@miphamai/cli 0.47.0 → 0.49.0

package/skills/standard/web-access.SKILL.md

@@ -1,213 +1,132 @@
 ---
 name: web-access
-description: All network operations — web search, page fetching, authenticated browsing, social media scraping, dynamic page rendering. Routes to the correct tool (WebSearch/WebFetch/ComputerUse browser) based on the task.
-version: 2.0.0
+description: '联网访问：CDP 驱动用户已登录 Chrome（登录后操作、动态页面、反爬站点、社交媒体、本地书签/历史检索）'
+license: MIT
+github: https://github.com/eze-is/web-access
+version: 2.5.0
 user-invocable: true
 allowed-tools:
   - Bash
   - WebFetch
   - WebSearch
-  - ComputerUse
   - Read
 ---
 
-# Web Access — Executable Workflow
+# Web Access — CDP 驱动已登录 Chrome
 
-**Type**: Flexible — use the decision tree to route to the right tool, then adapt to the specific site.
+> 来源：eze-is/web-access (MIT)，Mipham Code 合并升级。核心能力 = CDP Proxy 直连用户日常 Chrome，天然携带登录态。
 
-**Purpose**: All network-bound operations go through this skill. It routes the request to the correct underlying tool and handles authentication, rendering, and extraction strategy.
+## 前置检查
 
-**Triggers**: "search for", "look up", "find information about", "fetch this URL", "scrape", "browser", "login to", "check this website", "web", "online"
+先确保 CDP 就绪：
 
