foliko 2.0.17 → 2.0.19

package/skills/find-skills/SKILL.md

@@ -1,133 +1,133 @@
----
-name: find-skills
-description: Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
----
-
-# Find Skills
-
-This skill helps you discover and install skills from the open agent skills ecosystem.
-
-## When to Use This Skill
-
-Use this skill when the user:
-
-- Asks "how do I do X" where X might be a common task with an existing skill
-- Says "find a skill for X" or "is there a skill for X"
-- Asks "can you do X" where X is a specialized capability
-- Expresses interest in extending agent capabilities
-- Wants to search for tools, templates, or workflows
-- Mentions they wish they had help with a specific domain (design, testing, deployment, etc.)
-
-## What is the Skills CLI?
-
-The Skills CLI (`npx skills`) is the package manager for the open agent skills ecosystem. Skills are modular packages that extend agent capabilities with specialized knowledge, workflows, and tools.
-
-**Key commands:**
-
-- `npx skills find [query]` - Search for skills interactively or by keyword
-- `npx skills add <package>` - Install a skill from GitHub or other sources
-- `npx skills check` - Check for skill updates
-- `npx skills update` - Update all installed skills
-
-**Browse skills at:** https://skills.sh/
-
-## How to Help Users Find Skills
-
-### Step 1: Understand What They Need
-
-When a user asks for help with something, identify:
-
-1. The domain (e.g., React, testing, design, deployment)
-2. The specific task (e.g., writing tests, creating animations, reviewing PRs)
-3. Whether this is a common enough task that a skill likely exists
-
-### Step 2: Search for Skills
-
-Run the find command with a relevant query:
-
-```bash
-npx skills find [query]
-```
-
-For example:
-
-- User asks "how do I make my React app faster?" → `npx skills find react performance`
-- User asks "can you help me with PR reviews?" → `npx skills find pr review`
-- User asks "I need to create a changelog" → `npx skills find changelog`
-
-The command will return results like:
-
-```
-Install with npx skills add <owner/repo@skill>
-
-vercel-labs/agent-skills@vercel-react-best-practices
-└ https://skills.sh/vercel-labs/agent-skills/vercel-react-best-practices
-```
-
-### Step 3: Present Options to the User
-
-When you find relevant skills, present them to the user with:
-
-1. The skill name and what it does
-2. The install command they can run
-3. A link to learn more at skills.sh
-
-Example response:
-
-```
-I found a skill that might help! The "vercel-react-best-practices" skill provides
-React and Next.js performance optimization guidelines from Vercel Engineering.
-
-To install it:
-npx skills add vercel-labs/agent-skills@vercel-react-best-practices
-
-Learn more: https://skills.sh/vercel-labs/agent-skills/vercel-react-best-practices
-```
-
-### Step 4: Offer to Install
-
-If the user wants to proceed, you can install the skill for them:
-
-```bash
-npx skills add <owner/repo@skill> -g -y
-```
-
-The `-g` flag installs globally (user-level) and `-y` skips confirmation prompts.
-
-## Common Skill Categories
-
-When searching, consider these common categories:
-
-| Category        | Example Queries                          |
-| --------------- | ---------------------------------------- |
-| Web Development | react, nextjs, typescript, css, tailwind |
-| Testing         | testing, jest, playwright, e2e           |
-| DevOps          | deploy, docker, kubernetes, ci-cd        |
-| Documentation   | docs, readme, changelog, api-docs        |
-| Code Quality    | review, lint, refactor, best-practices   |
-| Design          | ui, ux, design-system, accessibility     |
-| Productivity    | workflow, automation, git                |
-
-## Tips for Effective Searches
-
-1. **Use specific keywords**: "react testing" is better than just "testing"
-2. **Try alternative terms**: If "deploy" doesn't work, try "deployment" or "ci-cd"
-3. **Check popular sources**: Many skills come from `vercel-labs/agent-skills` or `ComposioHQ/awesome-claude-skills`
-
-## When No Skills Are Found
-
-If no relevant skills exist:
-
-1. Acknowledge that no existing skill was found
-2. Offer to help with the task directly using your general capabilities
-3. Suggest the user could create their own skill with `npx skills init`
-
-Example:
-
-```
-I searched for skills related to "xyz" but didn't find any matches.
-I can still help you with this task directly! Would you like me to proceed?
-
-If this is something you do often, you could create your own skill:
