jinzd-ai-cli 0.4.19 → 0.4.21

package/README.md

@@ -7,7 +7,7 @@
 [![npm version](https://img.shields.io/npm/v/jinzd-ai-cli)](https://www.npmjs.com/package/jinzd-ai-cli)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 [![Node.js](https://img.shields.io/badge/node-%3E%3D20-brightgreen)](https://nodejs.org)
-[![Tests](https://img.shields.io/badge/tests-138%20passing-brightgreen)]()
+[![Tests](https://img.shields.io/badge/tests-282%20passing-brightgreen)]()
 [![GitHub Release](https://img.shields.io/github/v/release/jinzhengdong/ai-cli)](https://github.com/jinzhengdong/ai-cli/releases)
 [![CI](https://github.com/jinzhengdong/ai-cli/actions/workflows/ci.yml/badge.svg)](https://github.com/jinzhengdong/ai-cli/actions/workflows/ci.yml)
 
@@ -34,7 +34,7 @@
 - **PWA Support** — Install Web UI as a desktop/mobile app, accessible over LAN
 - **Hierarchical Context** — 3-layer context files (global / project / subdirectory) auto-injected
 - **Headless Mode** — `ai-cli -p "prompt"` for CI/CD pipelines and scripting
-- **37 REPL Commands** — Session management, checkpointing, code review, scaffolding, and more
+- **38 REPL Commands** — Session management, checkpointing, code review, scaffolding, user identity, and more
 - **GitHub Actions CI/CD** — Automated testing on Node 20/22 + npm publish on release tags
 - **Cross-Platform** — Windows, macOS, Linux
 
@@ -75,7 +75,7 @@ Pre-built CLI binaries (no Node.js required, ~56 MB):
 aicli
 ```
 
-On first run, an interactive setup wizard guides you through selecting a provider and entering your API key.
+On first run, an interactive setup wizard guides you through setting up your profile and entering your API key. Your identity is persisted and injected into every AI conversation.
 
 ```
 [deepseek] > Hello! Tell me about this project
@@ -167,12 +167,13 @@ AI autonomously invokes these 16 tools during conversations:
 | `/undo` | Undo last file operation |
 | `/doctor` | Health check (API keys, MCP, context) |
 | `/export` | Export session as Markdown or JSON |
+| `/profile` | View/edit your identity (AI knows who you are across all providers) |
 | `/config` | Open configuration wizard |
 | `/help` | Show all available commands |
 
 **Multi-line input**: Use `\` at end of line for continuation, or paste multi-line content directly (auto-detected and merged).
 
-Type `/help` in the REPL to see all 37 commands.
+Type `/help` in the REPL to see all 38 commands.
 
 ## CLI Parameters
 
@@ -348,11 +349,11 @@ The Web UI (`aicli web`) provides a full-featured browser interface:
 ## Testing
 
 ```bash
-npm test              # Run all 138 tests
+npm test              # Run all 282 tests
 npm run test:watch    # Watch mode
 ```
 
-8 test suites covering: authentication, sessions, tool types & danger levels, permissions, output truncation, diff rendering, edit-file similarity, error hierarchy.
+18 test suites covering: authentication, sessions, tool types & danger levels, permissions, output truncation, diff rendering, edit-file similarity, error hierarchy, config management, env loading, provider registry, web-fetch, grep-files, hub renderer, hub discussion, hub presets, dev-state.
 
 ## Documentation
 

package/README.zh-CN.md

@@ -7,7 +7,7 @@
 [![npm version](https://img.shields.io/npm/v/jinzd-ai-cli)](https://www.npmjs.com/package/jinzd-ai-cli)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 [![Node.js](https://img.shields.io/badge/node-%3E%3D20-brightgreen)](https://nodejs.org)
-[![Tests](https://img.shields.io/badge/tests-138%20passing-brightgreen)]()
+[![Tests](https://img.shields.io/badge/tests-282%20passing-brightgreen)]()
 [![GitHub Release](https://img.shields.io/github/v/release/jinzhengdong/ai-cli)](https://github.com/jinzhengdong/ai-cli/releases)
 [![CI](https://github.com/jinzhengdong/ai-cli/actions/workflows/ci.yml/badge.svg)](https://github.com/jinzhengdong/ai-cli/actions/workflows/ci.yml)
 
@@ -26,7 +26,7 @@
 - **PWA 支持** — Web UI 可安装为桌面/移动应用，支持局域网访问
 - **三层级上下文** — 全局 / 项目 / 子目录上下文文件自动注入
 - **无头模式** — `aicli -p "提示词"` 用于 CI/CD 管道和脚本
-- **37 个 REPL 命令** — 会话管理、检查点、代码审查、脚手架等
+- **38 个 REPL 命令** — 会话管理、检查点、代码审查、脚手架、用户身份等
 - **GitHub Actions CI/CD** — Node 20/22 自动测试 + Release tag 自动发布 npm
 - **跨平台** — Windows、macOS、Linux
 