----
-
-## Phase 0: Route to the Right Tool (ALWAYS RUN FIRST)
-
-```
-User request involves network?
-├── Search engine query (find/discover/look up)?
-│   └── → WebSearch tool
-│       Query best practices: specific + versioned + technical terms
-│
-├── Read a known URL (docs/article/API)?
-│   └── → WebFetch tool
-│       HTTP auto-upgrades to HTTPS, HTML converts to markdown
-│       Cached for 15 minutes — re-fetch only if stale
-│
-├── Login-required site? JavaScript SPA? Form submission?
-│   └── → ComputerUse browser automation
-│       browser_navigate → browser_snapshot → browser_click
-│
-├── Social media (Xiaohongshu, Weibo, Twitter, etc.)?
-│   └── → ComputerUse browser (render JS, handle auth)
-│       OR → WebFetch if public page
-│
-└── API endpoint (REST/GraphQL)?
-    └── → WebFetch with prompt for structured extraction
-```
-
----
-
-## Phase 1: Web Search
-
-Use `WebSearch` for discovery queries — finding documentation, news, troubleshooting, comparisons.
-
-### Query Construction
-
-```
-❌ "React"                           → too broad
-❌ "React problems"                  → ambiguous
-✅ "React 19 useEffect double mount fix 2026"  → specific + versioned
-✅ "Next.js 14 App Router caching behavior"     → targeted
-```
-
-### Domain Filtering
-
-Use `allowed_domains` for authoritative sources:
-
-- `docs.github.com` — GitHub docs
-- `nextjs.org` — Next.js official
-- `developer.mozilla.org` — MDN
-- `nodejs.org` — Node.js official
-
-Use `blocked_domains` to exclude noise (e.g., exclude `w3schools.com` when looking for MDN).
-
-### Verification
-
-- Cross-reference claims across 2+ independent sources
-- Prefer results from current year
-- Authority: official docs > well-known blogs > Stack Overflow > random forums
-
-### Source Attribution
-
-Always end responses with:
-
-```markdown
-Sources:
-
-- [Title](URL) — brief note
+```bash
+node ~/.mipham/skills/web-access/scripts/check-deps.mjs
 ```
 
----
+> Mipham Code 环境：`node` 不可用时可用 `bun` 替代（Bun 原生支持 WebSocket 与 node: 内建）。未通过时引导用户：Chrome 地址栏打开 `chrome://inspect/#remote-debugging`，勾选 "Allow remote debugging for this browser instance"。
 
-## Phase 2: Web Fetch
+**必须向用户展示**：部分站点对浏览器自动化检测严格，存在账号封禁风险。已内置防护但无法完全避免，Agent 继续操作即视为接受。
 
-Use `WebFetch` for reading a specific URL.
+## 工具选择
 
-### What it does
+| 场景                                          | 工具        |
+| --------------------------------------------- | ----------- |
+| 搜索摘要 / 发现来源                           | WebSearch   |
+| URL 已知，定向提取                            | WebFetch    |
+| URL 已知，要原始 HTML（meta/JSON-LD）         | Bash + curl |
+| 非公开内容 / 反爬站点（小红书、微信公众号等） | 浏览器 CDP  |
+| 需要登录态、交互、自由导航                    | 浏览器 CDP  |
 
-- Auto-upgrades HTTP → HTTPS
-- Converts HTML to Markdown (headings, links, images, lists, code blocks)
-- Strips scripts, styles, nav, header, footer before conversion
-- Caches results for 15 minutes per URL
-- Detects cross-host redirects and reports them
-- Truncates content at 100K characters
+浏览器 CDP 不要求 URL 已知；WebSearch/WebFetch/curl 均不处理登录态。
 
-### Prompt Parameter
+## 浏览器 CDP 模式
 
-Use `prompt` to guide extraction focus:
+通过 CDP Proxy 直连用户日常 Chrome，天然携带登录态。**不主动操作用户已有 tab**，所有操作在自己创建的后台 tab 中进行，任务结束关闭自建 tab（保留用户原 tab）。
 
-```
-WebFetch: url="https://docs.example.com", prompt="find the authentication API section"
-```
+Proxy（`scripts/cdp-proxy.mjs`）由 `check-deps.mjs` 自动拉起并常驻。Proxy API（curl 调 `http://localhost:3456/...`）：
 
-### When NOT to use WebFetch
+| 端点                                       | 用途                                                                     |
+| ------------------------------------------ | ------------------------------------------------------------------------ |
+| `GET /targets`                             | 列出已开 tab                                                             |
+| `GET /new?url=`                            | 新建后台 tab（自动等加载）                                               |
+| `GET /navigate?target=&url=`               | 导航（自动等加载）                                                       |
+| `GET /back?target=`                        | 后退                                                                     |
+| `GET /info?target=`                        | 页面标题/URL/状态                                                        |
+| `POST /eval?target=`（body=JS）            | 执行任意 JS（读写 DOM、提取、提交）                                      |
+| `POST /click?target=`（body=CSS 选择器）   | JS 点击（`el.click()`，覆盖大多数场景）                                  |
+| `POST /clickAt?target=`（body=CSS 选择器） | 真实鼠标点击（`Input.dispatchMouseEvent`，算用户手势，能触发文件对话框） |
+| `POST /setFiles?target=`（body JSON）      | 设置 file input 本地文件路径（`DOM.setFileInputFiles`，绕过文件对话框）  |
+| `GET /scroll?target=&y=&direction=`        | 滚动（`direction=down/up/top/bottom`，触发懒加载）                       |
+| `GET /screenshot?target=&file=`            | 截图                                                                     |
+| `GET /close?target=`                       | 关闭 tab                                                                 |
 
-- Search queries → use WebSearch
-- Login-required pages → use ComputerUse browser
-- Large file downloads → use Bash + curl/wget
-- API endpoints returning JSON → WebFetch works, returns raw JSON
+进入浏览器层后，`/eval` 是眼睛、`/click` 是手：先看 DOM 结构再决定下一步，不预先规划所有步骤。
 
----
+### 登录判断
 
-## Phase 3: Browser Automation (ComputerUse)
+核心问题只有一个：**目标内容拿到了吗？** 打开页面先尝试获取目标内容；确认「目标内容无法获取」且判断登录能解决时，告知用户在其 Chrome 登录后继续（无需重启任何东西，刷新页面即可）。
 
-Use `ComputerUse` for interactive browsing — login, form submission, JavaScript rendering.
+### 媒体资源提取
 
-### Available Actions
+判断内容在图片里时，用 `/eval` 从 DOM 直接拿图片 URL 定向读取，比全页截图精准。`/scroll` 到底部触发懒加载后再提取图片 URL。
 
-| Action             | Purpose                                     |
-| ------------------ | ------------------------------------------- |
-| `browser_navigate` | Go to a URL                                 |
-| `browser_snapshot` | Capture accessibility tree (page structure) |
-| `browser_click`    | Click an element by UID                     |
-| `screenshot`       | Capture visible viewport                    |
-| `launch`           | Open a desktop application                  |
+### 视频内容获取
 
-### Workflow for Authenticated Sites
+用户 Chrome 真实渲染，截图可捕获当前视频帧。用 `/eval` 操控 `<video>`（时长、seek、播放/暂停），配合 `/screenshot` 采帧，做离散采样分析。
 
-```
-1. browser_navigate → login page
-2. browser_snapshot → find form fields (UIDs)
-3. Ask user for credentials (NEVER auto-fill)
-4. browser_click → submit
-5. browser_navigate → target page
-6. browser_snapshot → extract content
-```
+## 本地 Chrome 资源
 
-### Workflow for SPAs (React/Vue/Angular)
+用户指向「本人访问过的页面」或「组织内部系统」时，检索本地书签/历史：
 
-```
-1. browser_navigate → SPA URL
-2. Wait 2-3 seconds (JavaScript render)
-3. browser_snapshot → extract rendered content
+```bash
+node ~/.mipham/skills/web-access/scripts/find-url.mjs [关键词...] [--only bookmarks|history] [--limit N] [--since 1d|7h|YYYY-MM-DD] [--sort recent|visits]
 ```
 