-npx skills init my-xyz-skill
-```
+---
+name: find-skills
+description: Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
+---
+
+# Find Skills
+
+This skill helps you discover and install skills from the open agent skills ecosystem.
+
+## When to Use This Skill
+
+Use this skill when the user:
+
+- Asks "how do I do X" where X might be a common task with an existing skill
+- Says "find a skill for X" or "is there a skill for X"
+- Asks "can you do X" where X is a specialized capability
+- Expresses interest in extending agent capabilities
+- Wants to search for tools, templates, or workflows
+- Mentions they wish they had help with a specific domain (design, testing, deployment, etc.)
+
+## What is the Skills CLI?
+
+The Skills CLI (`npx skills`) is the package manager for the open agent skills ecosystem. Skills are modular packages that extend agent capabilities with specialized knowledge, workflows, and tools.
+
+**Key commands:**
+
+- `npx skills find [query]` - Search for skills interactively or by keyword
+- `npx skills add <package>` - Install a skill from GitHub or other sources
+- `npx skills check` - Check for skill updates
+- `npx skills update` - Update all installed skills
+
+**Browse skills at:** https://skills.sh/
+
+## How to Help Users Find Skills
+
+### Step 1: Understand What They Need
+
+When a user asks for help with something, identify:
+
+1. The domain (e.g., React, testing, design, deployment)
+2. The specific task (e.g., writing tests, creating animations, reviewing PRs)
+3. Whether this is a common enough task that a skill likely exists
+
+### Step 2: Search for Skills
+
+Run the find command with a relevant query:
+
+```bash
+npx skills find [query]
+```
+
+For example:
+
+- User asks "how do I make my React app faster?" → `npx skills find react performance`
+- User asks "can you help me with PR reviews?" → `npx skills find pr review`
+- User asks "I need to create a changelog" → `npx skills find changelog`
+
+The command will return results like:
+
+```
+Install with npx skills add <owner/repo@skill>
+
+vercel-labs/agent-skills@vercel-react-best-practices
+└ https://skills.sh/vercel-labs/agent-skills/vercel-react-best-practices
+```
+
+### Step 3: Present Options to the User
+
+When you find relevant skills, present them to the user with:
+
+1. The skill name and what it does
+2. The install command they can run
+3. A link to learn more at skills.sh
+
+Example response:
+
+```
+I found a skill that might help! The "vercel-react-best-practices" skill provides
+React and Next.js performance optimization guidelines from Vercel Engineering.
+
+To install it:
+npx skills add vercel-labs/agent-skills@vercel-react-best-practices
+
+Learn more: https://skills.sh/vercel-labs/agent-skills/vercel-react-best-practices
+```
+
+### Step 4: Offer to Install
+
+If the user wants to proceed, you can install the skill for them:
+
+```bash
+npx skills add <owner/repo@skill> -g -y
+```
+
+The `-g` flag installs globally (user-level) and `-y` skips confirmation prompts.
+
+## Common Skill Categories
+
+When searching, consider these common categories:
+
+| Category        | Example Queries                          |
+| --------------- | ---------------------------------------- |
+| Web Development | react, nextjs, typescript, css, tailwind |
+| Testing         | testing, jest, playwright, e2e           |
+| DevOps          | deploy, docker, kubernetes, ci-cd        |
+| Documentation   | docs, readme, changelog, api-docs        |
+| Code Quality    | review, lint, refactor, best-practices   |
+| Design          | ui, ux, design-system, accessibility     |
+| Productivity    | workflow, automation, git                |
+
+## Tips for Effective Searches
+
+1. **Use specific keywords**: "react testing" is better than just "testing"
+2. **Try alternative terms**: If "deploy" doesn't work, try "deployment" or "ci-cd"
+3. **Check popular sources**: Many skills come from `vercel-labs/agent-skills` or `ComposioHQ/awesome-claude-skills`
+
+## When No Skills Are Found
+
+If no relevant skills exist:
+
+1. Acknowledge that no existing skill was found
+2. Offer to help with the task directly using your general capabilities
+3. Suggest the user could create their own skill with `npx skills init`
+
+Example:
+
+```
+I searched for skills related to "xyz" but didn't find any matches.
+I can still help you with this task directly! Would you like me to proceed?
+
+If this is something you do often, you could create your own skill:
+npx skills init my-xyz-skill
+```