@@ -67,7 +67,7 @@ npm install -g jinzd-ai-cli
 aicli
 ```
 
-首次运行会进入交互式配置向导，选择 Provider 并输入 API Key。配置保存在 `~/.aicli/config.json`。
+首次运行会进入交互式配置向导，先设置你的身份档案，再选择 Provider 并输入 API Key。身份信息会注入每次 AI 对话。
 
 ```
 [deepseek] > 你好！帮我分析一下这个项目
@@ -159,12 +159,13 @@ AI 在对话中可自主调用 16 个工具：
 | `/undo` | 撤销上次文件操作 |
 | `/doctor` | 健康检查（API Key、MCP、上下文） |
 | `/export` | 导出会话为 Markdown 或 JSON |
+| `/profile` | 查看/编辑身份档案（AI 跨 Provider 认识你） |
 | `/config` | 打开配置向导 |
 | `/help` | 显示所有命令 |
 
 **多行输入**：行末加 `\` 续行，或直接粘贴多行内容（自动检测合并）。
 
-在 REPL 中输入 `/help` 查看全部 37 个命令。
+在 REPL 中输入 `/help` 查看全部 38 个命令。
 
 ## CLI 参数
 
@@ -361,11 +362,11 @@ Web UI（`aicli web`）提供功能完备的浏览器界面：
 ## 测试
 
 ```bash
-npm test              # 运行全部 138 个测试
+npm test              # 运行全部 282 个测试
 npm run test:watch    # 监听模式
 ```
 
-8 个测试套件覆盖：认证、会话、工具类型与危险级别、权限、输出截断、diff 渲染、edit-file 相似度、错误层级。
+18 个测试套件覆盖：认证、会话、工具类型与危险级别、权限、输出截断、diff 渲染、edit-file 相似度、错误层级、配置管理、环境变量、Provider 注册、web-fetch、grep-files、Hub 渲染、Hub 讨论、Hub 预设、开发状态。
 
 ## 文档
 

package/dist/{chunk-PR5JZVNN.js → chunk-2JOMWVTE.js}

@@ -6,7 +6,7 @@ import {
   SUBAGENT_DEFAULT_MAX_ROUNDS,
   SUBAGENT_MAX_ROUNDS_LIMIT,
   runTestsTool
-} from "./chunk-JNAZORS2.js";
+} from "./chunk-AR656G5C.js";
 
 // src/tools/builtin/bash.ts
 import { execSync } from "child_process";

package/dist/{chunk-6WLDJKHU.js → chunk-6CJX3RST.js}

@@ -6,7 +6,7 @@ import { platform } from "os";
 import chalk from "chalk";
 
 // src/core/constants.ts
-var VERSION = "0.4.19";
+var VERSION = "0.4.21";
 var APP_NAME = "ai-cli";
 var CONFIG_DIR_NAME = ".aicli";
 var CONFIG_FILE_NAME = "config.json";
@@ -85,6 +85,35 @@ var AGENTIC_BEHAVIOR_GUIDELINE = `# Important Behavioral Guidelines
 - Only begin using write/execute tools when the user **explicitly requests** an action (e.g., "generate", "create", "modify", "run", "start", etc.).
 - Project context files (CLAUDE.md, AICLI.md) provide background information about the project. They are NOT instructions to start working. Only use them as reference when the user asks a project-related question or task.
 - If you are unsure about the user's intent, use the ask_user tool to confirm with the user, rather than assuming and executing on your own.`;
+function buildUserIdentityPrompt(profile) {
+  const lines = [];
+  const displayName = profile.nickname || profile.name;
+  if (displayName) {
+    lines.push(`The user's name is **${profile.name || displayName}**${profile.nickname && profile.name ? ` (prefers to be called **${profile.nickname}**)` : ""}.`);
+  }
+  if (profile.role) {
+    lines.push(`Role: ${profile.role}.`);
+  }
+  if (profile.bio) {
+    lines.push(`About: ${profile.bio}`);
+  }
+  if (profile.interests && profile.interests.length > 0) {
+    lines.push(`Interests & expertise: ${profile.interests.join(", ")}.`);
+  }
+  if (profile.locale) {
+    lines.push(`Preferred language: ${profile.locale}. Please respond in this language unless the user explicitly uses another language.`);
+  }
+  if (profile.extra) {
+    lines.push(`
+${profile.extra}`);
+  }
+  if (lines.length === 0) return null;
+  return `# Who You're Talking To
+
+${lines.join("\n")}
+
+Address the user personally and adapt your communication style to their background. This identity persists across all conversations and all AI providers.`;
+}
 var AUTHOR = "Jin Zhengdong";
 var AUTHOR_EMAIL = "zhengdong.jin@gmail.com";
 var DESCRIPTION = "Cross-platform REPL-style AI conversation tool with multi-provider and agentic tool calling support";
@@ -468,6 +497,7 @@ export {
   SUBAGENT_MAX_ROUNDS_LIMIT,
   SUBAGENT_ALLOWED_TOOLS,
   AGENTIC_BEHAVIOR_GUIDELINE,
+  buildUserIdentityPrompt,
   AUTHOR,
   AUTHOR_EMAIL,
   DESCRIPTION,

package/dist/{chunk-DBEYB76P.js → chunk-7T2W4LN3.js}

@@ -7,7 +7,7 @@ import {
   ProviderNotFoundError,
   RateLimitError,
   schemaToJsonSchema
-} from "./chunk-PR5JZVNN.js";
+} from "./chunk-2JOMWVTE.js";
 import {
   APP_NAME,
   CONFIG_DIR_NAME,
@@ -20,7 +20,7 @@ import {
   MCP_TOOL_PREFIX,
   PLUGINS_DIR_NAME,
   VERSION
-} from "./chunk-JNAZORS2.js";
+} from "./chunk-AR656G5C.js";
 
