Feat/ads optimization role

[GYFX35]

Summary by Sourcery

Create a full-stack AI agent web application with multiple specialized roles, including a new ads optimization feature, complete with frontend interface, Flask backend, and containerized deployment support

New Features:

• Add Flask backend with an /api/execute endpoint supporting 15+ AI assistant roles (developer, debugger, marketer, system analyzer, designer, educator, cybersecurity, business, public services, git helper, scam tracker, automation, astronaut, medical, and ads optimization)
• Introduce a web-based frontend (HTML/CSS/JS) providing a grid UI to interact with each AI role
• Implement ads optimization agent to generate ad copy and keyword suggestions for a given product or service

Build:

• Add Dockerfile and Procfile to containerize the app with Gunicorn
• Include backend requirements.txt and .gitignore for project setup

Documentation:

• Overhaul README with detailed feature list, usage instructions, setup, and deployment guides

[sourcery-ai]

Reviewer's Guide

This PR introduces a full-stack multi-role AI Agent application: it restructures documentation, implements a unified backend /api/execute dispatcher with multiple agent handlers (including the new ads optimization role), builds a dynamic frontend interface to interact with each role, and adds containerization and deployment scaffolding.

Sequence diagram for unified agent request handling in backend

sequenceDiagram
    actor User
    participant Frontend
    participant Backend
    User->>Frontend: Select agent role and submit input
    Frontend->>Backend: POST /api/execute {role, prompt}
    alt Role is 'ads_optimization'
        Backend->>Backend: optimize_ads_agent(prompt)
    else Other role
        Backend->>Backend: <role>_agent(prompt)
    end
    Backend-->>Frontend: JSON response
    Frontend-->>User: Display agent response

Loading

Class diagram for agent dispatcher and handlers in backend

classDiagram
    class FlaskApp {
      +route /api/execute
      +render_template()
    }
    class AgentDispatcher {
      +execute(command)
    }
    class AgentHandler {
      +generate_website(prompt)
      +debug_code(prompt)
      +generate_social_media_post(prompt)
      +analyze_website(prompt)
      +designer_agent(prompt)
      +educator_agent(prompt)
      +cybersecurity_agent(prompt)
      +business_agent(prompt)
      +public_services_agent(prompt)
      +git_helper_agent(prompt)
      +scam_tracker_agent(prompt)
      +automation_agent(prompt)
      +medical_agent(prompt)
      +optimize_ads_agent(prompt)
    }
    FlaskApp --> AgentDispatcher
    AgentDispatcher --> AgentHandler
    AgentHandler <|.. optimize_ads_agent
    AgentHandler <|.. generate_website
    AgentHandler <|.. debug_code
    AgentHandler <|.. generate_social_media_post
    AgentHandler <|.. analyze_website
    AgentHandler <|.. designer_agent
    AgentHandler <|.. educator_agent
    AgentHandler <|.. cybersecurity_agent
    AgentHandler <|.. business_agent
    AgentHandler <|.. public_services_agent
    AgentHandler <|.. git_helper_agent
    AgentHandler <|.. scam_tracker_agent
    AgentHandler <|.. automation_agent
    AgentHandler <|.. medical_agent

Loading

File-Level Changes

Change	Details	Files
Overhauled project documentation	Expanded README to describe project overview and multi-role features Added usage instructions per agent and examples Included setup, installation, and deployment guides (Docker, Heroku)	README.md
Implemented backend execution endpoint with multi-role dispatch	Added Flask /api/execute route that routes requests by role Integrated 15+ agent functions with structured text and code responses, including new ads_optimization handler Added backend dependencies and Heroku Procfile	backend/main.py backend/requirements.txt Procfile
Built frontend UI with dynamic agent interactions	Created HTML template with grid-based agent sections, including Ads Optimization Styled layout, components, and loader in CSS Added JS event listeners and sendCommand logic for each role, handling code/text responses	frontend/templates/index.html frontend/static/css/style.css frontend/static/js/script.js
Configured containerization and deployment scaffolding	Added Dockerfile for building and running the app in a container Provided root index.html for GitHub Pages deployment test Included a .gitignore to exclude transient files	Dockerfile index.html .gitignore

