omni-context-cli 0.0.95 → 0.0.97

package/README.md

@@ -1,17 +1,17 @@
 # OmniContext CLI
 
-A context-first, zero-telemetry coding assistant that extends into VS Code, Office, the browser, and mobile. Supports Anthropic, OpenAI, Gemini, and Responses API plus image generation via Google Imagen and OpenAI Images, with custom workflows, atlas navigation, and cross-session memory.
+A context-first, zero-telemetry coding assistant that extends into VS Code, Office, the browser, and mobile. Supports Anthropic, OpenAI, Gemini, and Responses API, plus chat image generation through Google Imagen, OpenAI Images, and xAI Images, and Image Workshop image/video providers for Google Imagen, OpenAI Images, Google Veo, and xAI, with custom workflows, atlas navigation, and cross-session memory.
 
 ## Context-First Architecture
 
 Every token matters. OmniContext CLI is engineered from the ground up to squeeze maximum value out of every context window.
 
 - **Lean system prompts** - the built-in system prompts are short, focused, and free of boilerplate. Tool descriptions are minimal. Your context budget goes toward actual work, not framework overhead.
-- **Agentic tools** - exploratory tasks (searching code, surveying project structure, previewing files) run as separate agentic tools, optionally on a dedicated agent model. Intermediate tool calls, file contents, and reasoning never enter your main context. You get a concise answer back; the scratch work stays off the books.
+- **Agentic tools** - exploratory tasks (searching code, surveying project structure, previewing files) run as separate agentic tools, optionally on a dedicated auxiliary model. Intermediate tool calls, file contents, and reasoning never enter your main context. You get a concise answer back; the scratch work stays off the books.
 - **Atlas navigation** - code navigation knowledge is stored as lightweight topic-to-file maps, so assistants can jump to the right files before searching from scratch.
-- **Context editing** - as a conversation grows, older rounds accumulate tool call payloads and thinking blocks that are no longer relevant. Context editing automatically compresses these, replacing bulky tool inputs and outputs with compact placeholders and stripping reasoning traces, so the model sees a clean, focused history.
 - **Cross-session memory** - every time a conversation is compacted, the model distills key points and evaluates existing memories. Good insights accumulate weight, stale knowledge decays naturally. When the next session starts, accumulated memories are injected automatically so the assistant knows your preferences and project context from the first message.
 - **Prompt caching** - you choose the cache TTL: 5 minutes for quick iteration, 1 hour for long work sessions. Cache control for Anthropic is applied automatically, so repeated context blocks are served from cache, cutting token usage and cost significantly.
+- **Context editing** - for long, tool-heavy sessions, an advanced setting can compress older tool inputs, tool outputs, and reasoning traces before the next request to reduce token usage while keeping saved history intact.
 
 ## Workflow System
 
@@ -57,20 +57,24 @@ Each LLM API protocol has its own dedicated request builder and stream handler.
 | **Responses API** | OpenAI's Responses API with built-in tool orchestration |
 | **Google Imagen** | Gemini generateContent with image output for image generation |
 | **OpenAI Images** | OpenAI Images API (generations and edits) for image generation |
+| **xAI Images** | xAI image API for chat image generation |
 
-Provider-specific interceptors handle protocol and model-source quirks such as Anthropic next-gen/legacy models, DeepSeek, Responses API adjustments, Gemini legacy models, Kimi, MiniMax, OpenCode Go, generic OpenAI-compatible endpoints, xAI, Zhipu GLM, and Zenmux model routing without compromising the protocol.
+Provider-specific interceptors handle protocol and model-source quirks such as Anthropic next-gen/legacy models, CPA proxy session affinity, DeepSeek, Responses API adjustments, Gemini legacy models, Kimi, MiniMax, OpenCode Go, generic OpenAI-compatible endpoints, xAI, Zhipu GLM, and Zenmux model routing without compromising the protocol.
 
-When an image generation model is configured, workflows that allow the `ImageGen` tool can generate images directly from chat and keep the result as an artifact. For direct image work, Image Workshop opens with `omx --serve --image-workshop` and supports generation, edits with reference images and masks, result sessions, and artifact folder access.
+When an image generation model is configured, workflows that allow the `ImageGen` tool can generate images directly from chat and keep the result as an artifact. For direct image and video work, Image Workshop opens with `omx --serve --image-workshop` and supports generation (including video models), edits with reference images and masks, privacy mode, result sessions, and artifact folder access.
 