-### Prerequisites
+## 并行调研：子 Agent 分治
 
-- Playwright must be installed: `npm install playwright`
-- First launch opens a visible browser window (headless: false)
+多个独立调研目标时，分治给子 Agent 并行执行（共享一个 Chrome、一个 Proxy，各自建 tab、各自 `/close`，无竞态）。子 Agent prompt 写**目标**（「获取/调研/了解」），不写**手段**（避免「搜索xx」锚定到 WebSearch 而错过需 CDP 的反爬站点）。
 
----
-
-## Phase 4: Extraction & Synthesis
+## 信息核实
 
-After fetching content (via any method):
+核实目标是一手来源，非二手报道。搜索引擎是**定位**工具，不可直接**证明**真伪；找到来源后直接访问读原文。
 
-### Content Extraction
+| 信息类型      | 一手来源       |
+| ------------- | -------------- |
+| 政策/法规     | 发布机构官网   |
+| 企业公告      | 公司官方新闻页 |
+| 工具能力/用法 | 官方文档、源码 |
 
-1. Identify relevant sections using the prompt/h3 headings
-2. Extract key facts, code examples, API signatures
-3. Note the source URL for attribution
+### 交叉验证
 
-### Cross-Referencing
+- 关键声明须 2+ 独立来源交叉印证。
+- 优先采纳当年/近期资料。
+- 权威层级：官方文档 > 知名博客 > 技术社区 > 随机论坛。
 
-1. Verify technical claims across 2+ sources
-2. Flag contradictions between sources
-3. Note version/deprecation warnings
+### 来源归因
 
-### Output Format
+回答结尾附来源列表：
 
 ```markdown
-## [Topic]
-
-[Key finding with source attribution]
-
-### Details
-
-[Structured content from page]
-
 Sources:
 
-- [Title](URL)
+- [标题](URL) — 一句话说明
 ```
 
----
+## 站点经验
 
-## Security Rules
+特定网站经验按域名存 `~/.mipham/skills/web-access/references/site-patterns/<domain>.md`（frontmatter: domain/aliases/updated + 平台特征/有效模式/已知陷阱）。操作前若有匹配经验先读；操作成功后把验证过的新模式写回。
 
-- **Never submit credentials** without explicit user approval
-- Respect `robots.txt` and rate limiting
-- Do not scrape PII or sensitive data
-- All URLs validated against SSRF before fetching
-- Only HTTPS for remote requests (HTTP auto-upgraded)
-- Cross-host redirects reported to caller (not silently followed)
+## Security Rules
 
