omni-context-cli 0.0.83 → 0.0.85

package/README.md

@@ -7,30 +7,33 @@ A context-first, zero-telemetry coding assistant that extends into VS Code, Offi
 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 agentic tools on a cheaper 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 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.
 - **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.
 
 ## Workflow System
 
-A workflow controls everything about how OmniContext CLI behaves: the system prompt, which tools are available, and how the assistant interacts with you. Two workflows ship built-in:
+A workflow controls everything about how OmniContext CLI behaves: the system prompt, which tools are available, and how the assistant interacts with you. Four workflows ship built-in:
 
 | Preset | Use Case | Description |
 |--------|----------|-------------|
 | **Programming** (default) | Terminal, VS Code | Coding assistant with base tools, agent tools, and MCP integration. Concise output, minimal overhead. |
 | **General** | Office, desktop | Personal assistant for documents, spreadsheets, and presentations. Proactive with tools, conversational tone. |
+| **Analytics** | Usage analysis | Query the local request analytics database to explore token usage, costs, latency, and model comparison. |
+| **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, with tab, page content, bookmark, history, and screenshot access.
+The desktop app also installs a **Browser** workflow for the Chrome sidebar, with tab, page content, bookmark, history, screenshot, and script execution access. It also installs a **Memo** workflow for reminders and notifications.
 
 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:
 
 ```markdown
 ---
 name: My Workflow
-allowBaseTools: true
+allowBuiltinTools: true
+allowExternalTools: true
 allowBuiltinAgents: true
-allowCustomAgents: true
+allowExternalAgents: true
 allowMcpTools: true
 allowRemoteTools: true
 ---
@@ -38,11 +41,11 @@ Your system prompt here. Template variables like {{OS_TYPE}},
 {{PLATFORM}}, {{ARCH}}, {{CWD}}, and {{TODAY}} are available.
 ```
 
-Switch workflows at startup with `omx --workflow my-workflow` or set a default in `omx.json`.
+Switch workflows at startup with `omx --workflow my-workflow` or save a default in OmniContext CLI's app config.
 
 ## Native Multi-Protocol
 
-Each LLM API protocol has its own dedicated request builder and stream handler. Prompt caching, extended thinking, structured outputs, and every other provider-specific feature work exactly as the vendor designed them. There is no translation layer. Anthropic requests are not converted into OpenAI format or vice versa.
+Each LLM API protocol has its own dedicated request builder and stream handler. Prompt caching, extended thinking, function calling, and other provider-specific features work in their native protocol shape. There is no translation layer. Anthropic requests are not converted into OpenAI format or vice versa.
 
 | Protocol | Description |
 |----------|-------------|
@@ -61,7 +64,7 @@ omx --add-provider openrouter --api-key sk-...
 omx --remove-provider openrouter
 ```
 
-Built-in providers: **Zenmux**, **DeepSeek**, **Kimi for Coding**, **OpenRouter**, **Zhipu (GLM)**, **MiniMax**
+Built-in providers: **Zenmux**, **DeepSeek**, **Kimi for Coding**, **MiniMax**, **OpenCode Go**, **OpenRouter**, **Zhipu (GLM)**
 
 ## Cross-Session Memory
 
@@ -73,7 +76,7 @@ Memory extraction runs automatically when a conversation is compacted. The model
 | Neutral | -1 |
 | Harmful | -6 |
 
-Points that drop below -10 are pruned. This means good insights accumulate weight over multiple sessions while bad advice is flushed quickly and stale knowledge decays on its own. Every project maintains its own memory file at `.omx/memory.json`. Edit it directly for full control.
+Points that drop below -10 are pruned. This means good insights accumulate weight over multiple sessions while bad advice is flushed quickly and stale knowledge decays on its own. Every project keeps its memory in `~/.omx/projects/<project-id>/memory.json`. Edit it directly for full control.
 
 ## Desktop & Integrations
 
@@ -83,7 +86,7 @@ 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, and browser automation
 - **Office Add-in** - AI panel inside Word, Excel, and PowerPoint
-- **Zed Editor** - external agent via Agent Client Protocol with full tool access
+- **ACP Clients** - external agent integration via Agent Client Protocol over stdio
 - **Web Client** - browser UI with LaTeX, Mermaid diagrams, file attachments, and drag-and-drop
 - **Mobile Access** - run `omx --serve` and connect from your phone
 

package/README.zh-CN.md

@@ -7,30 +7,33 @@
 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）由智能体式工具在更便宜的模型上运行。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 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。 
 - **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。
 
 ## 工作流系统
 
-工作流控制 OmniContext CLI 行为的方方面面：系统提示词、可用工具列表、助手交互方式。内置两套工作流：
+工作流控制 OmniContext CLI 行为的方方面面：系统提示词、可用工具列表、助手交互方式。内置四套工作流：
 
 | 预设 | 使用场景 | 说明 |
 |------|----------|------|
 | **Programming**（默认） | 终端、VS Code | 编程助手，包含基础工具、Agent 工具和 MCP 集成。简洁输出，最小开销。 |
 | **General** | Office、桌面端 | 多功能个人助理，处理文档、表格和演示文稿。主动使用工具，匹配对话语气。 |
+| **Analytics** | 使用分析 | 查询本地请求分析数据库，探索 token 用量、成本、延迟和模型对比。 |
+| **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，可访问标签页、页面内容、书签、历史记录和截图。
+桌面应用还会安装 **Browser** 工作流供 Chrome 侧边栏使用，可访问标签页、页面内容、书签、历史记录、截图和脚本执行能力。它也会安装 **Memo** 工作流用于提醒和通知。
 
 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：
 
