[Refactor] 리팩터링

lib/agents/__init__.py

@@ -0,0 +1,9 @@
+from lib.agents.get_sso_list import get_sso_list
+# 버전 업데이트 대비
+from lib.agents.get_sso_list_v2 import get_sso_list as get_sso_list_v2
+from lib.agents.login_google import login_google
+
+__all__ = [
+    "get_sso_list",
+    "login_google",
+]

lib/agents/get_sso_list.py

@@ -1,41 +0,0 @@
-import json
-from pydantic import BaseModel
-from lib.prompt.get_sso_list import get_sso_list_task
-
-from lib.browser_use_utils.run_task import run_task
-
-
-NOT_FOUND_LOGIN_PAGE = 0
-FOUND_LOGIN_PAGE = 1
-
-class FindLoginPageResponse(BaseModel):
-    status: int = NOT_FOUND_LOGIN_PAGE  # 0 if not found, 1 if found
-    msg: str | None = None
-    url: str | None = None
-    sso_list: list[str] = []  # List of SSO providers found on the login page
-
-async def get_sso_list(target_url) -> tuple[bool, str | FindLoginPageResponse | None]:
-
-    task = get_sso_list_task
-    ReturnModel = FindLoginPageResponse
-    success, response = await run_task(target_url, ReturnModel, task)
-    if not success:
-        return False, response
-    if isinstance(response, str):
-        return False, response
-    if isinstance(response, FindLoginPageResponse):
-        if response.status == FOUND_LOGIN_PAGE:
-            if not response.sso_list:
-                response.msg = "로그인 페이지는 찾았지만 SSO 제공자가 없습니다."
-            else:
-                response.msg = "로그인 페이지와 SSO 제공자를 찾았습니다."
-        else:
-            response.msg = "로그인 페이지를 찾지 못했습니다."
-    else:
-        return False, "응답 형식이 올바르지 않습니다. FindLoginPageResponse가 아닙니다."
-    
-    return True, response
-    
-    
-
-    

lib/agents/get_sso_list/__init__.py

@@ -0,0 +1,3 @@
+from lib.agents.get_sso_list.get_sso_list import get_sso_list
+
+__all__ = ["get_sso_list"]

lib/agents/get_sso_list/get_sso_list.py

@@ -0,0 +1,22 @@
+from lib.agents.get_sso_list.prompt import get_sso_list_task, FindLoginPageResponse
+from lib.browser_use_utils.run_task import run_task
+
+
+NOT_FOUND_LOGIN_PAGE = 0
+FOUND_LOGIN_PAGE = 1
+
+async def get_sso_list(target_url) -> tuple[bool, str | FindLoginPageResponse | None]:
+
+    task = get_sso_list_task
+    ReturnModel = FindLoginPageResponse
+    success, response = await run_task(target_url, ReturnModel, task)
+    if not success:
+        return False, response
+    if isinstance(response, str):
+        return False, response
+    
+    return True, response
+    
+    
+
+    