----
+- 不主动操作用户已有 tab；任务结束关闭自建 tab。
+- 不提交凭据（除非用户显式批准）。
+- 尊重 robots.txt 与速率限制；不抓 PII。
+- proxy 仅绑 127.0.0.1，不暴露外网；端口 3456 无鉴权，依赖本机信任边界，勿在共享/多用户主机运行。
+- ⚠️ proxy 不做 URL SSRF 校验（照搬上游，与 computer-use/Playwright 同类）：避免驱动 Chrome 访问本机内部服务/内网地址。
 
-## When NOT to Use This Skill
+## 何时不用本 skill
 
-- Pure logic / algorithmic questions (reasoning, not research)
-- Questions answerable from code already in context
-- Opinions / subjective recommendations (search for data, not consensus)
-- Downloading large binaries → use Bash + curl
+- 纯逻辑/算法题（推理非研究）。
+- 代码已在上下文里的问题。
+- 大文件下载 → Bash + curl。

package/src/agent/agent-context.ts

@@ -102,10 +102,12 @@ export function createAgentContext(
   contextWindow?: number,
   crsiConfig?: Partial<CrsiConfig>,
 ): AgentContextResult {
-  // Create isolated context
+  // Create isolated context, sized to the resolved model's window when known.
+  // Passing contextWindow (not just maxTokens) enables adaptive thresholds.
   const context = new ContextManager({
     maxTokens: contextWindow || 100_000,
     compactionThreshold: 0.85,
+    contextWindow,
   })
 
   // Build system prompt with optional agent memory

package/src/agent/sub-agent.ts

@@ -254,7 +254,35 @@ export class SubAgent {
     const systemPrompt =
       agentDef?.systemPrompt || options.systemPrompt || TYPE_SYSTEM_PROMPTS[agentType]
 
-    // Create isolated context with tool scoping
+    // Resolve the sub-agent's model first, so its context window is known
+    // before the isolated context is created (model-aware sizing).
+    const modelToUse = options.modelOverride || agentDef?.model || model
+    // 'inherit' means use parent model
+    const resolvedModel = modelToUse === 'inherit' ? model : modelToUse
+
+    // Validate resolved model exists in registry; fall back to parent model with warning
+    let finalModel = resolvedModel
+    if (resolvedModel !== model) {
+      const modelExists = this.registry.findModel(resolvedModel) !== undefined
+      if (!modelExists) {
+        const warnMsg = `Warning: model "${resolvedModel}" not found in provider registry. Falling back to "${model}".`
+        console.warn(warnMsg)
+
+        // Post warning to message bus for UI display
+        const bus = getMessageBus()
+        bus.post(
+          'system',
+          'main',
+          `Sub-agent model fallback: ${resolvedModel} → ${model}`,
+          warnMsg,
+          'warning',
+        )
+
+        finalModel = model
+      }
+    }
+
+    // Create isolated context with tool scoping, sized to the resolved model.
     const resolvedDef: AgentDefinition = agentDef || {
       name: agentType,
       description: '',
@@ -264,10 +292,11 @@ export class SubAgent {
       background: false,
       source: 'builtin',
     }
+    const contextWindow = this.registry.findModel(finalModel)?.contextWindow
     const { context, allowedTools } = createAgentContext(
       resolvedDef,
       this.toolRegistry,
-      options.maxContextMessages,
+      contextWindow,
     )
 
     context.setSystemPrompt(systemPrompt)
@@ -291,32 +320,6 @@ export class SubAgent {
           }))
         : undefined
 