---

Tips and commands

Interacting with Sourcery

• Trigger a new review: Comment @sourcery-ai review on the pull request.
• Continue discussions: Reply directly to Sourcery's review comments.
• Generate a GitHub issue from a review comment: Ask Sourcery to create an
  issue from a review comment by replying to it. You can also reply to a
  review comment with @sourcery-ai issue to create an issue from it.
• Generate a pull request title: Write @sourcery-ai anywhere in the pull
  request title to generate a title at any time. You can also comment
  @sourcery-ai title on the pull request to (re-)generate the title at any time.
• Generate a pull request summary: Write @sourcery-ai summary anywhere in
  the pull request body to generate a PR summary at any time exactly where you
  want it. You can also comment @sourcery-ai summary on the pull request to
  (re-)generate the summary at any time.
• Generate reviewer's guide: Comment @sourcery-ai guide on the pull
  request to (re-)generate the reviewer's guide at any time.
• Resolve all Sourcery comments: Comment @sourcery-ai resolve on the
  pull request to resolve all Sourcery comments. Useful if you've already
  addressed all the comments and don't want to see them anymore.
• Dismiss all Sourcery reviews: Comment @sourcery-ai dismiss on the pull
  request to dismiss all existing Sourcery reviews. Especially useful if you
  want to start fresh with a new review - don't forget to comment
  @sourcery-ai review to trigger a new review!

Customizing Your Experience

Access your dashboard to:

• Enable or disable review features such as the Sourcery-generated pull request
  summary, the reviewer's guide, and others.
• Change the review language.
• Add, remove or edit custom review instructions.
• Adjust other review settings.

Getting Help

• Contact our support team for questions or feedback.
• Visit our documentation for detailed guides and information.
• Keep in touch with the Sourcery team by following us on X/Twitter, LinkedIn or GitHub.

[guardrails]

⚠️ We detected 3 security issues in this pull request:

Insecure Access Control (1)

Severity	Details	Docs
High	Title: Missing User Instruction AI-services/Dockerfile Line 2 in 8759150 FROM python:3.11-slim	📚

More info on how to fix Insecure Access Control in Dockerfile.

---

Vulnerable Libraries (2)

Severity	Details
High	pkg:pypi/werkzeug@2.3.8 (t) upgrade to: 3.0.3
High	pkg:pypi/flask@2.2.2 (t) upgrade to: 2.3.2

More info on how to fix Vulnerable Libraries in Python.

---

👉 Go to the dashboard for detailed results.

📥 Happy? Share your feedback with us.

[sourcery-ai]

Hey there - I've reviewed your changes and found some issues that need to be addressed.

Blocking issues:

• User controlled data in methods like innerHTML, outerHTML or document.write is an anti-pattern that can lead to XSS vulnerabilities (link)
• User controlled data in a code.innerHTML is an anti-pattern that can lead to XSS vulnerabilities (link)
• HTML generation does not escape user-provided content. (link)
• Sanitization uses URL encoding for shell commands. (link)
• Frontend uses 'medical_info' role, backend expects 'medical'. (link)

General comments:

• Replace the long if/elif chain in execute() with a mapping of role names to handler functions to improve scalability.
• Ensure that role identifiers are consistent between the frontend (e.g. 'medical_info') and backend (expects 'medical') to prevent silent failures.
• Consider using a battle-tested syntax highlighting library instead of custom regexes to ensure robust multi-language support.

Prompt for AI Agents

Please address the comments from this code review:
## Overall Comments
- Replace the long if/elif chain in execute() with a mapping of role names to handler functions to improve scalability.
- Ensure that role identifiers are consistent between the frontend (e.g. 'medical_info') and backend (expects 'medical') to prevent silent failures.
- Consider using a battle-tested syntax highlighting library instead of custom regexes to ensure robust multi-language support.

## Individual Comments

### Comment 1
<location> `backend/main.py:64` </location>
<code_context>
+    }
+    return jsonify(response)
+
+def generate_website(prompt):
+    import datetime
+
+    # New: Check for Python script request
+    if 'python script' in prompt.lower():
+        script_prompt = prompt.lower().replace('python script to', '').strip()
+        py_script = f"""
+# This is a Python script generated by the AI Agent.
+# Your request was: '{script_prompt}'
+
+def main():
+    # A simple example: print "Hello, World!"
+    print("Hello, World!")
+
+if __name__ == "__main__":
+    main()
+"""
+        return {
+            "type": "code_single",
+            "payload": {
</code_context>

<issue_to_address>
Python script generation is hardcoded and not dynamic.

