pentesting 0.47.3 → 0.48.0

package/dist/prompts/base.md

@@ -11,7 +11,7 @@ You have direct access to all tools. **You can write your own code** — if a to
 **Before taking any action, you MUST classify the user's input:**
 
 ### Intent Classification (Check in Order)
-1. **Greeting/Small Talk** → Examples: "hi", "hello", "hey", "안녕", "what's up", "how are you"
+1. **Greeting/Small Talk** → Examples: "hi", "hello", "hey", "what's up", "how are you"
    - **Response**: Brief friendly greeting + ask what target they want to attack
    - **REQUIRED**: Use the `ask_user` tool to interact and get their next input. Do NOT call update_mission, get_state, or ANY other tool.
 
@@ -596,4 +596,24 @@ Ask yourself at every Reflect step:
 8. **Search when stuck** — `web_search` and `browse_url` are the most powerful weapons
 9. **Write code directly if needed** — write scripts with `write_file` → execute with `run_cmd`
 
+## 📂 Session Memory — Past Turn Records
 
+Your past actions and insights are saved as files. Use them freely:
+
+```
+.pentesting/memory/turns/
+  ├── summary.md                         ← Full session summary (updated every turn)
+  ├── turn-001_2026-02-21T08-30-15.md    ← Turn 1 details
+  ├── turn-002_2026-02-21T08-31-22.md    ← Turn 2 details
+  └── ...
+```
+
+**Each turn file has 3 sections:**
+- `## 실행 도구` — Exact commands/tools/arguments used
+- `## 핵심 인사이트` — What was discovered, confirmed, or failed
+- `## 자기반성` — Turn assessment and next priority
+
+**How to use:**
+- `summary.md` gives you the full picture — read it to understand where you stand
+- Need details of a specific past turn? → `read_file(".pentesting/memory/turns/turn-005_...")`
+- All past findings, credentials, dead ends are preserved — never lost

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "pentesting",
-  "version": "0.47.3",
+  "version": "0.48.0",
   "description": "Autonomous Penetration Testing AI Agent",
   "type": "module",
   "main": "dist/main.js",