package/src/agent/chat.js

@@ -674,9 +674,16 @@ class AgentChatHandler extends EventEmitter {
   async *chatStream(message, options = {}) {
     const sessionId = options.sessionId || this.getDefaultSessionId();
     const framework = this.agent.framework;
+    // ★ 提到外层作用域，catch 中要回滚 userMessage 时需要访问
+    let messageStore = null;
+    let messages = null;
+    let userMessage = null;
 
     try {
-      const { messageStore, messages } = await this._prepareSession(message, sessionId);
+      const prepared = await this._prepareSession(message, sessionId);
+      messageStore = prepared.messageStore;
+      messages = prepared.messages;
+      userMessage = prepared.userMessage;
 
       if (!this._aiClient) {
         throw new Error('AI 客户端未配置');
@@ -806,7 +813,43 @@ class AgentChatHandler extends EventEmitter {
 
       const userMsg = messages[messages.length - finishMessages.length - 1];
       this.emit('message', { content: fullText, sessionId: sessionId, userMessage: userMsg });
+
+      // ★ 修复：成功路径才持久化。AI 失败时若 finally 也 save，
+      //   会把刚 push 的 userMessage 写盘 → 下次请求 loadHistory 再次
+      //   load 到，_prepareSession 再 push 一份 → 连续两条相同 user
+      //   → AI SDK 抛 "Invalid prompt: ModelMessage[] schema"
+      try {
+        await messageStore.save();
+      } catch (err) {
+        logger.error(`[${sessionId}] Failed to save message store: ${err.message}`);
+      }
     } catch (err) {
+      // ★ 修复：失败时打印 InvalidPromptError 的 cause（含 Zod issue 路径），
+      //   方便定位是哪条消息、哪个字段不匹配 ModelMessage[] schema
+      logger.error('[AgentChat] chatStream error:', err.message);
+      if (err.cause) {
+        const cause = err.cause;
+        if (cause.issues) {
+          for (const issue of cause.issues.slice(0, 5)) {
+            logger.error(
+              `[AgentChat] schema issue: path=${JSON.stringify(issue.path)} code=${issue.code} message=${issue.message}`
+            );
+          }
+        } else {
+          logger.error(`[AgentChat] error cause: ${cause.message || String(cause)}`);
+        }
+      }
+
+      // ★ 修复：失败时 ROLLBACK 掉本轮 push 的 userMessage
+      try {
+        if (messages && userMessage) {
+          const last = messages[messages.length - 1];
+          if (last && last.role === 'user' && last === userMessage) {
+            messages.pop();
+          }
+        }
+      } catch { /* ignore */ }
+
       // 统一错误处理：提取简洁消息并通过 yield 传递
       const friendlyMessage = err?.message?.split('\n')[0] || '未知错误';
 
@@ -815,11 +858,6 @@ class AgentChatHandler extends EventEmitter {
         this.emit('message:error', { sessionId, error: friendlyMessage, originalError: err });
       }
       yield { type: 'error', error: friendlyMessage };
-    } finally {
-      const messageStore = this._getSessionMessageStore(sessionId);
-      messageStore.save().catch((err) => {
-        logger.error(`[${sessionId}] Failed to save message store: ${err.message}`);
-      });
     }
   }
 
@@ -869,9 +907,16 @@ class AgentChatHandler extends EventEmitter {
    */
   async _processMessage(sessionId, message, options) {
     const framework = this.agent.framework;
+    // ★ 提到外层作用域，catch 中要回滚 userMessage 时需要访问
+    let messageStore = null;
+    let messages = null;
+    let userMessage = null;
 
     try {
-      const { messageStore, messages } = await this._prepareSession(message, sessionId);
+      const prepared = await this._prepareSession(message, sessionId);
+      messageStore = prepared.messageStore;
+      messages = prepared.messages;
+      userMessage = prepared.userMessage;
 
       if (!this._aiClient) {
         throw new Error('AI 客户端未配置');
@@ -927,28 +972,57 @@ class AgentChatHandler extends EventEmitter {
       const userMsg = messages[messages.length - result.response.messages.length - 1];
       this.emit('message', { content: result.text, sessionId: sessionId, userMessage: userMsg });
 