 // src/config/config-manager.ts
 import { readFileSync, writeFileSync, existsSync, mkdirSync } from "fs";
@@ -58,8 +58,26 @@ var ModelParamsSchema = z.object({
   /** thinking 模式的 token 预算（最小 1024，仅 Claude Extended Thinking 使用） */
   thinkingBudget: z.number().int().min(1024).optional()
 });
+var UserProfileSchema = z.object({
+  /** 真实姓名（如 "Jin Zhengdong"） */
+  name: z.string().optional(),
+  /** 昵称/称呼偏好（如 "东叔"），AI 会以此称呼你 */
+  nickname: z.string().optional(),
+  /** 职业角色（如 "Full-stack developer"、"Data scientist"） */
+  role: z.string().optional(),
+  /** 个人简介 / 专长描述（1-3 句话） */
+  bio: z.string().optional(),
+  /** 兴趣领域或技术栈（如 ["TypeScript", "Rust", "AI/ML"]） */
+  interests: z.array(z.string()).default([]),
+  /** 语言偏好（如 "zh-CN"、"en"），AI 将据此选择交流语言 */
+  locale: z.string().optional(),
+  /** 自定义人设补充（自由格式，直接注入 system prompt） */
+  extra: z.string().optional()
+}).default({});
 var ConfigSchema = z.object({
   version: z.string().default("1.0.0"),
+  // 用户身份档案 — 跨 Provider 的 "灵魂"
+  userProfile: UserProfileSchema,
   defaultProvider: z.string().default("claude"),
   // 每个 provider 的默认模型（key 为 provider ID）
   defaultModels: z.record(z.string()).default({}),
@@ -3441,7 +3459,7 @@ function saveDevState(content) {
   if (trimmed.length > DEV_STATE_MAX_CHARS) {
     trimmed = trimmed.slice(0, DEV_STATE_MAX_CHARS);
     const lastNewline = trimmed.lastIndexOf("\n");
-    if (lastNewline > DEV_STATE_MAX_CHARS * 0.8) {
+    if (lastNewline > 0) {
       trimmed = trimmed.slice(0, lastNewline);
     }
     trimmed += "\n\n[...truncated]";

package/dist/{chunk-JNAZORS2.js → chunk-AR656G5C.js}

@@ -8,7 +8,7 @@ import { platform } from "os";
 import chalk from "chalk";
 
 // src/core/constants.ts
-var VERSION = "0.4.19";
+var VERSION = "0.4.21";
 var APP_NAME = "ai-cli";
 var CONFIG_DIR_NAME = ".aicli";
 var CONFIG_FILE_NAME = "config.json";
@@ -88,6 +88,35 @@ var AGENTIC_BEHAVIOR_GUIDELINE = `# Important Behavioral Guidelines
 - Only begin using write/execute tools when the user **explicitly requests** an action (e.g., "generate", "create", "modify", "run", "start", etc.).
 - Project context files (CLAUDE.md, AICLI.md) provide background information about the project. They are NOT instructions to start working. Only use them as reference when the user asks a project-related question or task.
 - If you are unsure about the user's intent, use the ask_user tool to confirm with the user, rather than assuming and executing on your own.`;
+function buildUserIdentityPrompt(profile) {
+  const lines = [];
+  const displayName = profile.nickname || profile.name;
+  if (displayName) {
+    lines.push(`The user's name is **${profile.name || displayName}**${profile.nickname && profile.name ? ` (prefers to be called **${profile.nickname}**)` : ""}.`);
+  }
+  if (profile.role) {
+    lines.push(`Role: ${profile.role}.`);
+  }
+  if (profile.bio) {
+    lines.push(`About: ${profile.bio}`);
+  }
+  if (profile.interests && profile.interests.length > 0) {
+    lines.push(`Interests & expertise: ${profile.interests.join(", ")}.`);
+  }
+  if (profile.locale) {
+    lines.push(`Preferred language: ${profile.locale}. Please respond in this language unless the user explicitly uses another language.`);
+  }
+  if (profile.extra) {
+    lines.push(`
+${profile.extra}`);
+  }
+  if (lines.length === 0) return null;
+  return `# Who You're Talking To
+
+${lines.join("\n")}
+
+Address the user personally and adapt your communication style to their background. This identity persists across all conversations and all AI providers.`;
+}
 var AUTHOR = "Jin Zhengdong";
 var AUTHOR_EMAIL = "zhengdong.jin@gmail.com";
 var DESCRIPTION = "Cross-platform REPL-style AI conversation tool with multi-provider and agentic tool calling support";
@@ -473,6 +502,7 @@ export {
   SUBAGENT_ALLOWED_TOOLS,
   CONTEXT_PRESSURE_THRESHOLD,
   AGENTIC_BEHAVIOR_GUIDELINE,
+  buildUserIdentityPrompt,
   AUTHOR,
   AUTHOR_EMAIL,
   DESCRIPTION,