lib/agents/get_sso_list/prompt.py

@@ -0,0 +1,68 @@
+from pydantic import BaseModel
+
+class FindLoginPageResponse(BaseModel):
+    msg: str | None = None
+    url: str | None = None
+    sso_list: list[str] = []  # List of SSO providers found on the login page
+
+get_sso_list_task = """
+You are an expert in finding login pages.
+
+Your task is to navigate to the login page of the given URL. Follow the steps below strictly and return results only in the specified format.
+
+※ You are NOT allowed to navigate to URLs that are not directly discoverable within the initial domain. Do NOT use search engines or guess external login URLs.
+
+0. INITIAL BLOCK CHECK
+- If the browser is blocked when trying to access the page — due to firewall, CAPTCHA, regional restrictions, or other access denials — immediately terminate the process and return the following JSON:
+    ```json
+    {
+        "msg": "Blocked",
+        "url": "",
+        "sso_list": []
+    }
+    ```
+- Do NOT proceed to further steps in this case.
+
+1. LOGIN PAGE NAVIGATION
+- Navigate only to a **client-side (non-enterprise)** login page within the provided domain.
+- Do NOT rely on external tools, search engines, or links not directly found on the site.
+- If a consent popup (e.g. for privacy/cookies) appears, you MUST dismiss or close it before proceeding.
+- Since step 0 confirmed access, assume the page now loads properly.
+
+2. SSO BUTTON IDENTIFICATION
+- On the login page, look for the following social login (SSO) buttons:
+  - Google, GitHub, Facebook, LinkedIn, Microsoft, Naver, Slack, Etc.
+- ✅ Proceed only if it is clearly an **actual SSO button**.
+- ❌ Exclude the following:
+  - Passkey-related buttons
+  - Username/password fields
+  - Email-based login
+  - Non-OAuth methods such as certificate or phone verification
+
+3. RETURN FORMAT
+- If the login page is successfully found, return:
+    ```json
+    {
+        "msg": "Login page found",
+        "url": "https://example.com/login",
+        "sso_list": ["Google", "GitHub"]
+    }
+    ```
+- If the login page cannot be found, return:
+    ```json
+    {
+        "msg": "Login page not found",
+        "url": "",
+        "sso_list": []
+    }
+    ```
+- If blocked (as in step 0), return:
+    ```json
+    {
+        "msg": "Blocked",
+        "url": "",
+        "sso_list": []
+    }
+    ```
+- Return ONLY the JSON object. Do NOT include any explanation, logging, or extra output.
+"""

lib/agents/get_sso_list_v2/__init__.py

@@ -0,0 +1,3 @@
+from lib.agents.get_sso_list_v2 import get_sso_list
+
+__all__ = ["get_sso_list"]

lib/agents/get_sso_list_v2/get_sso_list.py

@@ -0,0 +1,20 @@
+from lib.agents.get_sso_list_v2.prompt import get_sso_list_task, FindLoginPageResponse
+from lib.browser_use_utils.run_task import run_task
+
+# TODO - Split find login page agent and get SSO list agent
+
+async def get_sso_list(target_url) -> tuple[bool, str | FindLoginPageResponse | None]:
+
+    task = get_sso_list_task
+    ReturnModel = FindLoginPageResponse
+    success, response = await run_task(target_url, ReturnModel, task)
+    if not success:
+        return False, response
+    if isinstance(response, str):
+        return False, response
+    
+    return True, response
+    
+    
+
+    

lib/agents/get_sso_list_v2/prompt.py

@@ -0,0 +1,68 @@
+from pydantic import BaseModel
+
+class FindLoginPageResponse(BaseModel):
+    msg: str | None = None
+    url: str | None = None
+    sso_list: list[str] = []  # List of SSO providers found on the login page
+
+get_sso_list_task = """
+You are an expert in finding login pages.
+
+Your task is to navigate to the login page of the given URL. Follow the steps below strictly and return results only in the specified format.
+
+※ You are NOT allowed to navigate to URLs that are not directly discoverable within the initial domain. Do NOT use search engines or guess external login URLs.
+
+0. INITIAL BLOCK CHECK
+- If the browser is blocked when trying to access the page — due to firewall, CAPTCHA, regional restrictions, or other access denials — immediately terminate the process and return the following JSON:
+    ```json
+    {
+        "msg": "Blocked",
+        "url": "",
+        "sso_list": []
+    }
+    ```
+- Do NOT proceed to further steps in this case.
+
+1. LOGIN PAGE NAVIGATION
+- Navigate only to a **client-side (non-enterprise)** login page within the provided domain.
+- Do NOT rely on external tools, search engines, or links not directly found on the site.
+- If a consent popup (e.g. for privacy/cookies) appears, you MUST dismiss or close it before proceeding.
+- Since step 0 confirmed access, assume the page now loads properly.
+
+2. SSO BUTTON IDENTIFICATION
+- On the login page, look for the following social login (SSO) buttons:
+  - Google, GitHub, Facebook, LinkedIn, Microsoft, Naver, Slack, Etc.
+- ✅ Proceed only if it is clearly an **actual SSO button**.
+- ❌ Exclude the following:
+  - Passkey-related buttons
+  - Username/password fields
+  - Email-based login
+  - Non-OAuth methods such as certificate or phone verification
+
+3. RETURN FORMAT
+- If the login page is successfully found, return:
+    ```json
+    {
+        "msg": "Login page found",
+        "url": "https://example.com/login",
+        "sso_list": ["Google", "GitHub"]
+    }
+    ```
+- If the login page cannot be found, return:
+    ```json
+    {
+        "msg": "Login page not found",
+        "url": "",
+        "sso_list": []
+    }
+    ```
+- If blocked (as in step 0), return:
+    ```json
+    {
+        "msg": "Blocked",
+        "url": "",
+        "sso_list": []
+    }
+    ```
+- Return ONLY the JSON object. Do NOT include any explanation, logging, or extra output.
+"""

lib/agents/login_google/__init__.py

@@ -0,0 +1,3 @@
+from lib.agents.login_google.login_google import login_google
+
+__all__ = ["login_google"]

lib/agents/login_google/login_google.py

@@ -0,0 +1,11 @@
+from lib.agents.login_google.prompt import login_google_task, LoginGoogleResponse
+from lib.browser_use_utils.run_task import run_task
+
+async def login_google(target_url) -> tuple[bool, str | LoginGoogleResponse | None]:
+    task = login_google_task
+    ReturnModel = LoginGoogleResponse
+    success, response = await run_task(target_url, ReturnModel, task)
+    if not success:
+        return False, None
+
+    return True, response

lib/agents/login_google/prompt.py

@@ -0,0 +1,60 @@
+from pydantic import BaseModel
+from lib.config import GOOGLE_ID, GOOGLE_PASSWORD
+
+class LoginGoogleResponse(BaseModel):
+    msg: str | None = None
+    status: str | None = None  # "success", "mfa_required", "google_blocked", "sso_not_found", "login_page_not_found", "invalid_credentials"
+    final_url: str | None = None
+
+login_google_task = f"""
+You are a web automation agent.
+
+Your task is to visit the given domain and perform a full login via the **Google SSO button**, following all steps strictly as described below.
+
+▶ Target: Find a login page inside this domain that allows "Sign in with Google", and use it to complete login via Google.
+
+Instructions:
+
+1. If any cookie or privacy popups appear, dismiss or accept them.
+2. Navigate through the site's UI to find the **login or sign-in page** (e.g., via buttons like "Log In", "Sign In", "Get Started").
+    - Only follow links within the same domain.
+3. On the login page, look for a clearly labeled **Google SSO button** — typically labeled as:
+    - "Continue with Google"
+    - "Sign in with Google"
+    - or a button with the Google 'G' icon
+4. Click the **Google login button**.
+    - ⚠️ The Google login flow MUST open in a **new browser tab** (not a new window or popup).
+    - ❌ If the login opens in a new **window** or **popup**, do NOT continue. Immediately stop and return the appropriate status.
+5. Check if the user is **already logged in to Google and immediately redirected back to the original site** without showing a Google login screen.
+    - ✅ If so, treat the login as successful and return immediately.
+6. If redirected to the Google login page:
+    - If a **CAPTCHA**, **MFA prompt**, or a request for **ID/password entry** appears, do NOT proceed.
+    - Immediately stop and return the appropriate status.
+7. If login proceeds without interruptions, wait for redirection back to the original site and record the final URL.
+
+Credentials to use (only if needed):
+- Email: {GOOGLE_ID}
+- Password: {GOOGLE_PASSWORD}
+
+Constraints:
+- Do NOT use search engines or guess URLs — only navigate links discoverable from https://example.com
+- Do NOT use autofill, saved sessions, or cookies.
+- Do NOT proceed with login if:
+    - The login opens in a new window (only tabs are allowed)
+    - CAPTCHA or MFA appears
+    - ID/password input is required
+- If the user is already logged in to Google and redirected back automatically, stop there and report success.
+
+Final Output:
+Return the result in the following format only:
+
+```json
+{{
+    "msg": "Google login completed",
+    "status": "success" | "already_logged_in" | "mfa_required" | "captcha_triggered" | "window_blocked" | "idpw_required" | "google_blocked" | "sso_not_found" | "login_page_not_found",
+    "final_url": "<url_after_login_redirect or empty string>"
+}}
+```
+
+- Return ONLY the JSON object. Do NOT include any explanation, logging, or extra output.
+"""