+      // ★ 修复：AI 调用成功后才持久化（之前 finally 总是 save，
+      //   会把刚 push 的 userMessage 写盘；下次请求 loadHistory 再次 load 到，
+      //   _prepareSession 又 push 一份 → 连续两条相同 user 消息 →
+      //   AI SDK 抛 "Invalid prompt: ModelMessage[] schema"）
+      try {
+        await messageStore.save();
+      } catch (err) {
+        logger.error(`[${sessionId}] Failed to save message store: ${err.message}`);
+      }
+
       return {
         success: true,
         message: cleanResponse(result.text || ''),
         stepCount: result.stepCount || 1,
       };
     } catch (err) {
+      // ★ 修复：失败时打印 InvalidPromptError 的 cause（含 Zod issue 路径），
+      //   方便定位是哪条消息、哪个字段不匹配 ModelMessage[] schema
       logger.error('[AgentChat] _processMessage error:', err.message);
+      if (err.cause) {
+        const cause = err.cause;
+        if (cause.issues) {
+          // ZodError：逐条打印
+          for (const issue of cause.issues.slice(0, 5)) {
+            logger.error(
+              `[AgentChat] schema issue: path=${JSON.stringify(issue.path)} code=${issue.code} message=${issue.message}`
+            );
+          }
+        } else {
+          logger.error(`[AgentChat] error cause: ${cause.message || String(cause)}`);
+        }
+      }
       const errorMsg = err.message || String(err);
 
+      // ★ 修复：失败时 ROLLBACK 掉本轮 push 的 userMessage，
+      //   避免下次请求把它从 jsonl load 出来再 push 一遍
+      try {
+        if (messages && userMessage) {
+          const last = messages[messages.length - 1];
+          if (last && last.role === 'user' && last === userMessage) {
+            messages.pop();
+          }
+        }
+      } catch { /* ignore */ }
+
       return {
         success: false,
         message: 'AI 服务暂时不可用，请稍后重试。',
         error: errorMsg,
         stepCount: 0,
       };
-    } finally {
-      const messageStore = this._getSessionMessageStore(sessionId);
-      try {
-        await messageStore.save();
-      } catch (err) {
-        logger.error(`[${sessionId}] Failed to save message store: ${err.message}`);
-      }
     }
   }
 
@@ -1006,9 +1080,44 @@ class AgentChatHandler extends EventEmitter {
       messages.length = 0;
       messages.push(...validated);
     }
+
+    // ★ 修复：去重末尾重复的 user 消息。
+    // 场景：AI 失败时上一轮已把 userMessage 持久化到 jsonl（或留在 messageStore 内存），
+    //   本次 _prepareSession 再次 loadHistory 又会拿到它；
+    //   如果再 push 一次，消息数组末尾出现两条相同 user，
+    //   AI SDK 抛 "Invalid prompt: ModelMessage[] schema"。
+    // 仅对"末尾连续 user"做去重；中间重复历史由 validateAll 处理。
+    if (messages.length > 0) {
+      const last = messages[messages.length - 1];
+      if (
+        last &&
+        last.role === 'user' &&
+        userMessage &&
+        userMessage.role === 'user' &&
+        this._isSameUserContent(last.content, userMessage.content)
+      ) {
+        logger.debug(`[_prepareSession] 去重末尾 user 消息（避免连续两条相同 user）`);
+        messages.pop();
+      }
+    }
     messages.push(userMessage);
 
-    return { messageStore, messages };
+    // ★ 返回 userMessage 引用，调用方（_processMessage）失败时需 rollback
+    return { messageStore, messages, userMessage };
+  }
+
+  /**
+   * 判断两个 user content 是否等价（用于末尾 user 去重）
+   * @private
+   */
+  _isSameUserContent(a, b) {
+    if (a === b) return true;
+    if (typeof a === 'string' && typeof b === 'string') return a === b;
+    try {
+      return JSON.stringify(a) === JSON.stringify(b);
+    } catch {
+      return false;
+    }
   }
 
   /**

package/src/session/session.js

@@ -54,7 +54,7 @@ class SessionManager {
     this.labelTimestampsById = new Map();
     this.leafId = null;
     this.sessionId = '';
-
+    this.fileName=''
     if (persist && sessionDir && !fs.existsSync(sessionDir)) {
       fs.mkdirSync(sessionDir, { recursive: true });
     }
@@ -84,6 +84,7 @@ class SessionManager {
       }
 
       const header = this.fileEntries.find(e => e.type === 'session');
+      this.fileName = path.basename(sessionFile);
       this.sessionId = header?.id || createSessionId();
 
       this._buildIndex();