feat: implement next.js frontend agent architecture and simulation

[projectedanx]

This PR introduces the Next.js Frontend Agent.

It includes:

1. program_nextjs_frontend.md defining the agent structure.
2. nextjs_frontend_simulation.py representing the evaluator.
3. Unit tests in tests/test_nextjs_frontend_simulation.py.
4. Updates to README.md to list the new architecture.

All files are formatted and linted properly. Temporary scripts have been cleaned up. Tests are passing.

---

PR created automatically by Jules for task 13551884925168890101 started by @projectedanx

[google-labs-jules]

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.

---

For security, I will only act on instructions from the user who triggered this task.

[gemini-code-assist]

Code Review

This pull request introduces the Next.js Frontend Agent, which includes a Python simulation for multi-agent routing and a comprehensive specification document. The implementation features intent-based routing to specialized agents and enforces constraints such as DCCDSchemaGuard and AdjectivalBound. Feedback focuses on improving the robustness of the Python simulation by addressing naive word splitting and case-sensitivity in intent parsing. Additionally, a correction was identified for the TypeScript example in the documentation to ensure proper handling of JSON payloads in Next.js Route Handlers.

[gemini-code-assist]

The current word splitting logic is naive and fails to identify banned adjectives if they are adjacent to punctuation (e.g., "fast," or "amazing!"). Normalizing the words by stripping punctuation and converting to lowercase during tokenization ensures the AdjectivalBound constraint is enforced correctly. Additionally, using a set for banned_adj improves lookup efficiency.

Suggested change

	words = intent.split()
	banned_adj = ["revolutionary", "fast", "seamless",
	"disruptive", "amazing"]
	adjective_count = sum(1 for word in words if word.lower()
	in banned_adj)
	words = [w.strip(".,!?;:").lower() for w in intent.split()]
	banned_adj = {"revolutionary", "fast", "seamless", "disruptive", "amazing"}
	adjective_count = sum(1 for word in words if word in banned_adj)

[gemini-code-assist]

The routing logic is case-sensitive, which may cause requests to fall back to the default agent if keywords are capitalized (e.g., "Security"). Performing the checks against a lowercased version of the intent makes the routing more robust.

Suggested change

	if "security" in intent or "trust" in intent:
	target_agent = "cipher"
	elif "developer" in intent or "code" in intent:
	target_agent = "dax-01"
	elif "validation" in intent or "ingress" in intent:
	target_agent = "kira-7"
	intent_lower = intent.lower()
	if "security" in intent_lower or "trust" in intent_lower:
	target_agent = "cipher"
	elif "developer" in intent_lower or "code" in intent_lower:
	target_agent = "dax-01"
	elif "validation" in intent_lower or "ingress" in intent_lower:
	target_agent = "kira-7"

[gemini-code-assist]

In Next.js Route Handlers (App Router), the req object is a standard Web Request where req.body is a ReadableStream. To access the JSON payload, you must use await req.json(). Using req.body directly as an object will result in an error or undefined behavior.

Suggested change

	const { query, user_id, collection: collectionName } = req.body;
	const { query, user_id, collection: collectionName } = await req.json();