package/dist/{hub-RJRNBB5G.js → hub-CNSFX47B.js}

@@ -387,7 +387,7 @@ ${content}`);
   }
 }
 async function runTaskMode(config, providers, configManager, topic) {
-  const { TaskOrchestrator } = await import("./task-orchestrator-JKY2T2W3.js");
+  const { TaskOrchestrator } = await import("./task-orchestrator-UZQRB7AO.js");
   const orchestrator = new TaskOrchestrator(config, providers, configManager);
   let interrupted = false;
   const onSigint = () => {

package/dist/index.js

@@ -23,7 +23,7 @@ import {
   saveDevState,
   sessionHasMeaningfulContent,
   setupProxy
-} from "./chunk-DBEYB76P.js";
+} from "./chunk-7T2W4LN3.js";
 import {
   ToolRegistry,
   askUserContext,
@@ -38,7 +38,7 @@ import {
   theme,
   truncateOutput,
   undoStack
-} from "./chunk-PR5JZVNN.js";
+} from "./chunk-2JOMWVTE.js";
 import {
   AGENTIC_BEHAVIOR_GUIDELINE,
   AUTHOR,
@@ -57,8 +57,9 @@ import {
   PLAN_MODE_SYSTEM_ADDON,
   REPO_URL,
   SKILLS_DIR_NAME,
-  VERSION
-} from "./chunk-JNAZORS2.js";
+  VERSION,
+  buildUserIdentityPrompt
+} from "./chunk-AR656G5C.js";
 
