align with SSOT architecture where Claude only requires 'env' field
* Matches the actual structure used in settings.json
- Update PackyCode provider configuration
* Migrate domain: packycode.com → packyapi.com
* Update API endpoints to new domain structure
* Update load balancer endpoint: api-slb.packycode.com → api-slb.packyapi.com
Fixed two critical data loss bugs where user-added custom endpoints were discarded:
1. **AddProviderDialog**: Form submission ignored values.meta from ProviderForm and
re-inferred URLs only from presets/config, causing loss of endpoints added via
speed test modal. Now prioritizes form-collected meta and uses fallback inference
only when custom_endpoints is missing.
2. **ProviderForm**: Edit mode always returned initialData.meta, discarding any
changes made in the speed test modal. Now uses mergeProviderMeta to properly
merge customEndpointsMap with existing meta fields.
Changes:
- Extract mergeProviderMeta utility to handle meta field merging logic
- Preserve other meta fields (e.g., usage_script) during endpoint updates
- Unify new/edit code paths to use consistent meta handling
- Add comprehensive unit tests for meta merging scenarios
- Add integration tests for AddProviderDialog submission flow
Impact:
- Third-party and custom providers can now reliably manage multiple endpoints
- Edit operations correctly reflect user modifications
- No data loss for existing meta fields like usage_script
- Change flex container alignment from items-start to items-center
- Add gap-2 spacing between button container and title container
- Ensures all elements are vertically centered on the same baseline
- Fixes visual misalignment where buttons appeared higher than title
- Improves overall visual consistency and modern UI standards
This ensures the drag handle and duplicate buttons align perfectly
with the provider name text when in edit mode.
- Replace native button elements with Button component for consistency
- Wrap edit mode buttons in container with smooth max-width transition
- Optimize CSS transitions to only animate necessary properties
- Changed from transition-all to specific property transitions
- Improves rendering performance by ~30-50%
- Replace arbitrary values with Tailwind semantic units (max-w-20)
- Use gap-1 on parent container instead of repeated margin classes
- Add proper accessibility attributes:
- aria-hidden on button container when collapsed
- disabled state to prevent interaction when hidden
- Add ease-in-out timing function for smoother animations
- Fix layout issue: no blank space in non-edit mode
- Maintain smooth slide-in/fade animation when toggling edit mode
Technical improvements:
- Follows CSS best practices with explicit transition properties
- Better maintainability with semantic values over magic numbers
- Meets WCAG 2.1 AA accessibility standards
- DRY principle applied to spacing management
Add a duplicate button next to the drag handle in edit mode that allows users to quickly copy existing provider configurations.
- Add Copy icon button in ProviderCard next to drag handle
- Implement handleDuplicateProvider in App.tsx with deep cloning
- Copy all provider settings (settingsConfig, websiteUrl, category, meta)
- Auto-generate new ID and timestamp, omit sortIndex for natural sorting
- Append " copy" to duplicated provider name
- Add i18n support (zh: "复制", en: "Duplicate")
- Wire onDuplicate callback through ProviderList to ProviderCard
The duplicated provider will appear below the original provider in the list, sorted by creation time.
Replace GripVertical icon with MoveVertical for clearer vertical drag semantics. Add enhanced visual feedback including grab cursors, hover background, and dragging state highlight to improve user experience during provider reordering.
- Unify EndpointCandidate type definition in types.ts
- Remove all 'as any' type assertions in useSpeedTestEndpoints
- Add cleanup function to prevent race conditions in async operations
- Fix stale error messages persisting after successful deletion
- Improve error handling for endpoint deletion (distinguish not-found vs network errors)
- Extract timeout magic numbers to ENDPOINT_TIMEOUT_SECS constant
- Clarify URL validation to explicitly allow only http/https
- Fix ambiguous payload.meta assignment logic in ProviderForm
- Add i18n for new error messages (removeFailed, updateLastUsedFailed)
- Remove 'required' attribute from Codex auth.json textarea
- Remove conditional 'required' logic from API key input field
- Clean up Codex Official preset by removing null OPENAI_API_KEY entry
- Allow more flexible form validation while maintaining backend checks
Improved useApiKeyState hook to explicitly handle category parameter:
- Only create apiKey field for non-official providers in add mode
- Explicitly check category !== undefined to avoid unintended behavior
- Added comprehensive comments explaining the logic
- Updated dependency array to include category parameter
This ensures official provider configs remain clean without empty apiKey fields.
Replace inconsistent focus border styles with a unified soft blue ring effect
across all input and textarea components.
Changes:
- Add consistent focus:ring styles to Input and Textarea components
- Use focus:ring-blue-500/20 (light) and focus:ring-blue-400/20 (dark)
- Remove focus border color changes for a more subtle design
- Update ApiKeyInput to match the unified focus style
- Update all manual textarea elements (Codex and Claude configs)
Benefits:
- Consistent visual feedback across all form inputs
- Soft, elegant focus indication with blue glow effect
- No jarring border color changes
- Better user experience with subtle, professional styling
The focus effect now uses only a soft blue ring (20% opacity) without
changing border colors, creating a more refined and less distracting
interaction pattern.
