a7e9a7f30c
fix(gemini): ensure extra_content is not empty before processing
2025-11-20 23:30:19 +08:00
afb56cf707
feat: add supports for gemini-3 series thought signature ( #3698 )
...
* feat: add supports for gemini-3 series thought signature
* feat: refactor tools_call_extra_content to use a dictionary for better structure
2025-11-19 18:54:56 +08:00
6849af2bad
refactor: LLM response handling with reasoning content ( #3632 )
...
* refactor: LLM response handling with reasoning content
- Added a `show_reasoning` parameter to `run_agent` to control the display of reasoning content.
- Updated `LLMResponse` to include a `reasoning_content` field for storing reasoning text.
- Modified `WebChatMessageEvent` to handle and send reasoning content in streaming responses.
- Implemented reasoning extraction in various provider sources (e.g., OpenAI, Gemini).
- Updated the chat interface to display reasoning content in a collapsible format.
- Removed the deprecated `thinking_filter` package and its associated logic.
- Updated localization files to include new reasoning-related strings.
* feat: add Groq chat completion provider and associated configurations
* Update astrbot/core/provider/sources/gemini_source.py
Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com>
2025-11-15 18:59:17 +08:00
50144ddcae
refactor: revise LLM message schema and fix the reload logic when using dataclass-based LLM Tool registration ( #3234 )
...
* refactor: llm message schema
* feat: implement MCPTool and local LLM tools with enhanced context handling
* refactor: reorganize imports and enhance docstrings for clarity
* refactor: enhance ContentPart validation and add message pair handling in ConversationManager
* chore: ruff format
* refactor: remove debug print statement from payloads in ProviderOpenAIOfficial
* Update astrbot/core/agent/tool.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* Update astrbot/core/agent/message.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* Update astrbot/core/agent/message.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* Update astrbot/core/agent/tool.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* Update astrbot/core/pipeline/process_stage/method/llm_request.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* Update astrbot/core/agent/message.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* refactor: enhance documentation and import mcp in tool.py; update call method return type
* fix: 修复以数据类的方式注册 tool 时的插件重载机制问题
* refactor: change role attributes to use Literal types for message segments
* fix: add support for 'decorator_handler' method in call_local_llm_tool
* fix: handle None prompt in text_chat method and ensure context is properly formatted
---------
Co-authored-by: LIghtJUNction <lightjunction.me@gmail.com >
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
2025-11-02 18:12:20 +08:00
0b7fc29ac4
style: add ruff lint module of isort and pyupgrade, and some ruff check fix ( #3214 )
...
Co-authored-by: Dt8333 <25431943+Dt8333@users.noreply.github.com >
Co-authored-by: Soulter <905617992@qq.com >
2025-11-01 13:26:19 +08:00
5e9c7cdd91
fix: 当没有填写 api key 时，设置为空字符串 ( #2834 )
...
* fix: 修复空key导致的无法创建Provider对象的问题
* style: format code
* Update astrbot/core/provider/provider.py
Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com>
Co-authored-by: Soulter <905617992@qq.com >
2025-10-12 10:50:01 +08:00
fa53b468fd
fix: ensure function call name and args are not None before processing
2025-09-04 11:18:58 +08:00
388ae49e55
fix: 修复 e.message 为 None 时报错的问题和一些 lint error
2025-09-03 22:25:18 +08:00
29845fcc4c
feat: Gemini添加对LLMResponse的raw_completion支持
2025-08-23 14:14:25 +08:00
2cae941bae
Fix incomplete Gemini streaming responses in chat history ( #2429 )
...
* Initial plan
* Fix incomplete Gemini streaming responses in chat history
Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com >
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com >
Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com >
Co-authored-by: Raven95676 <Raven95676@gmail.com >
2025-08-14 11:56:50 +08:00
5f0d601baa
feat: add support for selecting provider and models in webchat
2025-07-03 10:42:20 +08:00
72702beb0b
chore: clean code
2025-07-02 10:29:10 +08:00
adb0cbc5dd
fix: handle tool_calls_result as list or single object in context query in streaming mode
2025-07-02 10:16:44 +08:00
efef34c01e
style: format code
2025-06-29 16:06:44 +08:00
a55a07c5ff
remove: useless provider init params
2025-06-29 14:43:36 +08:00
94ee8ea297
feat: 支持多轮次工具调用并且存储到数据库
...