 // src/index.ts
 import { program } from "commander";
@@ -166,14 +167,16 @@ var Renderer = class {
     const configured = options?.wrapWidth ?? 0;
     this.wrapWidth = configured > 0 ? configured : 0;
   }
-  printWelcome(provider, model, contextWindow) {
+  printWelcome(provider, model, contextWindow, userNickname) {
     const ctxStr = contextWindow ? theme.dim(` (ctx: ${fmtContextWindow(contextWindow)})`) : "";
+    const greeting = userNickname ? `  \u{1F44B} Hello, ${userNickname}!` : "";
     console.log();
     console.log(theme.heading("  \u{1F916} ai-cli") + theme.dim(` v${VERSION}`) + theme.dim("  \u2014  " + AUTHOR + " <" + AUTHOR_EMAIL + ">"));
+    if (greeting) console.log(theme.accent(greeting));
     console.log(theme.dim("  " + "\u2500".repeat(55)));
     console.log(theme.dim(`  Provider : `) + theme.prompt(provider));
     console.log(theme.dim(`  Model    : `) + chalk.white(model) + ctxStr);
-    console.log(theme.dim("  Commands : ") + theme.dim("/help \xB7 /about \xB7 Ctrl+C to exit"));
+    console.log(theme.dim("  Commands : ") + theme.dim("/help \xB7 /about \xB7 /profile \xB7 Ctrl+C to exit"));
     console.log();
   }
   printAbout(pluginCount = 0, mcpInfo) {
@@ -217,12 +220,12 @@ var Renderer = class {
     console.log(tool("spawn_agent", "Delegate to independent sub-agent (isolated dialog + auto tool-call loop)"));
     console.log(tool("run_tests", "Run project tests and return structured report (auto-detect Maven/npm/pytest etc.)"));
     console.log(HR);
-    console.log(theme.dim("  REPL Commands (37):"));
+    console.log(theme.dim("  REPL Commands (38):"));
     console.log(theme.dim("    /help  /about  /provider  /model  /clear  /compact  /plan  /session"));
     console.log(theme.dim("    /system  /context  /status  /search  /undo  /export  /copy  /paste"));
     console.log(theme.dim("    /cost  /init  /skill  /tools  /plugins  /mcp  /config  /checkpoint"));
-    console.log(theme.dim("    /review  /commands  /test  /scaffold  /add-dir  /memory  /doctor"));
-    console.log(theme.dim("    /bug  /think  /diff  /fork  /yolo  /exit"));
+    console.log(theme.dim("    /review  /commands  /test  /scaffold  /add-dir  /memory  /profile"));
+    console.log(theme.dim("    /doctor  /bug  /think  /diff  /fork  /yolo  /exit"));
     console.log(HR);
     console.log(theme.dim("  Key Features:"));
     console.log(feat("Agentic loop (up to 25 tool-call rounds, final answer streamed)"));
@@ -233,6 +236,7 @@ var Renderer = class {
     console.log(feat("File operation undo (/undo [list|<n>], supports write_file / edit_file / bash-created files/dirs)"));
     console.log(feat("Thinking mode collapse (<think> blocks auto-collapsed, GLM-5 etc.)"));
     console.log(feat("Token usage tracking (per-response + session cumulative, Gemini/Claude/DeepSeek etc.)"));
+    console.log(feat("User identity (/profile): persistent profile injected into every AI provider \u2014 AI knows who you are"));
     console.log(feat("MCP protocol support: connect external MCP server tools (config.json mcpServers)"));
     console.log(feat("Plugin system: ~/.aicli/plugins/*.js custom tools (requires allowPlugins:true, off by default)"));
     console.log(feat("Plan Mode: /plan enters read-only planning, AI uses safe tools only, /plan execute resumes"));
@@ -350,7 +354,7 @@ var Renderer = class {
     } catch (err) {
       if (err?.name === "AbortError") {
         interrupted = true;
-        flushBuf();
+        if (!inThinking) flushBuf();
       } else {
         throw err;
       }
@@ -423,6 +427,9 @@ var Renderer = class {
         process.stdout.write(theme.dim("\n\u{1F4AD} Thinking...\n"));
       }
     }
+    if (this.wrapWidth > 0) {
+      displayed = wrapText(displayed, this.wrapWidth);
+    }
     const CHUNK_SIZE = 12;
     const DELAY_MS = 8;
     let pos = 0;
@@ -881,6 +888,7 @@ function createDefaultCommands() {
           "  /test [command|filter]   - Run project tests and show structured report",
           "  /scaffold <description>  - Generate project scaffolding with AI",
           "  /add-dir [path|remove]   - Add/remove a directory from AI context",
+          "  /profile [show|set|clear] - View or edit your identity (AI knows who you are)",
           "  /memory [show|add|clear] - View or edit persistent memory (memory.md)",
           "  /doctor                  - Health check (API keys, config, MCP status)",
           "  /bug [--copy]            - Generate bug report template (--copy to clipboard)",
@@ -1038,11 +1046,18 @@ function createDefaultCommands() {
             return;
           }
           const sessions = ctx.sessions.listSessions();
-          const match = sessions.find((s) => s.id.startsWith(id));
-          if (!match) {
+          const matches = sessions.filter((s) => s.id.startsWith(id));
+          if (matches.length === 0) {
             ctx.renderer.renderError(`Session '${id}' not found.`);
             return;
           }
+          if (matches.length > 1) {
+            console.log(theme.warning(`  \u26A0 Ambiguous prefix '${id}' matches ${matches.length} sessions \u2014 loading most recent:`));
+            for (const m of matches.slice(0, 5)) {
+              console.log(theme.dim(`    ${m.id.slice(0, 12)}  ${m.title ?? "(untitled)"}`));
+            }
+          }
+          const match = matches[0];
           ctx.sessions.loadSession(match.id);
           ctx.setProvider(match.provider, match.model);
           ctx.resetSessionTokenUsage();
@@ -1155,7 +1170,8 @@ function createDefaultCommands() {
           const estStr = fmtCtx(estimated);
           const winStr = fmtCtx(ctxWindowSize);
           const pctColor = pct >= 80 ? theme.error : pct >= 60 ? theme.warning : theme.success;
-          console.log(`  Context% : ~${estStr} / ${winStr} tokens (${pctColor(`${pct}%`)})`);
+          const pctDisplay = pct > 100 ? `${pct}% \u26A0 over limit` : `${pct}%`;
+          console.log(`  Context% : ~${estStr} / ${winStr} tokens (${pctColor(pctDisplay)})`);
         }
         console.log();
       }
@@ -1821,7 +1837,8 @@ ${hint}` : "")
           }
           const ok = ctx.restoreCheckpoint(name);
           if (ok) {
-            console.log(theme.success(`  \u2713 Restored to checkpoint "${name}" (${session.messages.length} messages)`));
+            ctx.resetSessionTokenUsage();
+            console.log(theme.success(`  \u2713 Restored to checkpoint "${name}" (${session.messages.length} messages, token usage reset)`));
           } else {
             ctx.renderer.renderError(`Checkpoint "${name}" not found.`);
           }
@@ -1925,17 +1942,21 @@ ${hint}` : "")
       name: "test",
       description: "Run project tests and show structured report",
       usage: "/test [command|filter]",
-      async execute(args, _ctx) {
-        const { executeTests } = await import("./run-tests-HP4MMQAP.js");
-        const argStr = args.join(" ").trim();
-        let testArgs = {};
-        if (argStr) {
-          const isCommand = argStr.includes(" ") || /^(mvn|gradle|npm|pytest|cargo|go)\b/.test(argStr);
-          testArgs = isCommand ? { command: argStr } : { filter: argStr };
-        }
-        const report = await executeTests(testArgs);
-        const firstLines = report.split("\n").slice(0, 3).join("\n");
-        console.log(theme.dim(firstLines));
+      async execute(args, ctx) {
+        try {
+          const { executeTests } = await import("./run-tests-ZTVEN2O7.js");
+          const argStr = args.join(" ").trim();
+          let testArgs = {};
+          if (argStr) {
+            const isCommand = argStr.includes(" ") || /^(mvn|gradle|npm|pytest|cargo|go)\b/.test(argStr);
+            testArgs = isCommand ? { command: argStr } : { filter: argStr };
+          }
+          const report = await executeTests(testArgs);
+          const firstLines = report.split("\n").slice(0, 3).join("\n");
+          console.log(theme.dim(firstLines));
+        } catch (err) {