 ```markdown
 ---
 name: My Workflow
-allowBaseTools: true
+allowBuiltinTools: true
+allowExternalTools: true
 allowBuiltinAgents: true
-allowCustomAgents: true
+allowExternalAgents: true
 allowMcpTools: true
 allowRemoteTools: true
 ---
@@ -38,11 +41,11 @@ allowRemoteTools: true
 {{PLATFORM}}、{{ARCH}}、{{CWD}} 和 {{TODAY}}。
 ```
 
-启动时用 `omx --workflow my-workflow` 切换工作流，或在 `omx.json` 中设置默认值。
+启动时用 `omx --workflow my-workflow` 切换工作流，也可以把默认值保存到 OmniContext CLI 的应用配置中。
 
 ## 原生多协议
 
-每种 LLM API 协议都有专用的请求构建器和流处理器。提示词缓存、扩展思考、结构化输出和每一个供应商专属特性都按原厂设计工作。没有转换层，不会把 Anthropic 请求转成 OpenAI 格式，也不会反过来。
+每种 LLM API 协议都有专用的请求构建器和流处理器。提示词缓存、扩展思考、函数调用和其他供应商专属特性都按原生协议工作。没有转换层，不会把 Anthropic 请求转成 OpenAI 格式，也不会反过来。
 
 | 协议 | 说明 |
 |------|------|
@@ -61,7 +64,7 @@ omx --add-provider openrouter --api-key sk-...
 omx --remove-provider openrouter
 ```
 
-内置供应商：**Zenmux**、**DeepSeek**、**Kimi for Coding**、**OpenRouter**、**Zhipu (GLM)**、**MiniMax**
+内置供应商：**Zenmux**、**DeepSeek**、**Kimi for Coding**、**MiniMax**、**OpenCode Go**、**OpenRouter**、**Zhipu (GLM)**
 
 ## 跨会话记忆
 
@@ -73,7 +76,7 @@ omx --remove-provider openrouter
 | 中性 | -1 |
 | 有害 | -6 |
 
-评分低于 -10 的要点被剪枝。好的见解在多次会话中不断积累权重，坏的建议很快被清除，过时的知识自然衰减。每个项目在 `.omx/memory.json` 中维护自己的记忆文件，想要完全控制可以直接编辑。
+评分低于 -10 的要点被剪枝。好的见解在多次会话中不断积累权重，坏的建议很快被清除，过时的知识自然衰减。每个项目都会把记忆存放在 `~/.omx/projects/<project-id>/memory.json` 里，想要完全控制可以直接编辑。
 
 ## 桌面版与集成
 
@@ -83,7 +86,7 @@ omx --remove-provider openrouter
 - **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、数据提取和浏览器自动化
 - **Office 插件** - Word、Excel 和 PowerPoint 内的 AI 面板
-- **Zed 编辑器** - 通过 Agent Client Protocol 作为外部代理接入
+- **ACP 客户端** - 通过 Agent Client Protocol over stdio 作为外部代理接入
 - **Web 客户端** - 浏览器 UI，支持 LaTeX、Mermaid 图表、文件附件和拖拽
 - **移动端访问** - 运行 `omx --serve` 后从手机连接
 

package/dist/agents/deduce.md

@@ -0,0 +1,47 @@
+---
+name: Deduce
+description: Work through a bug or complex question using read-only exploration. Spends multiple rounds tracing code and evidence, returns root cause and fix proposal. Does not modify files.
+inheritContext: true
+displayFields: [question]
+parameters:
+  properties:
+    question:
+      type: string
+      description: The bug, symptom, or question to investigate. Be specific about what is happening and what is expected to happen.
+    hints:
+      type: string
+      description: Optional known clues, such as stack traces, recent changes, or files where the issue likely lives.
+  required: [question]
+---
+
+Investigate this question: {{question}}
+
+{{#if hints}}Known hints: {{hints}}.{{/if}}
+
+Do not modify any files. Bash is allowed for read-only commands like ls, cat, git log, git diff, git blame.
+
+Spend multiple rounds reading, searching, and tracing. Form hypotheses, gather evidence, rule out alternatives, and land on a root cause. Cite file:line for every claim. If something cannot be proven, say where the trail went cold.
+
+Return the results in this format:
+
+```
+Question: Restate what was investigated.
+
+Evidence:
+- Finding with file:line
+- Finding with file:line
+
+Root Cause:
+One or two sentences stating what is actually going on, backed by the evidence above.
+
+Fix Proposal:
+- Concrete change at file:line
+- Side effects to watch for
+
+Open Questions:
+- What still needs user input or runtime verification.
+```
+
+If the investigation is inconclusive, say so and list what would be needed to finish it.
+
+Do not include explanations beyond the result format. Keep responses concise and structured.