-    const modelToUse = options.modelOverride || agentDef?.model || model
-    // 'inherit' means use parent model
-    const resolvedModel = modelToUse === 'inherit' ? model : modelToUse
-
-    // Validate resolved model exists in registry; fall back to parent model with warning
-    let finalModel = resolvedModel
-    if (resolvedModel !== model) {
-      const modelExists = this.registry.findModel(resolvedModel) !== undefined
-      if (!modelExists) {
-        const warnMsg = `Warning: model "${resolvedModel}" not found in provider registry. Falling back to "${model}".`
-        console.warn(warnMsg)
-
-        // Post warning to message bus for UI display
-        const bus = getMessageBus()
-        bus.post(
-          'system',
-          'main',
-          `Sub-agent model fallback: ${resolvedModel} → ${model}`,
-          warnMsg,
-          'warning',
-        )
-
-        finalModel = model
-      }
-    }
-
     const chunks: string[] = []
     const MAX_TOOL_TURNS = options.maxTurns || 5
 

package/src/agent/types.ts

@@ -39,7 +39,6 @@ export interface SubAgentOptions {
   type?: SubAgentType
   agentDef?: AgentDefinition
   systemPrompt?: string
-  maxContextMessages?: number
   allowedTools?: string[]
   modelOverride?: string
   /** Maximum tool-calling turns (default: 5) to prevent infinite loops. */

package/src/core/engine.ts

@@ -1431,7 +1431,7 @@ export class QueryEngine {
         const DISABLE_1M = process.env.MIPHAM_DISABLE_1M_CONTEXT === '1'
         const maxTokens =
           DISABLE_1M && model.contextWindow > 200_000 ? 200_000 : model.contextWindow
-        this.context.updateMaxTokens(maxTokens)
+        this.context.updateMaxTokens(maxTokens, model.contextWindow)
       }
     }
   }

package/src/daemon/server.ts

@@ -67,6 +67,22 @@ function resolveDaemonPermission(): PermissionMode {
     : 'default'
 }
 
+const DAEMON_DEFAULT_CONTEXT_WINDOW = 200_000
+
+/**
+ * Resolve the effective context window (in tokens) for the daemon session's
+ * model. Mirrors the CLI's model-aware context sizing so a 1M-context model
+ * isn't silently hard-capped at 200K; falls back when the model isn't in the
+ * registry.
+ */
+export function resolveContextWindow(
+  registry: ProviderRegistry,
+  modelId: string,
+  fallback = DAEMON_DEFAULT_CONTEXT_WINDOW,
+): number {
+  return registry.findModel(modelId)?.contextWindow ?? fallback
+}
+
 export function createServer(config: ServerConfig): Server<WsData> {
   const {
     db,
@@ -120,7 +136,6 @@ export function createServer(config: ServerConfig): Server<WsData> {
   const engineCache = new Map<string, QueryEngine>()
   let sharedRegistry: ProviderRegistry | null = null
   let sharedTools: Map<string, ToolDefinition> | null = null
-  const DEFAULT_MAX_TOKENS = 200_000
 
   function getOrCreateEngine(
     sessionId: string,
@@ -148,11 +163,13 @@ export function createServer(config: ServerConfig): Server<WsData> {
       sharedTools = createToolRegistry()
     }
 
-    // Create per-session context, restoring previous messages from DB
+    // Create per-session context, restoring previous messages from DB.
+    // Size it to the active model's context window (1M-capable models get 1M).
+    const contextWindow = resolveContextWindow(sharedRegistry!, model)
     const context = new ContextManager({
-      maxTokens: DEFAULT_MAX_TOKENS,
+      maxTokens: contextWindow,
       compactionThreshold: 0.9,
-      contextWindow: DEFAULT_MAX_TOKENS,
+      contextWindow,
     })
 
     const dbMessages = db.getMessages(sessionId, 10000)

