Feature/multimodal ai upstream - #16
Open
1982167424-art wants to merge 3 commits into
Open
Conversation
添加图片识别、图片生成、视频理解、视频生成功能： - 图片识别：基础描述、物体检测、场景分析、OCR、问答 - 图片生成：文本到图片、多种风格、保存到本地 - 视频理解：流式分析、时间线、关键帧、情感分析、问答 - 视频生成：文本到视频、图片转视频、保存到本地 Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- OpenAI客户端绕过系统代理(trust_env=False)
- requests库下载时禁用代理(proxies={})
- 修复httpx URL解析错误
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- B1: 统一 API base 为 https://api.moonshot.cn/v1（修正 video_understanding 误用的 .ai） - B2: reasoning_effort 对齐 README，仅支持 low/high/max（默认 max） - B3: 将 video_understanding.py 合并进 KimiClient，旧模块改为向后兼容重导出 - 新增 ChatSession：多轮对话并保留完整 thinking history（含 reasoning_content/tool_calls） - 新增 KimiClient.chat() 纯文本对话与流式 reasoning/content 分离 - 新增 test_chat_session.py 离线单测（mock 验证历史保留） - 新增 .gitignore
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
添加了Kimi K3的多模态AI工具，支持：
Test Plan
New Files
kimi_multimodal.py- 核心多模态模块run_tests.py- 自动化测试脚本test_all_features.py- 完整功能测试Bug Fixes