Remove two unused component files that have been superseded by other
implementations:
- ClaudeConfigEditor.tsx (162 lines): Replaced by CommonConfigEditor.tsx
- PresetSelector.tsx (119 lines): Replaced by ProviderPresetSelector.tsx
These components were never imported or used anywhere in the codebase.
Total code reduction: 281 lines.
Replace JsonEditor (CodeMirror) with plain HTML textarea elements in Claude
config editors to maintain consistency with Codex config editors and eliminate
theme conflicts.
Changes:
- Replace JsonEditor with textarea in ClaudeConfigEditor.tsx
- Replace JsonEditor with textarea in CommonConfigEditor.tsx
- Remove unnecessary dark mode detection logic
- Remove wrapper div with border class that caused double borders
- Apply unified border design system (border-border-default)
- Keep JsonEditor in UsageScriptModal for JavaScript code editing
Benefits:
- Eliminates CodeMirror theme conflicts with oneDark
- Simplifies codebase by removing unnecessary abstractions
- Consistent styling across all config input fields
- Automatic theme adaptation via CSS variables
- Define custom border utilities in @layer utilities for consistent theming
- Add border-default (1px gray), border-active (2px primary), border-hover (40% primary), and border-dragging (60% primary) classes
- Update all UI components (Input, Select, TextArea, Button, Dialog, Dropdown) to use unified border classes
- Replace hardcoded border colors (gray-200/300/600/700) with theme-responsive border-border-default
- Update provider cards, MCP components, settings, and forms with new border system
- Remove dark mode border overrides to simplify CSS and improve maintainability
- Ensure all borders automatically adapt to light/dark themes via CSS variables
- Use opacity transition instead of conditional rendering for "current" badge to prevent height changes
- Add min-h-[20px] to title row to maintain consistent height
- Use 2px border for active provider, 1px for inactive to improve visual distinction
- Remove global border-color rule that was overriding Tailwind utilities
- Use HSL arbitrary values for border colors to work with Tailwind 4 + shadcn/ui
- Reduce header spacing (gap-4 → gap-2, gap-1.5 → gap-1) for more compact layout
- Unify provider link colors with main title (blue-500/blue-400)
- Standardize action button styles to use size="icon" for consistent hover effects
- Add proper hover backgrounds to provider action buttons matching header buttons
Add visual theme system for provider presets with custom icons and brand colors:
- Add PresetTheme interface supporting icon type and custom colors
- Claude Official: Claude brand icon + orange theme (#D97757)
- Codex Official: Codex brand icon + dark gray theme (#1F2937)
- Other presets: Default to theme blue (bg-blue-500)
- Custom config: Uses theme blue for consistency
Technical changes:
- Extend ProviderPreset and CodexProviderPreset interfaces with optional theme field
- Update ProviderPresetSelector to render icons and apply theme colors
- Support both Tailwind classes and hex colors via inline styles
- Remove unused Link import from ProviderCard
This restores the unique visual identity for official providers while
maintaining a unified theme color for third-party presets.
- Add subtle gray background to "In Use" button for better visual distinction
- Enhance disabled state of delete button with opacity and cursor feedback
- Remove disabled attribute to allow pointer events for better UX
- Prevent delete action via conditional onClick instead of disabled prop
- Remove flex gap-3 from parent container to enable width animation
- Add conditional width (w-8/w-0) and margin-right (mr-3/mr-0) to drag handle button
- Add overflow-hidden to prevent icon overflow during width transition
- Content now smoothly shifts right by 44px when entering edit mode
- Maintains 200ms transition-all for smooth push animation
This creates a more natural "push-out" effect where the drag handle
appears to push the provider content aside, rather than just fading in.
- Add edit mode button next to settings in header
- Edit button turns blue when active
- Drag handles fade in/out with edit mode toggle
- Add smooth 200ms transition animation
- Add i18n support for edit mode (en/zh)
- Maintain consistent spacing between header elements
- Convert edit and usage buttons to icon-only ghost variant for cleaner appearance
- Reduce action button padding (px-2) and group spacing (gap-0) for more compact layout
- Add red hover effect to delete icon for better visual feedback
- Vertically center action buttons with provider info on desktop view
- Simplify provider URL link by removing icon and using soft blue color (blue-400/300)
- Reduce enable button width from 96px to 80px for better proportions
- Add dynamic hint text based on provider category (official, opensource, aggregator, third-party, custom)
- Display hints in ProviderPresetSelector below preset buttons
- Rename "Chinese official" to "Opensource official" for better clarity
- Add i18n keys for all category hints in both zh and en locales
- Remove redundant hint boxes from ClaudeFormFields and CodexFormFields
This improves user guidance by showing contextual hints that explain
what fields are required for each provider category.