package/src/i18n-core/locales/en-US.json

@@ -718,6 +718,79 @@
       "shift_tab_cycle": "shift+tab",
       "left_for_agents": "ctrl+g agents to manage",
       "mipham_modes": "Mipham"
+    },
+    "wizard": {
+      "header_subtitle": " — Configuration Wizard",
+      "welcome_title": "Welcome to Mipham Code!",
+      "welcome_intro": "Before you start, you need to configure your AI model connection.",
+      "welcome_time": "This wizard takes about 1 minute — please have your API key ready.",
+      "welcome_start": "Press Enter to start →",
+      "welcome_skip": "Esc to skip",
+      "mode_title": "Choose connection method:",
+      "mode_cloud": "🌐 Cloud AI models (recommended)",
+      "mode_local": "🖥️ Local models (Ollama)",
+      "mode_local_hint": " Requires Ollama installed with models downloaded",
+      "nav_hint": "↑↓ select · Enter confirm · Esc back",
+      "provider_title": "Choose AI model provider:",
+      "provider_count": " ({count} models)",
+      "model_title": "Choose model ({provider}):",
+      "apikey_title": "Paste your API key:",
+      "apikey_provider": "Provider: {provider}",
+      "apikey_model": "Model: {model}",
+      "apikey_placeholder": "Paste API key then press Enter...",
+      "apikey_continue": "Enter to continue · Esc to go back to model",
+      "ollama_title": "Ollama local model configuration:",
+      "ollama_status": "Status: ",
+      "ollama_installed": "✅ installed",
+      "ollama_not_installed": "❌ not installed",
+      "ollama_running": " · running",
+      "ollama_not_running": " · not running (run ollama serve)",
+      "ollama_detecting": "Detecting Ollama...",
+      "ollama_downloaded": "Downloaded models (↑↓ select · Enter confirm):",
+      "ollama_source_hot": "Popular",
+      "ollama_no_models": "No downloaded models found. Run ollama pull <model> to download one.",
+      "ollama_preset_hint": "Below are preset models — switch anytime via /models.",
+      "confirm_title": "Confirm configuration:",
+      "confirm_connection": "Connection: ",
+      "confirm_cloud": "🌐 Cloud",
+      "confirm_local": "🖥️ Local",
+      "confirm_provider": "Provider: {provider}",
+      "confirm_model": "Model: {model}",
+      "confirm_apikey": "API key: {masked}",
+      "confirm_ollama_model": "Ollama model: {model}",
+      "confirm_save_path": "Config will be saved to ~/.mipham/config.yml",
+      "confirm_save": "Press Enter to save and launch →",
+      "confirm_back": "Esc to go back",
+      "done_title": "✅ Configuration complete!",
+      "done_launching": "Mipham Code is starting...",
+      "error_apikey_required": "Please enter your API key",
+      "error_write_failed": "Failed to write config: {err}"
+    },
+    "goal_progress": {
+      "title": "🎯 Goal: {goal}",
+      "no_subtasks": " (no subtasks yet)",
+      "summary": "═══ {done}/{total} done",
+      "in_progress": " · {n} in progress",
+      "failed": " · {n} failed",
+      "tokens": " · {n} tokens",
+      "border_end": " ═══"
+    },
+    "workflow": {
+      "title": "═══ Workflow: {runId} ═══",
+      "phase": "Phase: {name}",
+      "done_count": " [{done}/{total} done]",
+      "footer": "═══ Elapsed: {time} | Agents: {done}/{total}",
+      "running": " ({n} running)",
+      "failed": " ({n} failed)",
+      "cache_hits": " | Cache hits: {n}",
+      "done_marker": " | DONE ═══",
+      "running_marker": " | Status: running ═══"
+    },
+    "error_boundary": {
+      "title": "⚠️ UI Render Error",
+      "unknown": "Unknown rendering error",
+      "recovery": "The terminal interface encountered a rendering issue. Auto-recovery in 5 seconds... Press Enter to attempt immediate recovery.",
+      "preserved": "Your session data and conversation history are preserved."
     }
   },
   "tools": {

