omni-context-cli 0.0.96 → 0.0.98

package/README.md

@@ -1,13 +1,13 @@
 # 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 chat image generation and Image Workshop image/video providers, 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.
 - **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.
@@ -25,7 +25,7 @@ A workflow controls everything about how OmniContext CLI behaves: the system pro
 | **Memory** | Key point management | Browse, edit, and clean up cross-session key points stored in the project memory. |
 | **Recall** | Session search | Search and review past chat sessions for decisions, context, and discussion history. |
 
-The desktop app also installs a **Browser** workflow for the Chrome sidebar (tab, page content, bookmark, history, screenshot, and script execution access), a **Memo** workflow for personal reminders and notifications (with Apple Reminders sync on macOS), and a **Research** workflow for PDF-heavy study and analysis (PDF split, chunk reading, preview, and web search).
+The desktop app also installs a **Browser** workflow for the Chrome sidebar (tab, page content, bookmark, history, screenshot, and script execution access) and a **Research** workflow for PDF-heavy study and analysis (PDF split, chunk reading, preview, and web search). It also includes a memo and reminder system with Apple Reminders sync on macOS.
 
 Create your own by dropping a markdown file in `~/.omx/workflows/` or `.omx/workflows/`. Each workflow is a markdown file with YAML frontmatter that defines the tool set and a body that becomes the system prompt:
 
@@ -58,6 +58,8 @@ Each LLM API protocol has its own dedicated request builder and stream handler.
 | **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 |
+| **Google Veo** | Vertex AI long-running video generation for Image Workshop |
+| **xAI Videos** | xAI video generation API for Image Workshop |
 
 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.
 
@@ -68,9 +70,12 @@ 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
 ```
 
+`--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
@@ -108,7 +113,7 @@ Custom workflows, agents, skills, hooks, external tools, MCP servers, and remote
 
 - **Custom Workflows** - define your own system prompt and control exactly which tools are available: base tools, agents, MCP servers, and remote tools.
 - **Custom Agentic Tools** - write a markdown file with a prompt template, parameter schema, and tool permissions. It becomes a callable agentic tool instantly. Add `AGENTS.md` for agent-specific instructions, or fall back to `OMX.md` project instructions automatically.
-- **Custom Skills** - directory-based prompt capabilities invoked as slash commands (`/skill-name`). Skills inject instructions into the current conversation for domain-specific knowledge and workflows. Compatible with Claude Code skill format.
+- **Custom Skills** - directory-based prompt capabilities invoked as slash commands (`/skill-name`). Skills inject instructions into the current conversation for domain-specific knowledge and workflows. Skill arguments are natural-language text, so work-language translation applies to them while structured local command arguments stay unchanged. Compatible with Claude Code skill format.
 - **Model Prompts** - add markdown files with frontmatter in `~/.omx/model-prompts/` or `.omx/model-prompts/` to append extra system prompt text for matching model names.
 - **External Tools** - drop JavaScript or ESM tool modules into `~/.omx/tools/` or `.omx/tools/` and they are registered alongside built-in tools.
 - **MCP Servers** - connect external tools and data sources via Model Context Protocol. Stdio and HTTP transports supported.

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，同时支持聊天图像生成以及图像工坊的图像/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、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
 
@@ -25,7 +25,7 @@
 | **Memory** | 要点管理 | 浏览、编辑和清理项目记忆中的跨会话关键要点。 |
 | **Recall** | 会话搜索 | 搜索和回顾过去的聊天会话，查找决策、上下文和讨论历史。 |
 
-桌面应用还会安装 **Browser** 工作流供 Chrome 侧边栏使用（标签页、页面内容、书签、历史记录、截图和脚本执行）、**Memo** 工作流用于个人提醒和通知（macOS 上支持 Apple Reminders 同步），以及 **Research** 工作流用于 PDF 密集型研究和分析（PDF 拆分、分块阅读、预览和网页搜索）。
+桌面应用还会安装 **Browser** 工作流供 Chrome 侧边栏使用（标签页、页面内容、书签、历史记录、截图和脚本执行），以及 **Research** 工作流用于 PDF 密集型研究和分析（PDF 拆分、分块阅读、预览和网页搜索）。它也内置备忘录与提醒系统，macOS 上支持 Apple Reminders 同步。
 
 在 `~/.omx/workflows/` 或 `.omx/workflows/` 中放一个 Markdown 文件即可创建自定义工作流。每个工作流是一个带 YAML frontmatter 的 Markdown 文件，frontmatter 定义工具集，正文成为系统提示词：
 
@@ -58,6 +58,8 @@ allowRemoteTools: true
 | **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 |
+| **Google Veo** | 用于图像工坊的 Vertex AI 长轮询视频生成 |
+| **xAI Videos** | 用于图像工坊的 xAI 视频生成 API |
 
 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。
 
@@ -68,9 +70,12 @@ allowRemoteTools: true
 ```bash
 omx --list-providers
 omx --add-provider openrouter --api-key sk-...
+omx --refresh-provider openrouter
 omx --remove-provider openrouter
 ```
 
+`--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
@@ -108,7 +113,7 @@ Atlas 是面向大型或高频项目的持久代码导航索引。每张地图
 
 - **自定义工作流** - 定义自己的系统提示词，精确控制可用工具列表：基础工具、Agent、MCP 服务器和远程工具。
 - **智能体式工具** - 写一个带提示词模板、参数定义和工具权限的 Markdown 文件，立刻成为可调用的智能体式工具。添加 `AGENTS.md` 作为 Agent 专属指令，未找到时自动回退到 `OMX.md` 项目指令。
-- **自定义技能** - 基于目录的提示词能力，通过斜杠命令（`/技能名`）调用。技能注入当前对话，提供领域知识和工作流。兼容 Claude Code 技能格式。
+- **自定义技能** - 基于目录的提示词能力，通过斜杠命令（`/技能名`）调用。技能注入当前对话，提供领域知识和工作流。技能参数会作为自然语言文本处理，因此工作语言翻译会作用于技能参数，但结构化的本地命令参数会保持不变。兼容 Claude Code 技能格式。
 - **模型提示词** - 在 `~/.omx/model-prompts/` 或 `.omx/model-prompts/` 中添加带 frontmatter 的 Markdown 文件，即可为匹配的模型名称追加额外系统提示词。
 - **外部工具** - 把 JavaScript 或 ESM 工具模块放到 `~/.omx/tools/` 或 `.omx/tools/`，即可和内置工具一起注册。
 - **MCP 服务器** - 通过 Model Context Protocol 接入外部工具和数据源，支持 stdio 和 HTTP 传输。