 One command to add all models from a provider:
 
 ```bash
 omx --list-providers
 omx --add-provider openrouter --api-key sk-...
+omx --refresh-provider openrouter
 omx --remove-provider openrouter
 ```
 
-Built-in providers: **Zenmux**, **DeepSeek**, **Kimi for Coding**, **MiniMax**, **OpenCode Go**, **OpenRouter**, **Zhipu (GLM)**
+`--refresh-provider` refreshes a provider's model list and reuses its stored API key, so you never need to remove and re-add just to pull in newly released models. Add `--api-key` to swap in a rotated key at the same time.
+
+Built-in providers: **Zenmux**, **Zenmux Expert**, **DeepSeek**, **Kimi for Coding**, **MiniMax**, **OpenCode Go**, **OpenRouter**, **Zhipu (GLM)**
 
 ## Atlas Navigation
 
@@ -98,8 +102,8 @@ Terminal is home base, but OmniContext CLI extends into every tool you use. The
 - **VS Code Extension** - IDE integration with file context, diagnostics, and diff views
 - **Chrome Extension** - sidebar on any webpage for summarization, data extraction, tab control, screenshots, and browser automation
 - **Office Add-in** - AI panel inside Word, Excel, and PowerPoint
-- **Web Client** - browser UI with login support, session rewind, LaTeX, Mermaid diagrams, file attachments, drag-and-drop, memory management, tool approval, and Image Workshop for desktop image generation and editing
-- **Mobile Access** - run `omx --serve --host 0.0.0.0` and connect from your phone
+- **Web Client** - browser UI with login support, session rewind, LaTeX, Mermaid diagrams, file attachments, drag-and-drop, memory management, tool approval, response/work language settings, and Image Workshop for image and video generation and editing
+- **Mobile Access** - run `omx --serve --host 0.0.0.0` and connect from your phone; install the web UI to your home screen as a PWA for a standalone app experience
 
 ## Extensibility
 

package/README.zh-CN.md

@@ -1,17 +1,17 @@
 # OmniContext CLI
 
-上下文优先、零遥测的编程助手，可集成到 VS Code、Office、浏览器和移动端。兼容 Anthropic、OpenAI、Gemini 和 Responses API，并支持通过 Google Imagen 和 OpenAI Images 生成图像，提供自定义工作流、代码地图与跨会话记忆。
+上下文优先、零遥测的编程助手，可集成到 VS Code、Office、浏览器和移动端。兼容 Anthropic、OpenAI、Gemini 和 Responses API，同时支持通过 Google Imagen、OpenAI Images 和 xAI Images 进行聊天图像生成，并在图像工坊中支持 Google Imagen、OpenAI Images、Google Veo 和 xAI 的图像/视频供应商，提供自定义工作流、代码地图与跨会话记忆。
 
 ## 上下文优先架构
 
 每一个 token 都很重要。OmniContext CLI 从底层开始就为最大化利用上下文窗口而设计。
 
 - **精简系统提示词** - 内置提示词短小、聚焦、没有模板废话。工具描述力求精简。你的上下文预算用在实际工作上，而不是框架开销。
-- **智能体式工具** - 探索性任务（搜索代码、勘察项目结构、预览文件）作为独立的智能体式工具运行，也可以单独指定 Agent 模型。中间工具调用、文件内容和推理过程不会进入主上下文。你只拿到一个简洁的结论，中间草稿完全不占空间。
+- **智能体式工具** - 探索性任务（搜索代码、勘察项目结构、预览文件）作为独立的智能体式工具运行，也可以单独指定辅助模型。中间工具调用、文件内容和推理过程不会进入主上下文。你只拿到一个简洁的结论，中间草稿完全不占空间。
 - **代码地图** - 代码导航知识会保存为轻量的主题到文件索引，让助手先跳到关键文件，再决定是否需要继续搜索。
-- **上下文编辑** - 随着对话增长，早期的工具调用负载和思考块变得不再相关。上下文编辑自动压缩这些内容，用紧凑的占位符替换庞大的工具输入输出，剥离推理痕迹，让模型看到干净、聚焦的历史。
 - **跨会话记忆** - 每次对话压缩时，模型自动提炼关键要点并评估已有记忆。好的见解不断积累权重，过时的知识自然衰减。下次会话开始时，积累的记忆自动注入，让助手从第一句话就了解你的偏好和项目背景。
 - **提示词缓存** - 你可以自主选择缓存 TTL：5 分钟适合快速迭代，1 小时适合长时间工作。Anthropic 的缓存控制自动应用，重复的上下文块直接从缓存读取，大幅降低 token 消耗和成本。
+- **上下文编辑** - 随着对话增长，早期的工具调用负载和思考块变得不再相关。上下文编辑自动压缩这些内容，用紧凑的占位符替换庞大的工具输入输出，剥离推理痕迹，让模型看到干净、聚焦的历史。
 
