adbb84530a
chore: bump version to 4.5.8
2025-11-17 09:58:02 +08:00
6cf169f4f2
fix: ImageURLPart typo ( #3665 )
...
* 修复新版本更新对不上格式的问题
entities.py生成的格式：{"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,..."}}
ImageURLPart期望的格式：{"type": "image_url", "image_url": "data:image/jpeg;base64,..."}
* Revert "修复新版本更新对不上格式的问题"
This reverts commit 28b4791391piexian@users.noreply.github.com >
Co-authored-by: Dt8333 <lb0016@foxmail.com >
2025-11-17 09:52:31 +08:00
5ab9ea12c0
chore: bump verstion to 4.5.7
2025-11-16 14:01:25 +08:00
fd9cb703db
refactor: update ToolSet initialization to use Pydantic Field and clean up deprecated methods in Context
2025-11-16 12:13:11 +08:00
388c1ab16d
fix: ensure parameter properties are correctly handled in spec_to_func
2025-11-16 11:50:58 +08:00
f867c2a271
feat: enhance parameter type handling in LLM tool registration with JSON schema support ( #3655 )
...
* feat: enhance parameter type handling in LLM tool registration with JSON schema support
* refactor: remove debug print statement from FunctionToolManager
2025-11-16 00:55:40 +08:00
605bb2cb90
refactor: disable debug logging for chunk delta in OpenAI provider
2025-11-15 22:29:06 +08:00
5ea15dde5a
feat: enhance LLM handsoff tool execution with system prompt and run hooks
2025-11-15 22:26:13 +08:00
3ca545c4c7
Merge pull request #3636 from AstrBotDevs/feat/context-llm-capability
...
refactor: better invoke the LLM / Agent capabilities
2025-11-15 21:41:42 +08:00
e200835074
refactor: remove unused Message import and context_model initialization in LLMRequestSubStage
2025-11-15 21:36:54 +08:00
3a90348353
Merge branch 'master' into feat/context-llm-capability
2025-11-15 21:34:54 +08:00
5a11d8f0ee
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 21:31:03 +08:00
824af5eeea
fix: Provider.meta() error ( #3647 )
...
fixes : #3643
2025-11-15 21:30:05 +08:00
08ec787491
fix(core.platform): make DingTalk user-ID compliant with UMO ( #3634 )
2025-11-15 21:30:05 +08:00
b062e83d54
refactor: remove redundant session lock management from message sending logic in RespondStage ( #3645 )
...
fixes : #3644
Co-authored-by: Dt8333 <lb0016@foxmail.com >
2025-11-15 21:30:05 +08:00
17422ba9c3
feat: introduce messages field in agent RunContext
2025-11-15 21:15:20 +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
09c3da64f9
fix: Provider.meta() error ( #3647 )
...
fixes : #3643
2025-11-15 18:01:51 +08:00
2c8470e8ac
fix(core.platform): make DingTalk user-ID compliant with UMO ( #3634 )
2025-11-15 17:31:03 +08:00
c4ea3db73d
refactor: remove redundant session lock management from message sending logic in RespondStage ( #3645 )
...
fixes : #3644
Co-authored-by: Dt8333 <lb0016@foxmail.com >
2025-11-15 16:39:49 +08:00
89e79863f6
fix: ensure image_urls and system_prompt default to empty values in ProviderRequest
2025-11-14 22:45:55 +08:00
d19945009f
refactor: decople the agent impl part and introduce some helper context method to call llm
2025-11-14 19:17:24 +08:00
c77256ee0e
feat: add id field to ProviderMetaData and update provider manager to set provider ID
2025-11-14 12:35:30 +08:00
7d823af627
refactor: update provider metadata handling and enhance ProviderMetaData structure
2025-11-13 19:53:23 +08:00
3957861878
refactor: streamline llm processing logic ( #3607 )
...
* refactor: streamline llm processing logic
* perf: merge-nested-ifs
Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com>
* fix: ruff format
* refactor: remove unnecessary debug logs in FunctionToolExecutor and LLMRequestSubStage
---------
Co-authored-by: sourcery-ai[bot] <58596630+sourcery-ai[bot]@users.noreply.github.com>
2025-11-13 10:08:57 +08:00
6ac43c600e
perf: improve streaming fallback strategy for streaming-unsupported platform ( #3547 )
...