The generated script does not adapt to different prompts and always outputs the same code. Please consider implementing logic to generate scripts based on the user's request, or notify users when only a static template is provided.
</issue_to_address>

<suggested_fix>
<<<<<<< SEARCH
    if 'python script' in prompt.lower():
        script_prompt = prompt.lower().replace('python script to', '').strip()
        py_script = f"""
# This is a Python script generated by the AI Agent.
# Your request was: '{script_prompt}'

def main():
    # A simple example: print "Hello, World!"
    print("Hello, World!")

if __name__ == "__main__":
    main()
"""
        return {
            "type": "code_single",
            "payload": {
                "language": "python",
                "filename": "script.py",
                "content": py_script.strip()
            }
        }
=======
    if 'python script' in prompt.lower():
        script_prompt = prompt.lower().replace('python script to', '').strip()
        # Basic dynamic generation for demonstration
        if "print" in script_prompt:
            # Extract message to print
            import re
            match = re.search(r'print\s+[\'"](.+)[\'"]', script_prompt)
            if match:
                message = match.group(1)
            else:
                # Fallback to generic message
                message = "Hello, World!"
            py_script = f"""
# This is a Python script generated by the AI Agent.
# Your request was: '{script_prompt}'

def main():
    print("{message}")

if __name__ == "__main__":
    main()
"""
            notify = None
        elif "add" in script_prompt and "numbers" in script_prompt:
            py_script = f"""
# This is a Python script generated by the AI Agent.
# Your request was: '{script_prompt}'

def main():
    a = 2
    b = 3
    print("Sum:", a + b)

if __name__ == "__main__":
    main()
"""
            notify = None
        else:
            # Static template with notification
            py_script = f"""
# This is a Python script generated by the AI Agent.
# Your request was: '{script_prompt}'
# NOTE: Only a static template was provided. Please specify your request more clearly for dynamic generation.

def main():
    print("Hello, World!")

if __name__ == "__main__":
    main()
"""
            notify = "Only a static template was provided. Please specify your request more clearly for dynamic generation."

        payload = {
            "language": "python",
            "filename": "script.py",
            "content": py_script.strip()
        }
        if notify:
            payload["notification"] = notify
        return {
            "type": "code_single",
            "payload": payload
        }
>>>>>>> REPLACE

</suggested_fix>

### Comment 2
<location> `backend/main.py:119` </location>
<code_context>
+    footer_content = structure.get('footer', '')
+
+    main_content = ""
+    for section in structure['sections']:
+        main_content += f"    <section>\n"
+        main_content += f"      <h2>{section.get('title', '')}</h2>\n"
+        if 'text' in section['content']:
+            main_content += f"      <p>{section['content']['text']}</p>\n"
+        if 'images' in section['content']:
+            try:
+                num_images = int(section['content']['images'])
+                for i in range(num_images):
+                    main_content += f"      <img src='https://via.placeholder.com/150' alt='placeholder image {i+1}'>\n"
+            except ValueError:
+                pass # Ignore if 'images' is not a number
+        main_content += f"    </section>\n"
+
+    html_content = f"""
</code_context>

<issue_to_address>
HTML generation does not escape user-provided content.

Directly inserting user content into HTML without escaping can allow HTML injection. Please escape all user-provided values before rendering.
</issue_to_address>

### Comment 3
<location> `backend/main.py:209` </location>
<code_context>
+    else:
+        lang = 'CSS'
+        # CSS checks
+        if code.count('{') != code.count('}'):
+            errors.append("Mismatched curly braces {}.")
+
+        lines = code.split('\n')
+        in_block = False
+        for i, line in enumerate(lines):
+            line = line.strip()
+            if '{' in line:
</code_context>

<issue_to_address>
CSS semicolon check may produce false positives.