 ## 工作流系统
 
@@ -57,20 +57,24 @@ allowRemoteTools: true
 | **Responses API** | OpenAI 的 Responses API，内置工具编排 |
 | **Google Imagen** | Gemini generateContent 图像输出，用于图像生成 |
 | **OpenAI Images** | OpenAI Images API（生成与编辑），用于图像生成 |
+| **xAI Images** | xAI 图像 API，用于聊天中的图像生成 |
 
-供应商专属拦截器处理协议和模型源差异，例如 Anthropic 新旧模型、DeepSeek、Responses API 调整、Gemini 旧模型、Kimi、MiniMax、OpenCode Go、通用 OpenAI 兼容端点、xAI、Zhipu GLM 和 Zenmux 模型路由，同时不影响协议本身。
+供应商专属拦截器处理协议和模型源差异，例如 Anthropic 新旧模型、CPA 代理会话亲和、DeepSeek、Responses API 调整、Gemini 旧模型、Kimi、MiniMax、OpenCode Go、通用 OpenAI 兼容端点、xAI、Zhipu GLM 和 Zenmux 模型路由，同时不影响协议本身。
 
-配置图像生成模型后，允许 `ImageGen` 工具的工作流可以直接在聊天中生成图像，并把结果保存为生成物。如果要直接处理图像，可以用 `omx --serve --image-workshop` 打开图像工坊，支持生成、基于参考图和蒙版的编辑、结果会话和生成物文件夹访问。
+配置图像生成模型后，允许 `ImageGen` 工具的工作流可以直接在聊天中生成图像，并把结果保存为生成物。如果要直接处理图像和视频，可以用 `omx --serve --image-workshop` 打开图像工坊，支持生成（含视频模型）、基于参考图和蒙版的编辑、隐私模式、结果会话和生成物文件夹访问。
 
 一条命令添加供应商的所有模型：
 
 ```bash
 omx --list-providers
 omx --add-provider openrouter --api-key sk-...
+omx --refresh-provider openrouter
 omx --remove-provider openrouter
 ```
 
-内置供应商：**Zenmux**、**DeepSeek**、**Kimi for Coding**、**MiniMax**、**OpenCode Go**、**OpenRouter**、**Zhipu (GLM)**
+`--refresh-provider` 会刷新供应商的模型列表并复用已保存的 API Key，因此不必为了获取新发布的模型而先删除再重新添加。加上 `--api-key` 可以在刷新的同时替换已轮换的 Key。
+
+内置供应商：**Zenmux**、**Zenmux Expert**、**DeepSeek**、**Kimi for Coding**、**MiniMax**、**OpenCode Go**、**OpenRouter**、**Zhipu (GLM)**
 
 ## 代码地图
 
@@ -98,8 +102,8 @@ Atlas 是面向大型或高频项目的持久代码导航索引。每张地图
 - **VS Code 扩展** - IDE 集成，感知打开文件、诊断信息和 diff 视图
 - **Chrome 扩展** - 任意网页上的侧边栏，支持摘要、数据提取、标签页控制、截图和浏览器自动化
 - **Office 插件** - Word、Excel 和 PowerPoint 内的 AI 面板
-- **Web 客户端** - 浏览器 UI，支持登录、会话回退、LaTeX、Mermaid 图表、文件附件、拖拽、记忆管理、工具审批，以及桌面端图像生成与编辑的图像工坊
-- **移动端访问** - 运行 `omx --serve --host 0.0.0.0` 后从手机连接
+- **Web 客户端** - 浏览器 UI，支持登录、会话回退、LaTeX、Mermaid 图表、文件附件、拖拽、记忆管理、工具审批、回复/工作语言设置，以及用于图像与视频生成和编辑的图像工坊
+- **移动端访问** - 运行 `omx --serve --host 0.0.0.0` 后从手机连接；可将 Web UI 安装到主屏幕作为 PWA，获得独立应用体验
 
 ## 可扩展性