* feat: 修改tool_loop_agent_runner，新增stream_to_general属性。
Co-authored-by: aider (openai/gemini-2.5-flash-preview) <aider@aider.chat >
* refactor: 优化text_chat_stream，直接yield完整信息
Co-authored-by: aider (openai/gemini-2.5-flash-preview) <aider@aider.chat >
* feat(core): ✨ 添加streaming_fallback选项，允许进行流式请求和非流式输出
添加了streaming_fallback配置，默认为false。在PlatformMetadata中新增字段用于标识是否支持真流式输出。在LLMRequest中添加判断是否启用Fallback。
#3431 #2793 #3014
* refactor(core): 将stream_to_general移出toolLoopAgentRunner
* refactor(core.platform): 修改metadata中的属性名称
* fix: update streaming provider settings descriptions and add conditions
* fix: update streaming configuration to use unsupported_streaming_strategy and adjust related logic
* fix: remove support_streaming_message flag from WecomAIBotAdapter registration
* fix: update hint for non-streaming platform handling in configuration
* fix(core.pipeline): Update astrbot/core/pipeline/process_stage/method/llm_request.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
* fix(core.pipeline): Update astrbot/core/pipeline/process_stage/method/llm_request.py
---------
Co-authored-by: aider (openai/gemini-2.5-flash-preview) <aider@aider.chat >
Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com >
Co-authored-by: Soulter <905617992@qq.com >
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
2025-11-12 18:01:20 +08:00
27af9ebb6b
feat: changelog display improvement
...
* feat: 添加旧版本changelog的modal
* style: 调整发布说明对话框的样式，移除背景颜色
2025-11-12 14:54:03 +08:00
b360c8446e
feat: add default model selection chip in provider model selector
2025-11-10 13:04:28 +08:00
6d00717655
feat: add streaming support with toggle in chat interface and adjust layout for mobile
2025-11-09 21:57:30 +08:00
bb5f06498e
perf: refine login page
2025-11-09 20:57:45 +08:00
aca5743ab6
feat: 为部分适配器添加缺失的 send_streaming 方法 ( #3545 )
...
为Wechatpadpro和discord添加缺失的方法。
2025-11-09 16:00:24 +08:00
6903032f7e
fix: improve knowledge base chip display with truncation and styling ( #3582 )
...
fixes : #3546
2025-11-09 15:30:41 +08:00
1ce0ff87bd
feat: supports to add custom headers for openai providers ( #3581 )
...
* feat: OPENAI系支持自定义添加请求头
* chore: add custom headers and extra body to config for zhipu
---------
Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com >
2025-11-09 15:12:52 +08:00
e39d6bae0b
fix: update JSON submission link in plugin publish template
2025-11-09 15:06:40 +08:00
8028e9e9a6
chore: bump version to 4.5.6
2025-11-07 16:20:19 +08:00
817f20ea01
fix: pyproject
2025-11-07 16:18:42 +08:00
ad5579a2f4
chore: bump version to 4.5.5
2025-11-07 15:52:58 +08:00
81a689a79b
fix: typo
2025-11-07 15:41:14 +08:00
1893dd8336
fix: dockefile
2025-11-07 15:41:03 +08:00
021ca8175b
chore: bump version to 4.5.4
2025-11-07 14:28:51 +08:00
39d6207fe1
chore: remove dynamic version
2025-11-07 14:26:56 +08:00
23ce687229
chore: fix dockerfile
2025-11-07 14:23:49 +08:00
3715312fd2
fix: update project description to English ( #3516 )
2025-11-07 01:13:32 +08:00
8196922cac
docs: simplify README
2025-11-06 15:22:43 +08:00
8089ad91da
perf: improve extension market ui
2025-11-06 13:57:46 +08:00
2930cc3fd8
chore: bump version to 4.5.3
2025-11-05 21:21:14 +08:00
0e841a8b25
fix: correct tools dictionary comprehension in get_tool_list method
2025-11-05 21:19:10 +08:00
67fa1611cc
chore: bump version to 4.5.2
2025-11-05 19:02:51 +08:00
91136bb9f7
fix: llm tool register error ( #3493 )
2025-11-05 14:27:37 +08:00
7c050d1adc
feat: add customizable sidebar module ordering ( #3307 )
...
* Initial plan
* Add sidebar customization feature with drag-and-drop support
Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com >
* Add dist/ to .gitignore to exclude build artifacts
Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com >
* Fix memory leak and improve code quality per code review
Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com >
* Fix i18n key format: use dot notation instead of colon notation
Co-authored-by: Soulter <37870767+Soulter@users.noreply.github.com >
* Fix drag-and-drop to empty list issue
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 >
2025-11-04 23:59:45 +08:00
Soulter
piexian
Soulter
Dt8333
RC-CHN
nazo
Raven95676
Copilot