Refine the semicolon check to exclude comments and closing braces, reducing false positives.
</issue_to_address>

### Comment 4
<location> `backend/main.py:514` </location>
<code_context>
+
+    return "Sorry, I don't have specific resources for that topic yet. Please try 'climate change', 'agriculture', or 'biodiversity'."
+
+def git_helper_agent(prompt):
+    """
+    Generates a shell script for Git commands based on user input.
+    """
+    branch = prompt.get('branch', 'new-feature')
+    commit_message = prompt.get('commitMessage', 'New changes')
+    repo_url = "https://github.com/gyfx35/AI-services" # Hardcoded for safety
+
+    # Basic validation
+    if not branch or not commit_message:
+        return "Error: Branch name and commit message are required."
+
+    # Sanitize inputs to prevent command injection
+    safe_branch = quote(branch)
+    safe_commit_message = quote(commit_message)
+
</code_context>

<issue_to_address>
Sanitization uses URL encoding for shell commands.

URL encoding is not sufficient for shell command sanitization. Use shlex.quote or a shell-specific escaping method to better protect against command injection.
</issue_to_address>

### Comment 5
<location> `frontend/static/js/script.js:95` </location>
<code_context>
+        sendCommand('astronaut', input);
+    });
+
+    medicalBtn.addEventListener('click', () => {
+        const input = document.getElementById('medical-input').value;
+        sendCommand('medical_info', input);
+    });
+
</code_context>

<issue_to_address>
Frontend uses 'medical_info' role, backend expects 'medical'.

This role mismatch will block medical queries. Please align the role names across frontend and backend.
</issue_to_address>

## Security Issues

### Issue 1
<location> `frontend/static/js/script.js:166` </location>

<issue_to_address>
**security (javascript.browser.security.insecure-document-method):** User controlled data in methods like `innerHTML`, `outerHTML` or `document.write` is an anti-pattern that can lead to XSS vulnerabilities

*Source: opengrep*
</issue_to_address>

### Issue 2
<location> `frontend/static/js/script.js:166` </location>

<issue_to_address>
**security (javascript.browser.security.insecure-innerhtml):** User controlled data in a `code.innerHTML` is an anti-pattern that can lead to XSS vulnerabilities

*Source: opengrep*
</issue_to_address>

---

Sourcery is free for open source - if you like our reviews please consider sharing them ✨

• X
• Mastodon
• LinkedIn
• Facebook

_{Help me be more useful! Please click 👍 or 👎 on each comment and I'll use the feedback to improve your reviews.}

[sourcery-ai]

suggestion: Python script generation is hardcoded and not dynamic.

The generated script does not adapt to different prompts and always outputs the same code. Please consider implementing logic to generate scripts based on the user's request, or notify users when only a static template is provided.

Suggested change

	if 'python script' in prompt.lower():
	script_prompt = prompt.lower().replace('python script to', '').strip()
	py_script = f"""
	# This is a Python script generated by the AI Agent.
	# Your request was: '{script_prompt}'
	def main():
	# A simple example: print "Hello, World!"
	print("Hello, World!")
	if __name__ == "__main__":
	main()
	"""
	return {
	"type": "code_single",
	"payload": {
	"language": "python",
	"filename": "script.py",
	"content": py_script.strip()
	}
	}
	if 'python script' in prompt.lower():
	script_prompt = prompt.lower().replace('python script to', '').strip()
	# Basic dynamic generation for demonstration
	if "print" in script_prompt:
	# Extract message to print
	import re
	match = re.search(r'print\s+[\'"](.+)[\'"]', script_prompt)
	if match:
	message = match.group(1)
	else:
	# Fallback to generic message
	message = "Hello, World!"
	py_script = f"""
	# This is a Python script generated by the AI Agent.
	# Your request was: '{script_prompt}'
	def main():
	print("{message}")
	if __name__ == "__main__":
	main()
	"""
	notify = None
	elif "add" in script_prompt and "numbers" in script_prompt:
	py_script = f"""
	# This is a Python script generated by the AI Agent.
	# Your request was: '{script_prompt}'
	def main():
	a = 2
	b = 3
	print("Sum:", a + b)
	if __name__ == "__main__":
	main()
	"""
	notify = None
	else:
	# Static template with notification
	py_script = f"""
	# This is a Python script generated by the AI Agent.
	# Your request was: '{script_prompt}'
	# NOTE: Only a static template was provided. Please specify your request more clearly for dynamic generation.
	def main():
	print("Hello, World!")
	if __name__ == "__main__":
	main()
	"""
	notify = "Only a static template was provided. Please specify your request more clearly for dynamic generation."
	payload = {
	"language": "python",
	"filename": "script.py",
	"content": py_script.strip()
	}
	if notify:
	payload["notification"] = notify
	return {
	"type": "code_single",
	"payload": payload
	}

[sourcery-ai]

🚨 issue (security): HTML generation does not escape user-provided content.