移除了 llm tuner 适配器
2025-06-29 14:27:00 +08:00
f77c453843
fix: clean code
2025-06-10 00:20:35 +00:00
7fe1c1ec89
feat: add URL context feature to Gemini model configuration
2025-06-09 04:54:24 +00:00
33b64ddf39
feat: enhance tool selection logic for Gemini model versions
2025-06-09 03:55:59 +00:00
62e70a673a
perf: 优化 Gemini 报错提示
2025-05-17 12:04:36 +08:00
b7d7e0b682
fix: 设置thinking_budget前，先检查是否存在
2025-05-10 09:51:30 +08:00
752d13b1b1
perf: 优化 gemini_source 方法默认参数
2025-05-07 19:04:24 +08:00
f5b3d94d16
fix: 修正thinking_config
2025-05-02 15:36:07 +08:00
85609ea742
feat: 支持Gemini思考设置
2025-05-02 10:49:45 +08:00
a23d5be056
refactor: 减少嵌套条件和重复代码
2025-04-23 12:49:27 +08:00
97a6a1fdc2
feat: 保证第一条消息不为model
2025-04-23 12:20:18 +08:00
c8f567347b
feat: 修改重排序逻辑为合并连续相同类型的消息
2025-04-23 11:52:22 +08:00
f07c54d47c
style: 减少一层 intent
...
Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com >
2025-04-23 00:48:25 +08:00
8d7273924f
fix: Gemini保证偶数索引为用户消息，奇数索引为模型消息
2025-04-22 22:12:03 +08:00
01d52cef74
perf: 支持更多参数
2025-04-20 00:12:14 +08:00
5596565ec4
fix: 若启用Gemini原生工具，构建Content列表时忽略工具调用
2025-04-18 23:36:12 +08:00
e98c3d8393
fix: Gemini保证工具间的互斥
2025-04-18 16:19:36 +08:00
ea8035e854
feat: 添加对Gemini原生搜索功能的支持
2025-04-17 20:36:22 +08:00
1be5b4c7ff
fix: 兼容旧版本google-genai sdk
2025-04-16 00:34:08 +08:00
a0ce0cf18a
fix: 增加更多Gemini不支持多模态输出的情况
2025-04-16 00:11:46 +08:00
43ee943acb
🐛 fix: 多轮函数调用的报错
2025-04-15 10:59:16 +08:00
6986c8d8f7
fix: clean code，处理Gemini流式输出最后一部分概率性为None的情况
2025-04-13 18:34:57 +08:00
fe95506db4
perf: 添加日志过滤器以抑制非文本部分警告信息
2025-04-13 17:50:44 +08:00
310ed76b18
fix: 仅在确实包含图片模态时降级
2025-04-13 17:28:34 +08:00
739f09059e
feat: 为Gemini原生代码执行器提供有限支持
2025-04-13 12:43:25 +08:00
9c29df47bb
fix: 更新流式输出逻辑，禁用图片模态并添加日志警告。
2025-04-13 01:09:42 +08:00
3860634fd2
fix: 修复了多模态输出支持判断问题并对只输出图片的情况进行处理。
2025-04-12 19:15:39 +08:00
44dbe475af
refactor: 拆分方法以提高代码可读性
2025-04-12 00:23:57 +08:00
bd24cf3ea4
feat: 初步完成原生流式请求逻辑
2025-04-11 23:45:30 +08:00
b493a808fe
fix: 处理更多多模态不支持错误
2025-04-11 20:25:20 +08:00
c5e8bc7e20
fix: 修复模型生成内容的重试机制。
2025-04-11 18:55:46 +08:00
1b3963ebea
fix: 更新类型提示，简化代码并修复潜在的空值问题。
2025-04-11 18:07:00 +08:00
2ca95eaa9f
fix: 在设置新key后重新初始化Gemini客户端
2025-04-11 14:42:24 +08:00
0dc5b4cdfc
perf: 增加对RECITATION完成原因的处理，提取内容处理逻辑到独立方法
2025-04-11 12:25:44 +08:00
cc6cd96d8e
fix: 修复潜在的空消息
2025-04-11 11:03:17 +08:00
Soulter