+          ctx.renderer.renderError(`Test execution failed: ${err instanceof Error ? err.message : String(err)}`);
+        }
       }
     },
     {
@@ -2017,6 +2038,64 @@ ${hint}` : "")
         }
       }
     },
+    // ── /profile ───────────────────────────────────────────────────────────────
+    {
+      name: "profile",
+      description: 'View or edit your identity profile (the "soul" of AI)',
+      usage: "/profile [show|edit|set <field> <value>|clear]",
+      execute(args, ctx) {
+        const sub = args[0] ?? "show";
+        const profile = ctx.config.get("userProfile") ?? {};
+        if (sub === "show" || sub === "view") {
+          const hasProfile = profile.name || profile.nickname || profile.role;
+          if (!hasProfile) {
+            console.log(theme.dim("\n  No profile configured yet. Use /profile edit or /config to set up.\n"));
+            return;
+          }
+          console.log(theme.heading("\n\u{1F464} Your Profile\n") + theme.dim("\u2500".repeat(50)));
+          if (profile.name) console.log(`  ${theme.dim("Name:")}      ${chalk2.white(profile.name)}`);
+          if (profile.nickname) console.log(`  ${theme.dim("Nickname:")}  ${theme.accent(profile.nickname)}`);
+          if (profile.role) console.log(`  ${theme.dim("Role:")}      ${chalk2.white(profile.role)}`);
+          if (profile.bio) console.log(`  ${theme.dim("Bio:")}       ${chalk2.white(profile.bio)}`);
+          if (profile.interests?.length) console.log(`  ${theme.dim("Interests:")} ${chalk2.white(profile.interests.join(", "))}`);
+          if (profile.locale) console.log(`  ${theme.dim("Locale:")}    ${chalk2.white(profile.locale)}`);
+          if (profile.extra) console.log(`  ${theme.dim("Extra:")}     ${chalk2.white(profile.extra.slice(0, 80))}${profile.extra.length > 80 ? "\u2026" : ""}`);
+          console.log(theme.dim("\u2500".repeat(50)));
+          console.log(theme.dim("  This identity is injected into every AI conversation.\n"));
+        } else if (sub === "edit") {
+          ctx.renderer.printInfo("Use /config to open the interactive profile editor, or use:\n  /profile set <field> <value>\n  Fields: name, nickname, role, bio, interests, locale, extra");
+        } else if (sub === "set") {
+          const field = args[1];
+          const value = args.slice(2).join(" ").trim();
+          const validFields = ["name", "nickname", "role", "bio", "interests", "locale", "extra"];
+          if (!field || !validFields.includes(field)) {
+            ctx.renderer.printInfo(`Usage: /profile set <field> <value>
+  Fields: ${validFields.join(", ")}`);
+            return;
+          }
+          if (!value) {
+            ctx.renderer.printInfo(`Usage: /profile set ${field} <value>`);
+            return;
+          }
+          const updated = { ...profile };
+          if (field === "interests") {
+            updated.interests = value.split(",").map((s) => s.trim()).filter(Boolean);
+          } else {
+            updated[field] = value;
+          }
+          ctx.config.set("userProfile", updated);
+          ctx.config.save();
+          const displayVal = field === "interests" ? updated.interests : value;
+          ctx.renderer.printSuccess(`Profile updated: ${field} = ${JSON.stringify(displayVal)}`);
+        } else if (sub === "clear") {
+          ctx.config.set("userProfile", {});
+          ctx.config.save();
+          ctx.renderer.printSuccess("Profile cleared. AI will no longer know who you are.");
+        } else {
+          ctx.renderer.printInfo("Usage: /profile [show|edit|set <field> <value>|clear]");
+        }
+      }
+    },
     // ── /memory ────────────────────────────────────────────────────────────────
     {
       name: "memory",
@@ -2993,8 +3072,10 @@ var SetupWizard = class {
   }
   async runFirstRun() {
     console.log(theme.heading("\nWelcome to ai-cli!\n"));
-    console.log("Let's set up your first AI provider.\n");
+    console.log("Let's get to know you first, then set up your AI provider.\n");
     try {
+      await this.setupProfile();
+      console.log();
       const providerId = await select({
         message: "Which AI provider do you want to set up first?",
         choices: PROVIDERS
@@ -3002,7 +3083,11 @@ var SetupWizard = class {
       await this.setupProvider(providerId);
       this.config.set("defaultProvider", providerId);
       this.config.save();
-      console.log(theme.success("\nSetup complete! Starting ai-cli...\n"));
+      const nickname = this.config.get("userProfile")?.nickname;
+      const greeting = nickname ? `Setup complete, ${nickname}!` : "Setup complete!";
+      console.log(theme.success(`
+${greeting} Starting ai-cli...
+`));
       return true;
     } catch {
       return false;
@@ -3015,9 +3100,12 @@ var SetupWizard = class {
       const currentProxy = this.config.get("proxy") ?? "";
       const proxyStatus = currentProxy ? theme.success(`[${currentProxy}]`) : theme.dim("[not configured]");
       const googleKeyStatus = this.config.getApiKey("google-search") ? theme.success("[configured]") : theme.dim("[not configured]");
+      const profileName = this.config.get("userProfile")?.nickname || this.config.get("userProfile")?.name;
+      const profileStatus = profileName ? theme.success(`[${profileName}]`) : theme.dim("[not configured]");
       const action = await select({
         message: "What would you like to configure?",
         choices: [
+          { value: "profile", name: `Edit your profile (identity)  ${profileStatus}` },
           { value: "apikey", name: "Manage API key for a provider" },
           { value: "default", name: "Change default provider" },
           { value: "proxy", name: `Configure proxy (HTTP/HTTPS)  ${proxyStatus}` },
@@ -3025,7 +3113,9 @@ var SetupWizard = class {
           { value: "done", name: "Done" }
         ]
       });
-      if (action === "proxy") {
+      if (action === "profile") {
+        await this.setupProfile();
+      } else if (action === "proxy") {
         await this.setupProxy();
       } else if (action === "google") {
         await this.setupGoogleSearch();
@@ -3198,6 +3288,50 @@ Managing ${displayName} API Key`);
     }
     console.log();
   }
+  /** 收集用户身份档案 — aicli 的 "灵魂" 功能 */
+  async setupProfile() {
+    const existing = this.config.get("userProfile") ?? {};
+    console.log(theme.heading("\n\u{1F464} Your Profile"));
+    console.log(theme.dim("  This helps AI know who you are \u2014 across all providers and sessions.\n"));
+    const name = await input({
+      message: "Your name:",
+      default: existing.name || void 0
+    });
+    const nickname = await input({
+      message: "Preferred nickname (AI will call you this):",
+      default: existing.nickname || void 0
+    });
+    const role = await input({
+      message: 'Your role (e.g. "Full-stack developer", "Student"):',
+      default: existing.role || void 0
+    });
+    const bio = await input({
+      message: "Brief intro (1-2 sentences about your background):",
+      default: existing.bio || void 0
+    });
+    const interestsStr = await input({
+      message: "Interests / tech stack (comma-separated):",
+      default: existing.interests?.join(", ") || void 0
+    });
+    const locale = await input({
+      message: 'Preferred language (e.g. "zh-CN", "en", "ja"):',
+      default: existing.locale || void 0
+    });
+    const profile = {};
+    if (name) profile.name = name;
+    if (nickname) profile.nickname = nickname;
+    if (role) profile.role = role;
+    if (bio) profile.bio = bio;
+    if (interestsStr) profile.interests = interestsStr.split(",").map((s) => s.trim()).filter(Boolean);
+    if (locale) profile.locale = locale;
+    if (existing.extra) profile.extra = existing.extra;
+    this.config.set("userProfile", profile);
+    this.config.save();
+    const displayName = nickname || name || "User";
+    console.log(theme.success(`
+  Profile saved! AI will know you as "${displayName}".
+`));
+  }
 };
 
