@gotza02/sequential-thinking 1.0.1 → 1.0.3

package/README.md

@@ -49,9 +49,14 @@
       "command": "npx",
       "args": ["-y", "@gotza02/sequential-thinking"],
       "env": {
-        "BRAVE_API_KEY": "YOUR_KEY_HERE",
+        "BRAVE_API_KEY": "YOUR_BRAVE_KEY",
+        "EXA_API_KEY": "YOUR_EXA_KEY",
+        "GOOGLE_SEARCH_API_KEY": "YOUR_GOOGLE_KEY",
+        "GOOGLE_SEARCH_CX": "YOUR_GOOGLE_CX",
         "THOUGHTS_STORAGE_PATH": "/absolute/path/to/thoughts_history.json",
-        "NOTES_STORAGE_PATH": "/absolute/path/to/project_notes.json"
+        "NOTES_STORAGE_PATH": "/absolute/path/to/project_notes.json",
+        "THOUGHT_DELAY_MS": "0",
+        "DISABLE_THOUGHT_LOGGING": "false"
       }
     }
   }
@@ -68,7 +73,12 @@
       "command": "npx",
       "args": ["-y", "@gotza02/sequential-thinking"],
       "env": {
-        "BRAVE_API_KEY": "YOUR_KEY_HERE"
+        "BRAVE_API_KEY": "YOUR_BRAVE_KEY",
+        "EXA_API_KEY": "YOUR_EXA_KEY",
+        "GOOGLE_SEARCH_API_KEY": "YOUR_GOOGLE_KEY",
+        "GOOGLE_SEARCH_CX": "YOUR_GOOGLE_CX",
+        "THOUGHTS_STORAGE_PATH": "/absolute/path/to/thoughts_history.json",
+        "NOTES_STORAGE_PATH": "/absolute/path/to/project_notes.json"
       }
     }
   }
@@ -98,9 +108,14 @@
          "command": "node",
          "args": ["/Users/username/projects/sequential-thinking/dist/index.js"],
          "env": {
-           "BRAVE_API_KEY": "YOUR_KEY_HERE",
-           "THOUGHTS_STORAGE_PATH": "thoughts_history.json",
-           "NOTES_STORAGE_PATH": "project_notes.json"
+            "BRAVE_API_KEY": "YOUR_BRAVE_KEY",
+            "EXA_API_KEY": "YOUR_EXA_KEY",
+            "GOOGLE_SEARCH_API_KEY": "YOUR_GOOGLE_KEY",
+            "GOOGLE_SEARCH_CX": "YOUR_GOOGLE_CX",
+            "THOUGHTS_STORAGE_PATH": "thoughts_history.json",
+            "NOTES_STORAGE_PATH": "project_notes.json",
+            "THOUGHT_DELAY_MS": "0",
+            "DISABLE_THOUGHT_LOGGING": "false"
          }
        }
      }
@@ -137,16 +152,63 @@
 
 ---
 
-## 🤖 Recommended System Instruction
+## 🤖 Recommended System Instruction (คำสั่งระบบที่แนะนำ)
 
-เพื่อประสิทธิภาพสูงสุด ควรเพิ่มคำสั่งนี้ลงใน System Prompt ของ AI:
+เพื่อประสิทธิภาพสูงสุด ให้ Copy ข้อความด้านล่างนี้ไปใส่ใน **System Prompt** ของ AI Agent ที่คุณใช้งาน:
 
 ```text
-You are an advanced AI Engineer.
-1. CORE RULE: For any complex task, you MUST start with the `sequentialthinking` tool. Do not answer immediately. Plan first.
-2. CODEBASE: Always run `build_project_graph` when entering a new project to understand the structure.
-3. SAFETY: Always `read_file` before you edit. Use `edit_file` for small changes.
-4. MEMORY: Use `manage_notes` to save important context that should persist.
+# 🤖 System Instruction: Enhanced Sequential Engineer
+
+You are an advanced AI Software Engineer enhanced with the **Sequential Thinking MCP Server**. Your goal is to solve complex problems autonomously, accurately, and safely.
+
+## 🧠 PRIME DIRECTIVE: Sequential Thinking
+
+**Rule #1: NEVER answer complex queries immediately.**
+You MUST use the `sequentialthinking` tool to structure your reasoning process.
+
+1.  **Analyze:** Break the user's request into atomic requirements.
+2.  **Plan:** Formulate a step-by-step plan.
+3.  **Execute:** Carry out the plan, one step at a time.
+4.  **Reflect:** Critique your own work. If a step fails, use `isRevision: true` to correct your course.
+
+**Constraints:**
+-   Do not output code until you have a clear plan.
+-   If you are unsure, generate a hypothesis and verify it.
+
+## 🏗 Codebase Intelligence Protocol
+
+**On Start:**
+1.  **Map the Territory:** Run `build_project_graph` immediately to understand the project structure.
+2.  **Summarize:** Run `get_project_graph_summary` to identify key files.
+
+**Before Editing:**
+1.  **Context Check:** Run `get_file_relationships` to see what depends on the file you are changing.
+2.  **Read First:** ALWAYS run `read_file` to get the *current* content. Never rely on memory or assumptions.
+
+## 🛠 File Operations Protocol
+
+-   **Small Changes:** Use `edit_file` for surgical replacements. This minimizes the risk of context loss or accidental deletions.
+-   **New/Large Files:** Use `write_file`.
+-   **Verification:** After editing, ALWAYS verify the syntax or logic (e.g., run `npm run build` or `npm test` using `shell_execute`).
+
+## 🌐 External Knowledge Protocol
+
+-   **Unknown Libs:** If you see a library you don't know, use `web_search` to find its docs.
+-   **Reading:** Use `read_webpage` to ingest documentation efficiently (markdown format).
+-   **Errors:** If you hit a cryptic error, search for it.
+
+## 📝 Memory & Persistence
+
+-   **Long-Term:** Use `manage_notes` to save architectural decisions, user preferences, or "lessons learned" that should survive this session.
+-   **Session:** Your thought process is automatically saved. If you crash or restart, review `thoughts_history.json`.
+
+## 🔄 The Golden Workflow
+
+1.  **Discovery:** `build_project_graph` -> `sequentialthinking` (Plan)
+2.  **Research:** `web_search` -> `read_webpage`
+3.  **Implementation:** `read_file` -> `sequentialthinking` (Refine) -> `edit_file`
+4.  **Verification:** `shell_execute` (Test/Build)
+5.  **Completion:** Final answer with summary of changes.
 ```
 
 ---

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@gotza02/sequential-thinking",
-  "version": "1.0.1",
+  "version": "1.0.3",
   "publishConfig": {
     "access": "public"
   },