package/src/i18n-core/locales/zh-CN.json

@@ -718,6 +718,79 @@
       "shift_tab_cycle": "Shift+Tab",
       "left_for_agents": "ctrl+g 管理代理",
       "mipham_modes": "Mipham独有"
+    },
+    "wizard": {
+      "header_subtitle": " — 配置向导",
+      "welcome_title": "欢迎使用 Mipham Code！",
+      "welcome_intro": "在开始之前，需要先配置 AI 模型连接。",
+      "welcome_time": "此向导只需 1 分钟，需要您准备好 API Key。",
+      "welcome_start": "按 Enter 开始 →",
+      "welcome_skip": "Esc 跳过配置",
+      "mode_title": "选择模型连接方式：",
+      "mode_cloud": "🌐 云端 AI 模型（推荐）",
+      "mode_local": "🖥️ 本地模型（Ollama）",
+      "mode_local_hint": " 需要提前安装 Ollama 并下载模型",
+      "nav_hint": "↑↓ 选择 · Enter 确认 · Esc 返回",
+      "provider_title": "选择 AI 模型提供商：",
+      "provider_count": " ({count} 个模型)",
+      "model_title": "选择模型（{provider}）：",
+      "apikey_title": "粘贴 API Key：",
+      "apikey_provider": "提供商：{provider}",
+      "apikey_model": "模型：{model}",
+      "apikey_placeholder": "粘贴 API Key 后按 Enter...",
+      "apikey_continue": "Enter 继续 · Esc 返回选模型",
+      "ollama_title": "Ollama 本地模型配置：",
+      "ollama_status": "状态：",
+      "ollama_installed": "✅ 已安装",
+      "ollama_not_installed": "❌ 未安装",
+      "ollama_running": " · 运行中",
+      "ollama_not_running": " · 未运行（请执行 ollama serve）",
+      "ollama_detecting": "正在检测 Ollama...",
+      "ollama_downloaded": "已下载模型（↑↓ 选择 · Enter 确认）：",
+      "ollama_source_hot": "热门",
+      "ollama_no_models": "未检测到已下载模型。请先运行 ollama pull <model> 下载模型。",
+      "ollama_preset_hint": "以下为预置模型列表，选择后可在对话中通过 /models 切换。",
+      "confirm_title": "配置确认：",
+      "confirm_connection": "连接方式：",
+      "confirm_cloud": "🌐 云端",
+      "confirm_local": "🖥️ 本地",
+      "confirm_provider": "提供商：{provider}",
+      "confirm_model": "模型：{model}",
+      "confirm_apikey": "API Key：{masked}",
+      "confirm_ollama_model": "Ollama 模型：{model}",
+      "confirm_save_path": "配置文件将保存到 ~/.mipham/config.yml",
+      "confirm_save": "按 Enter 保存并启动 →",
+      "confirm_back": "Esc 返回修改",
+      "done_title": "✅ 配置完成！",
+      "done_launching": "Mipham Code 正在启动...",
+      "error_apikey_required": "请填写 API Key",
+      "error_write_failed": "写入配置失败: {err}"
+    },
+    "goal_progress": {
+      "title": "🎯 目标：{goal}",
+      "no_subtasks": " （暂无子任务）",
+      "summary": "═══ {done}/{total} 完成",
+      "in_progress": " · {n} 进行中",
+      "failed": " · {n} 失败",
+      "tokens": " · {n} tokens",
+      "border_end": " ═══"
+    },
+    "workflow": {
+      "title": "═══ 工作流：{runId} ═══",
+      "phase": "阶段：{name}",
+      "done_count": " [{done}/{total} 完成]",
+      "footer": "═══ 耗时：{time} | Agent：{done}/{total}",
+      "running": " （{n} 运行中）",
+      "failed": " （{n} 失败）",
+      "cache_hits": " | 缓存命中：{n}",
+      "done_marker": " | 完成 ═══",
+      "running_marker": " | 状态：运行中 ═══"
+    },
+    "error_boundary": {
+      "title": "⚠️ UI 渲染错误",
+      "unknown": "未知渲染错误",
+      "recovery": "终端界面遇到渲染问题，5 秒后自动恢复... 按 Enter 尝试立即恢复。",
+      "preserved": "你的会话数据和对话历史已保留。"
     }
   },
   "tools": {

package/src/shared/package-info.ts

@@ -9,7 +9,7 @@
 export const PACKAGE_NAME = '@miphamai/cli' as const
 
 /** 当前发布版本 */
-export const PACKAGE_VERSION = '0.47.0' as const
+export const PACKAGE_VERSION = '0.49.0' as const
 
 /** npm install 全局安装命令 */
 export const NPM_INSTALL_COMMAND = `npm install -g ${PACKAGE_NAME}` as const