package/dist/agents/explore.md

@@ -1,7 +1,7 @@
 ---
 name: Explore
 description: Get a high-level overview of how a project or directory is organized. Use this to understand what exists and where things live, not to answer specific code questions.
-allowBaseTools: [Read, Glob, Grep, Bash, BashOutput]
+allowBuiltinTools: [Read, Glob, Grep, Bash, BashOutput]
 displayFields: [directory]
 parameters:
   properties:

package/dist/agents/glance.md

@@ -1,7 +1,7 @@
 ---
 name: Glance
 description: Preview multiple files at once. Reads files and directories, returns a brief summary for each file to help understand what's in them without reading the full contents.
-allowBaseTools: [Read, Glob, Grep, Bash, BashOutput]
+allowBuiltinTools: [Read, Glob, Grep, Bash, BashOutput]
 displayFields: [paths, recursive, maxFiles]
 parameters:
   properties:

package/dist/agents/recall.md

@@ -0,0 +1,49 @@
+---
+name: Recall
+description: Search past chat sessions and summarize the most relevant history for the current question. Use this when earlier conversations might have useful context for the current task.
+allowBuiltinTools: [RecallSearch, RecallRead]
+displayFields: [question, limit, days]
+parameters:
+  properties:
+    question:
+      type: string
+      description: What you want to recall from earlier sessions. Be specific about the topic, task, decision, bug, or project.
+    limit:
+      type: number
+      description: Maximum number of past sessions to summarize. Defaults to 3.
+    days:
+      type: number
+      description: Only search sessions from the last N days.
+  required: [question]
+---
+
+Recall what happened in past sessions about: {{question}}
+
+Summarize at most {{#if limit}}{{limit}}{{else}}3{{/if}} relevant sessions.{{#if days}} Only look at the last {{days}} days.{{/if}}
+
+Use RecallSearch to find matching sessions.{{#if days}} Pass days={{days}} to limit the time range.{{/if}}
+
+RecallSearch is keyword-based, not semantic. It only matches exact words in the text. Search for words that would literally appear in the conversation, not abstract category labels.
+
+If no results, rethink what words the conversation would actually contain and retry. Try up to 3 rounds before giving up.
+
+When you find relevant hits, use RecallRead to get the surrounding conversation. Pass the sessionId and messageIndex from the hit. Use contextBefore and contextAfter to control the reading window (defaults to 2 before, 5 after).
+
+Return the results in this format:
+
+```
+Overview: One short paragraph summarizing what past sessions say about the topic.
+
+Sessions:
+- title or session id
+  - When: relative or absolute time if clear
+  - What happened: the key actions, findings, or decisions
+  - Useful details: commands, files, errors, URLs, or constraints worth remembering
+
+Gaps:
+- Anything unclear, conflicting, or still unresolved.
+```
+
+If there are no matches after all attempts, say that no relevant past sessions were found.
+
+Do not include explanations beyond the result format. Keep responses concise and structured.

package/dist/agents/review.md

@@ -0,0 +1,46 @@
+---
+name: Review
+description: Review the recent work in this conversation with a fresh eye. Returns blockers, important issues, and nits found in the changes. Does not modify files.
+inheritContext: true
+displayFields: [focus]
+parameters:
+  properties:
+    focus:
+      type: string
+      description: Optional angle to prioritize during the review, such as security, performance, tests, readability, or error handling.
+---
+
+Review the work just completed with fresh eyes.
+
+{{#if focus}}Prioritize this angle: {{focus}}.{{/if}}
+
+Do not modify any files. Read the changed files to verify the claims made. Do not assume what was described is what was really written.
+
+Check for:
+- Correctness bugs, unhandled edge cases, missing validation
+- Inconsistency with surrounding code style
+- Unclear naming or logic that will confuse later readers
+- Over-engineering or unneeded complexity
+- Gaps between what was requested and what was delivered
+
+Return the results in this format:
+
+```
+Verdict: ship / fix blockers / rethink
+
+Blockers:
+- Issue that would cause real problems. Cite file:line.
+
+Important:
+- Worth addressing before shipping. Cite file:line.
+
+Nits:
+- Style or polish. Safe to skip.
+
+Missed:
+- Anything the work should have covered but did not.
+```
+
+If nothing needs changing, say so plainly. Do not invent problems.
+
+Do not include explanations beyond the result format. Keep responses concise and structured.

package/dist/agents/search.md

@@ -1,7 +1,7 @@
 ---
 name: Search
 description: Search the codebase to answer a specific question. Returns targeted code segments from across the project that address the query.
-allowBaseTools: [Read, Glob, Grep, Bash, BashOutput]
+allowBuiltinTools: [Read, Glob, Grep, Bash, BashOutput]
 displayFields: [question, directory]
 parameters:
   properties: