- Adopt a compact seven-column credential layout with visible quotas, request stats, and actions
- Display cooldown scope, countdowns, and model details with accessible reset controls
- Fix cooldown misassignment when merging same-named credentials from different accounts
- Add client visibility management with search, auto-detection, and persisted preferences
- Integrate plugin OAuth providers with deduplication and change synchronization
- Refine dashboard typography and spacing, and streamline usage history controls
- Add translations, unit tests, and responsive interaction coverage
- Add plugin store, version selection, configuration, and OAuth login
- Support Muse (Meta) OAuth device authorization
- Redesign home dashboard and add batch model health checks
- Support per-credential provider editing, removal, and reordering
- Improve usage charts and track actual response models
- Preserve installed plugins and runtime data during portable rebuilds
- Update translations, documentation, and related tests
- Add grouped token, cache, and latency details
- Tighten column spacing and preserve custom widths
- Move pagination to the footer and add CSV export
- Support dark mode and responsive layouts
Adopt a white theme, add home-page shortcuts, and show usage metrics with color-coded details, automatic units, and explicit estimated-cost coverage. Update the README screenshots.
- Default absent optional config nodes to empty values without hiding other errors
- Normalize empty parent mappings to prevent alias save and rollback conflicts
- Add regression tests for missing config, first-time alias creation, and rollback
- Display credentials in responsive cards with quota progress bars
- Add request statistics and detailed health and cooldown information
- Consolidate nine credential settings into a dialog with partial updates
- Reuse Codex quota reset logic and confirmation across pages
- Move notes above card actions and hide the healthy status indicator
- Add translations and regression coverage
- Add editable model lists, alias suggestions, and usage guidance
- Ignore unselected rows and validate alias conflicts and naming rules
- Fix alias routing through disabled or excluded providers
- Preserve model routes when restoring legacy backups
- Repair legacy metadata and remove unsupported context fields
- Add regression tests for validation and configuration recovery
- Add Devin login to standard and simplified modes
- Support credentials, model aliases, and exclusions
- Display daily and weekly quotas with reset times
- Validate callbacks and prevent stale login updates
- Add translations, theme support, and integration tests
- Move operation feedback into a shared floating stack to prevent layout shifts
- Allow identical errors to reappear after dismissal
- Support keyboard navigation, scrolling, and focus restoration in dialogs
- Add notification interaction regression tests
- Remove code comments throughout the project
- Align TPS and token normalization with Keeper
- Add Redis usage queue batch pulling with HTTP fallback
- Prevent cache and invalid token double counting
- Refresh usage details immediately after new records arrive
- require explicit model discovery before saving DeepSeek connections
- preserve selected models when refreshing the catalog
- mark model lists stale when connection details change
- add model refresh support to easy mode
- apply built-in DeepSeek reasoning levels consistently
- Use Tauri native theme APIs with Linux desktop preference support
- Fall back to WebView theme detection for startup and browser preview
- Add a follow-system option to both standard and beginner modes
- Persist preferences and handle resume events and async race conditions
- Add translations and theme behavior and UI regression tests
- Read context limits from the core catalog and configuration
- Show numeric values with their source instead of automatic placeholders
- Preserve manual overrides and support resetting to inherited values
- Separate default model selection from catalog configuration
- Use API metadata with per-model and provider overrides
- Expose documented capability, reasoning, protocol, and request settings
- Preserve customizations with conflict detection and transactional rollback
- Allow resets when applicable credits are zero or a previous reset failed
- Remove applicable-credit details from the confirmation and obsolete tooltips
- Keep the existing in-app dialog and require explicit confirmation before submitting
- Update regression tests for cancellation, confirmation, and retries
- Merge weekly and monthly billing fields to preserve 100% remaining quota
- Display unknown usage instead of assuming a full balance
- Align paid account health checks and billing failure fallback
- Add localized messages and regression tests
- Resolve context limits from core model definitions, aliases, and configuration
- Preserve user overrides and display context sources and fallback hints
- Refresh defaults from CPA when restoring all model settings
- Keep restore-all available without customizations and remove its icon
- Allow saving restored defaults even when values remain unchanged
- Add regression coverage for context resolution and default restoration
- Remove test buttons from credential and quota pages
- Delete paid probe requests, confirmations, and result feedback
- Clean up related translations and obsolete button hints
- Preserve quota queries and update tests to verify no paid probes occur
- Use consistent in-app dialogs for confirmation actions
- Keep quota refreshes free of prompts and automatic paid probes
- Add a separate confirmation flow for xAI availability tests
- Require explicit approval for Codex resets and prevent duplicate requests
- Show reset outcomes and require a quota refresh before retrying failures
- Cover confirmation and reset flows with fully mocked tests
- Align model management with Management Center by separating model viewing, account exclusions, and provider-wide exclusions
- Read and update excluded_models per credential without affecting other accounts
- Make checked models represent exclusions and support manual wildcard rules
- Limit Select All to candidate models and preserve wildcard and off-list rules when clearing selections
- Allow rule editing when the model list is empty or unavailable, including removal of wildcard bans
- Update translations and add regression coverage for account isolation and rule persistence
- Replace transient toasts with dismissible, accessible inline notices
- Remove redundant success messages for toggles and clipboard actions
- Preserve list focus during background refreshes
- Remove duplicate English captions and localize onboarding content
- Complete Japanese translations and remove English fallback
- Preserve API field names, Token units, and raw reasoning-level values
- Add regression tests for operation feedback and localization
- Update Claude, Codex, Kimi, Antigravity, and xAI compatibility
- Display plan details, subscription expiry, and dynamic reset times
- Deduplicate quota requests and serialize Codex resets
- Require confirmation for potentially billable xAI health probes
- Add quota parsing, request, and rendering regression tests
- Increment the counter on each page visit, check for updates at five, and reset it to zero
- Prevent duplicate counting on re-renders and reset the counter on app restart
- Preserve startup and manual checks while avoiding duplicate requests
- Preserve the saved download source and stop checking automatically when sources change
- Add regression tests for visit counting and check triggers, and update English and Chinese documentation
- Move blocking usage queries and core lifecycle operations to background
workers, limit concurrency, and prevent overlapping core operations
- Coalesce statistics refreshes and consolidate category aggregations,
reducing unfiltered analysis queries from 11 to 4
- Cache bundled model prices, reuse management API connections, and reduce
redundant checks in the usage collector
- Throttle download progress and guide positioning updates, and avoid
redundant renders when core status is unchanged
- Bound and coalesce configuration watcher events, and reuse a single
model catalog refresh worker
- Stop scheduling remaining health checks when the dialog closes and
limit backend health-check concurrency
- Replace overlapping OAuth polling with sequential requests, retry
backoff, timeouts, and stale callback protection
- Add regression tests and a statistics benchmark script, and move
performance verification documentation to agent_docs
- add per-model context, reasoning, modality, visibility, and parallel tool settings
- persist customizations separately and apply them during catalog generation
- support restoring individual or all models to official fallback templates
- expose full fallback reasoning levels while keeping Fast available
- add localized UI, validation, documentation, and regression tests
lzt404