 // src/repl/custom-commands.ts
@@ -3857,7 +3991,15 @@ You have a maximum of ${MAX_TOOL_ROUNDS} tool call rounds per conversation turn.
 - On Windows, use PowerShell cmdlets (Invoke-RestMethod, Get-ChildItem) instead of Unix commands (curl, grep, find).
 - If starting a long-running server process via bash, use background execution \u2014 do not block the tool round.
 - Prioritize the most critical tasks first in case you run out of rounds.`;
-    const parts = [dateTimeInfo + "\n" + envInfo, AGENTIC_BEHAVIOR_GUIDELINE + budgetInfo];
+    const parts = [dateTimeInfo + "\n" + envInfo];
+    const userProfile = this.config.get("userProfile");
+    if (userProfile) {
+      const identityPrompt = buildUserIdentityPrompt(userProfile);
+      if (identityPrompt) {
+        parts.push(identityPrompt);
+      }
+    }
+    parts.push(AGENTIC_BEHAVIOR_GUIDELINE + budgetInfo);
     const memory = this.loadMemoryContent();
     if (memory) {
       parts.push(`# Persistent Memory
@@ -4097,7 +4239,8 @@ Session '${this.resumeSessionId}' not found.
     const pluginCount = await this.toolRegistry.loadPlugins(this.config.getPluginsDir(), allowPlugins);
     const welcomeProvider = this.providers.get(this.currentProvider);
     const welcomeModelInfo = welcomeProvider?.info.models.find((m) => m.id === this.currentModel);
-    this.renderer.printWelcome(this.currentProvider, this.currentModel, welcomeModelInfo?.contextWindow);
+    const profileNickname = this.config.get("userProfile")?.nickname || this.config.get("userProfile")?.name;
+    this.renderer.printWelcome(this.currentProvider, this.currentModel, welcomeModelInfo?.contextWindow, profileNickname);
     if (welcomeModelInfo?.contextWindow) setContextWindow(welcomeModelInfo.contextWindow);
     if (this.resumeSessionId) {
       const session = this.sessions.current;
@@ -5548,7 +5691,7 @@ program.command("web").description("Start Web UI server with browser-based chat
     console.error("Error: Invalid port number. Must be between 1 and 65535.");
     process.exit(1);
   }
-  const { startWebServer } = await import("./server-JFLTWF7Q.js");
+  const { startWebServer } = await import("./server-IDPMZAUF.js");
   await startWebServer({ port, host: options.host });
 });
 program.command("user [action] [username]").description("Manage Web UI users (list | create <name> | delete <name> | reset-password <name> | migrate <name>)").action(async (action, username) => {
@@ -5781,7 +5924,7 @@ program.command("hub [topic]").description("Start multi-agent hub (discuss / bra
     }),
     config.get("customProviders")
   );
-  const { startHub } = await import("./hub-RJRNBB5G.js");
+  const { startHub } = await import("./hub-CNSFX47B.js");
   await startHub(
     {
       topic: topic ?? "",