Directly inserting user content into HTML without escaping can allow HTML injection. Please escape all user-provided values before rendering.

[sourcery-ai]

nitpick: CSS semicolon check may produce false positives.

Refine the semicolon check to exclude comments and closing braces, reducing false positives.

[sourcery-ai]

🚨 issue (security): Sanitization uses URL encoding for shell commands.

URL encoding is not sufficient for shell command sanitization. Use shlex.quote or a shell-specific escaping method to better protect against command injection.

[sourcery-ai]

issue (bug_risk): Frontend uses 'medical_info' role, backend expects 'medical'.

This role mismatch will block medical queries. Please align the role names across frontend and backend.

[sourcery-ai]

issue (code-quality): Avoid function declarations, favouring function assignment expressions, inside blocks. (avoid-function-declarations-in-blocks)

Explanation

Function declarations may be hoisted in Javascript, but the behaviour is inconsistent between browsers. Hoisting is generally confusing and should be avoided. Rather than using function declarations inside blocks, you should use function expressions, which create functions in-scope.

[sourcery-ai]

suggestion (code-quality): Merge nested if conditions (merge-nested-ifs)

Suggested change

	if 'animation' in prompt or 'script' in prompt:
	if 'fade in' in prompt:
	css_snippet = """
	/* CSS for a fade-in animation */
	.fade-in {
	animation: fadeIn 1s ease-in-out;
	}
	@keyframes fadeIn {
	from {
	opacity: 0;
	}
	to {
	opacity: 1;
	}
	}
	"""
	return {
	"type": "code_single",
	"payload": {
	"language": "css",
	"content": css_snippet.strip()
	}
	}
	if ('animation' in prompt or 'script' in prompt) and 'fade in' in prompt:
	css_snippet = """
	/* CSS for a fade-in animation */
	.fade-in {
	animation: fadeIn 1s ease-in-out;
	}
	@keyframes fadeIn {
	from {
	opacity: 0;
	}
	to {
	opacity: 1;
	}
	}
	"""
	return {
	"type": "code_single",
	"payload": {
	"language": "css",
	"content": css_snippet.strip()
	}
	}

Explanation

Too much nesting can make code difficult to understand, and this is especially
true in Python, where there are no brackets to help out with the delineation of
different nesting levels.

Reading deeply nested code is confusing, since you have to keep track of which
conditions relate to which levels. We therefore strive to reduce nesting where
possible, and the situation where two if conditions can be combined using
and is an easy win.

[sourcery-ai]

suggestion (code-quality): We've found these issues:

• Swap if/else branches [×2] (swap-if-else-branches)
• Remove unnecessary else after guard condition (remove-unnecessary-else)

Suggested change

	else:
	message = f"Found {len(broken_links)} broken links on {url}:\n\n"
	for link in broken_links:
	query = f"'{link}' on page '{url}' is a broken link"
	search_url = f"https://www.google.com/search?q={quote(query)}"
	message += f"- Broken Link: {link}\n"
	message += f" Suggested Search: {search_url}\n\n"
	return message
	message = f"Found {len(broken_links)} broken links on {url}:\n\n"
	for link in broken_links:
	query = f"'{link}' on page '{url}' is a broken link"
	search_url = f"https://www.google.com/search?q={quote(query)}"
	message += f"- Broken Link: {link}\n"
	message += f" Suggested Search: {search_url}\n\n"
	return message

[sourcery-ai]

suggestion (code-quality): We've found these issues:

• Use the built-in function next instead of a for-loop (use-next)
• Remove unnecessary call to keys() (remove-dict-keys)
• Use named expression to simplify assignment and conditional (use-named-expression)

Suggested change

	found_topic = None
	for topic in resources.keys():
	if topic in prompt:
	found_topic = topic
	break
	if found_topic:
	if found_topic := next(
	(topic for topic in resources if topic in prompt), None
	):

[sourcery-ai]

issue (code-quality): We've found these issues:

• Replace f-string with no interpolated values with string (remove-redundant-fstring)
• Swap if/else branches [×2] (swap-if-else-branches)
• Remove unnecessary else after guard condition (remove-unnecessary-else)