* feat: add audio input support across providers and chatui recording issue fix
- Introduced audio_urls parameter in Provider class and related methods to handle audio input.
- Updated ProviderAnthropic, ProviderGoogleGenAI, and ProviderOpenAIOfficial to process audio URLs.
- Enhanced media_utils with functions to ensure audio format compatibility and detect audio types.
- Modified dashboard components to display audio input support and handle audio attachments in messages.
- Updated localization files to include audio as a supported modality.
- Added new icons for audio input in the dashboard UI.
* feat: enhance audio handling with temporary file cleanup and format support
* feat: track temporary local files for converted audio components
* fix: update image placeholder in prompt from "[图片]" to "[Image]"
* fix: 改进 KnowledgeBaseManager 和 KBHelper 中的初始化错误处理
* fix: 改进知识库初始化和重排序错误处理，增强日志记录
* fix: 改进知识库模块初始化和检索错误处理
* fix(ui): handle kb init errors in list cards
display a dedicated error state for knowledge base cards that fail
initialization, including a visible badge and error details
prevent navigation and edit actions for failed cards while keeping
delete available, and hide normal stats/description for error items
add list.initError locale strings for en-US, ru-RU, and zh-CN
* fix(kb): avoid replacing helper on init failure
Initialize a new KB helper before swapping instances so a failed re-init
does not break the active knowledge base service.
If initialization fails, restore in-memory KB settings and keep the
existing helper and previous init error state.
Also clear stale init_error after successful vector DB initialization to
prevent outdated error reporting.
* test(kb): add kb manager resilience tests
cover initialization failure and recovery scenarios to guard
against regressions in kb error handling
include reference assets under refs for test validation
---------
Co-authored-by: RC-CHN <1051989940@qq.com>
* fix: filter empty assistant messages to prevent 400 error on strict APIs
Some OpenAI-compatible APIs (e.g., Moonshot) reject requests with
empty content in assistant messages when no tool_calls are present.
This fix cleans up the messages payload before sending to avoid
'message at position X must not be empty' errors.
Closes related issue with fallback provider behavior.
* test(openai): add tests for empty assistant message filtering
* refactor(openai): simplify empty assistant message filtering logic
* style: format code
---------
Co-authored-by: RC-CHN <1051989940@qq.com>
* feat: add new StatsPage for enhanced statistics overview
- Introduced StatsPage.vue to provide a comprehensive overview of statistics with various metrics and charts.
- Implemented fetching and displaying of base and model provider statistics.
- Added unit tests for provider statistics persistence in the database.
* style: refine card styles and remove unnecessary shadow for improved aesthetics
- fix(openai_source): remove dead code comment
- fix(common.ts): use resolveApiUrl helper for live-log endpoint
- style(mdi-subset): clean up icon CSS
- feat: add translation check script and unit tests
Resolved conflicts:
- openai_source.py: keep dev version with abort_signal filtering
- customizer.ts: keep dev version with viewMode functionality
- useSessions.ts: keep dev version with pendingSessionId handling
- platformUtils.js: keep dev version with correct tutorial links
- AddNewPlatform.vue: keep dev version with correct docs link
- FullLayout.vue: keep dev version with viewMode-based logic
- VerticalHeader.vue: keep dev version with viewMode-based logic
`abort_signal` (asyncio.Event) is passed via **kwargs into payloads during
tool_call streaming, causing "Object of type Event is not JSON serializable"
when the OpenAI client tries to serialize the request body.
Regression test added: test_prepare_chat_payload_strips_non_json_serializable_kwargs
* feat: add two-phase startup lifecycle
Allow the dashboard to become available before plugin bootstrap completes and surface runtime readiness and failure states to API callers.
Guard plugin-facing endpoints until runtime is ready and clean up provider and plugin runtime state safely across bootstrap failures, retries, stop, and restart flows.
* fix: harden runtime cleanup review fixes
Continue terminating remaining providers and disable MCP servers even if one provider terminate hook fails.
Also add InitialLoader failure-path coverage and extract guarded plugin routes into a shared constant for easier review and maintenance.
* fix: harden deferred startup recovery
* fix: streamline runtime guard handling
* fix: simplify runtime lifecycle coordination
* fix: restore orchestrator logger binding
- Add _message_count and _last_activity_timestamp to orchestrator
- Add record_activity() method to orchestrator
- Add name field to get_protocol_status returns
- Add total_messages and last_activity to get_stats
- Update tests to verify new fields
- Fix echo_mcp_server.py stdio parsing (use stdin.buffer, not readline)
- Mark MCP handshake tests as skip (protocol requires server notifications)
- Update test_list_stars to account for auto-registered RuntimeStatusStar
- Fix orchestrator to use anyio.get_cancelled_exc_class() instead of anyio.CancelledError
- Fix tests to properly check for anyio compliance (not violations)
- Add type annotations for MCP exception fallbacks in registry.py
- Remove unused type: ignore comment in mcp/tool.py
- All 111 tests pass
- uvx ty check passes
- ruff check passes
