* fix: preserve assistant messages with reasoning_content in sanitize pass
When _sanitize_assistant_messages encounters an assistant message with empty content and no tool_calls but with reasoning_content, keep it with content set to empty string instead of dropping it. Reasoning models (DeepSeek V4, MiMo, etc.) require this history for subsequent turn validation.
* Update astrbot/core/provider/sources/openai_source.py
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
* fix: default to empty TokenUsage when completion.usage is None
When completion.usage is None (e.g. certain proxy/streaming edge cases), llm_response.usage stayed unset (None). Plugins accessing .input_tokens on it would crash with AttributeError.
Always assign llm_response.usage — extract from completion.usage if present, otherwise fall back to a zeroed TokenUsage().
Closes#8605
---------
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: renchonghan <renchonghan@users.noreply.github.com>
* sanitize orphaned tool_result blocks in Anthropic provider
Sanitize tool_result blocks and merge consecutive messages with the same role to comply with Anthropic API requirements.
* Fix content handling in message merging logic
* fix: sanitize anthropic assistant messages
* fix: validate anthropic tool result ordering
---------
Co-authored-by: Soulter <905617992@qq.com>
* fix: reliably kill shell process tree on Windows timeout
Fixes#8809
* fix: remove redundant import and wrap taskkill in try/except
- Remove 'import subprocess as _sp' (subprocess already imported at top)
- Use subprocess.run directly with DEVNULL for stdout/stderr
- Wrap taskkill in try/except to avoid masking original TimeoutExpired
- If taskkill fails, cleanup failures don't prevent proc.wait() or re-raise
https://buymeacoffee.com/muhamedfazalps
* style: apply ruff formatting to local.py
* test: fix shell component tests to match Popen-based implementation
The tests were monkeypatching subprocess.run but the implementation
now uses subprocess.Popen + communicate() for timeout handling.
Updated tests to mock Popen instead.
Fixes CI Unit Tests failure
* fix: harden windows shell timeout cleanup
---------
Co-authored-by: Soulter <905617992@qq.com>
- Add At component handling in _parse_to_qqofficial method
- Convert At(qq=openid) to <@openid> plain_text format
- Maintain original message chain order by appending
- Skip At(qq='all') since QQ Official API may not support it
Closes#8982
- Add ExaWebSearchTool (web_search_exa) with keyword/semantic search,
category filters, domain restrictions, and date range support
- Add ExaGetContentsTool (exa_get_contents) for extracting web page content
- Add _exa_search() and _exa_get_contents() API helpers hitting
https://api.exa.ai/search and https://api.exa.ai/contents
- Add _EXA_KEY_ROTATOR for multi-key rotation
- Register Exa tools in _apply_web_search_tools() dispatch
- Add Exa to WEB_SEARCH_CITATION_TOOL_NAMES for citation support
- Add websearch_exa_key config default and provider option
- Add i18n metadata for en-US, zh-CN, ru-RU
- Add Exa section to docs (en + zh)
- Add 6 unit tests covering search, contents, error handling, and
legacy config migration
Closes#5621
* fix: tool definition does not pass back to gemini properly, causing repeated tool calls.
fixes: #8789fixes: #8773fixes: #7111fixes: #6402fixes: #7684
* fix: remove unnecessary logging and improve log messages in Gemini source
* fix: improve type checking for tool calls in Google Gemini provider
Add QQ Official Bot QR binding registration flow for the WebSocket adapter, wire dashboard credential autofill, and mark the WebSocket template as recommended.
