* feat: add Rerank API support for NVIDIA NIM
- Add Rerank API support for NVIDIA NIM
- Add related i18n support in en-US zh-CN
* chore: format code
* fix: replace illegal characters
Replace illegal characters when building request model path.
* fix: refactor client initialization method
* fix: enhance response parsing
* docs: add comment for model_path process
* docs: add russia translation
* feat: update AddNewProvider component to support current provider type and enhance provider icon mapping
---------
Co-authored-by: Soulter <905617992@qq.com>
* 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]"
* feat(provider/vllm_rerank): add configurable rerank_api_suffix option
Add rerank_api_suffix config option to the VLLM Rerank provider so
users can control the API URL path suffix instead of having /v1/rerank
hardcoded.
- Default value is /v1/rerank (preserves existing behavior)
- Users can set it to empty string to disable auto-append
- Handles suffix without leading slash by auto-adding one
- Schema, default config, and i18n metadata all updated
Issue: Fixes#7238
* fix(provider/vllm_rerank): handle null suffix and improve hint descriptions
- Add explicit None check for rerank_api_suffix (fixes HIGH from Gemini)
- Update rerank_api_base hint to describe actual behavior without
mentioning specific provider options (fixes 3x MEDIUM from Gemini)
- Add ru-RU i18n for rerank_api_suffix (fixes P2 from Codex)
Co-authored-by: gemini-code-assist[bot]
Co-authored-by: chatgpt-codex-connector[bot]
---------
Co-authored-by: LehaoLin <linlehao@cuhk.edu.cn>
Gemini 3 models return thinking parts (part.thought=True) alongside the
actual response text. _process_content_parts was including these thinking
parts in the message chain sent to the user, effectively leaking internal
reasoning into the output. On platforms that split long messages (e.g.
aiocqhttp with realtime segmenting), this caused duplicate or triple
replies since the thinking text often mirrors the actual response.
The streaming path already handled this correctly via chunk.text which
skips thinking parts, but the non-streaming path and the final-chunk
processing in streaming both went through _process_content_parts.
Also switch the Gemini 3 model name matching from an exhaustive list to
prefix matching (gemini-3- / gemini-3.) so new variants like gemini-3.1
get proper thinkingLevel config without code changes.
Fixes#7183
Gemini API requires function_response to be a google.protobuf.Struct
(JSON object). When tool results are plain text strings, the API
returns 400 Invalid argument. Detect non-JSON tool content for Gemini
models and wrap it in {"result": content} before sending.
Fixes#7134
* 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>
* fix: support both old and new Bailian Rerank API response formats
The new compatible API (compatible-api/v1/reranks) returns results at
the top level as data.results, while the old API returns them nested
under data.output.results. The parser only checked the old path,
causing qwen3-rerank to always report empty results.
Fixes#7161
* Update astrbot/core/provider/sources/bailian_rerank_source.py
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
---------
Co-authored-by: Ruochen Pan <badbatch0x01@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
entities.py:
- Improve assemble_context return type annotation
- Add explicit type annotations for content_blocks
- Add safety checks for text content extraction
provider.py:
- Improve type annotations throughout
- Clean up code structure
Various source providers:
- Add/improve type annotations in anthropic, azure_tts, gemini, volcengine_tts, etc.
- Improve code quality in whisper and xinference providers
- MCPTool_T must be imported at runtime, not in TYPE_CHECKING
- Add __future__ annotations for forward references
- Fix remaining conflict markers in openai_source.py
- 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
* fix(gsvi_tts): Use the correct calling method (#5638)
Add some configuration items for GSVI
* fix(gsvi_tts): add default value for api_key in provider configuration
* fix(gsvi_tts): Adjust wherever the Authorization header is built to only include it when `self.api_key` is truthy
Delete some comments
* chore: ruff format
---------
Co-authored-by: Soulter <905617992@qq.com>
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
- Add URL param support (?api_url=, ?username=) for shareable config
- Add share link button to server config dialog
- Fix ToolSet API bug: tools.func_list -> tools.list_tools()
- Fix Vue template bugs in CommandTable.vue (orphaned v-else, wrong prop)
- Use master version of InstalledPluginsTab.vue (dev had pre-existing bugs)
BREAKING CHANGE: Uses master version for InstalledPluginsTab.vue
* 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
The dev branch has astrbot/dashboard/dist as a symlink to
../../dashboard/dist, which is valid in the dev workspace but
becomes a broken symlink when cloned to /opt/astrbot for installation.
Fix the maturin build hook to:
- Remove broken symlinks before creating placeholder directories
- Handle symlink vs directory removal in copy_dashboard_dist()
- Always generate placeholder when dashboard build is skipped or fails
* fix(provider): add missing index field to streaming tool_call deltas
- Fix#6661: Streaming tool_call arguments lost when OpenAI-compatible proxy omits index field
- Gemini and some proxies (e.g. Continue) don't include index field in tool_call deltas
- Add default index=0 when missing to prevent ChatCompletionStreamState.handle_chunk() from rejecting chunks
Fixes#6661
* fix(provider): use enumerate for multi-tool-call index assignment
- Use enumerate() to assign correct index based on list position
- Iterate over all choices (not just the first) for completeness
- Addresses review feedback from sourcery-ai and gemini-code-assist
---------
Co-authored-by: Yaohua-Leo <3067173925@qq.com>
Co-authored-by: Soulter <905617992@qq.com>
* fix: auto-append /v1 to embedding_api_base in OpenAI embedding provider (#6855)
When users configure `embedding_api_base` without the `/v1` suffix,
the OpenAI SDK does not auto-complete it, causing request path errors.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix: ensure API base URL for OpenAI embedding ends with /v1 or /v4
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-authored-by: Soulter <905617992@qq.com>