package/dist/{run-tests-AUTWQ5NB.js → run-tests-3PLCZ4P3.js}

@@ -1,7 +1,7 @@
 import {
   executeTests,
   runTestsTool
-} from "./chunk-6WLDJKHU.js";
+} from "./chunk-6CJX3RST.js";
 export {
   executeTests,
   runTestsTool

package/dist/{run-tests-HP4MMQAP.js → run-tests-ZTVEN2O7.js}

@@ -2,7 +2,7 @@
 import {
   executeTests,
   runTestsTool
-} from "./chunk-JNAZORS2.js";
+} from "./chunk-AR656G5C.js";
 export {
   executeTests,
   runTestsTool

package/dist/{server-JFLTWF7Q.js → server-IDPMZAUF.js}

@@ -18,7 +18,7 @@ import {
   renderDiff,
   runHook,
   setupProxy
-} from "./chunk-DBEYB76P.js";
+} from "./chunk-7T2W4LN3.js";
 import {
   AuthManager
 } from "./chunk-BYNY5JPB.js";
@@ -32,7 +32,7 @@ import {
   spawnAgentContext,
   truncateOutput,
   undoStack
-} from "./chunk-PR5JZVNN.js";
+} from "./chunk-2JOMWVTE.js";
 import {
   AGENTIC_BEHAVIOR_GUIDELINE,
   AUTHOR,
@@ -48,8 +48,9 @@ import {
   PLAN_MODE_SYSTEM_ADDON,
   PLUGINS_DIR_NAME,
   SKILLS_DIR_NAME,
-  VERSION
-} from "./chunk-JNAZORS2.js";
+  VERSION,
+  buildUserIdentityPrompt
+} from "./chunk-AR656G5C.js";
 
 // src/web/server.ts
 import express from "express";
@@ -396,7 +397,14 @@ function buildSystemPrompt(ctx) {
   const envInfo = `OS: ${osName}
 ${shellInfo}
 Working directory: ${process.cwd()}`;
-  const parts = [dateTimeInfo + "\n" + envInfo, AGENTIC_BEHAVIOR_GUIDELINE];
+  const parts = [dateTimeInfo + "\n" + envInfo];
+  if (ctx.userProfile) {
+    const identityPrompt = buildUserIdentityPrompt(ctx.userProfile);
+    if (identityPrompt) {
+      parts.push(identityPrompt);
+    }
+  }
+  parts.push(AGENTIC_BEHAVIOR_GUIDELINE);
   if (ctx.configDir) {
     const memory = loadMemoryContent(ctx.configDir);
     if (memory) {
@@ -1490,7 +1498,7 @@ ${undoResults.map((r) => `  \u2022 ${r}`).join("\n")}` });
       case "test": {
         this.send({ type: "info", message: "\u{1F9EA} Running tests..." });
         try {
-          const { executeTests } = await import("./run-tests-HP4MMQAP.js");
+          const { executeTests } = await import("./run-tests-ZTVEN2O7.js");
           const argStr = args.join(" ").trim();
           let testArgs = {};
           if (argStr) {
@@ -2041,7 +2049,8 @@ Add .md files to create commands.` });
       activeSystemPrompt: this.activeSystemPrompt,
       activeSkill,
       planMode: this.planMode,
-      configDir: this.config.getConfigDir()
+      configDir: this.config.getConfigDir(),
+      userProfile: this.config.get("userProfile")
     });
     if (this.addedDirs.size > 0) {
       const MAX_DIR_CONTEXT = 4e4;

package/dist/{task-orchestrator-JKY2T2W3.js → task-orchestrator-UZQRB7AO.js}

@@ -4,10 +4,10 @@ import {
   getDangerLevel,
   googleSearchContext,
   truncateOutput
-} from "./chunk-PR5JZVNN.js";
+} from "./chunk-2JOMWVTE.js";
 import {
   SUBAGENT_ALLOWED_TOOLS
-} from "./chunk-JNAZORS2.js";
+} from "./chunk-AR656G5C.js";
 
 // src/hub/task-orchestrator.ts
 import { createInterface } from "readline";

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "jinzd-ai-cli",
-  "version": "0.4.19",
+  "version": "0.4.21",
   "description": "Cross-platform REPL-style AI CLI with multi-provider support",
   "type": "module",
   "main": "./dist/index.js",