Add Supply Chain, Logistics, Data Engineering, Incoterm, and Digital Twins Roles

[GYFX35]

This change adds five specialized AI roles to the agent: Supply Chain Consultant, Logistics & Transportation Specialist, Data Engineering & Architecture, Incoterms Expert, and Digital Twin Specialist.

Each role includes:

• A dedicated prompt in google_ai.py defining its expertise.
• A secure POST endpoint in app.py protected by API key authentication.
• A UI card in the 'Our Services' section of the landing page.
• An interactive 'Request Assistance' section with a dedicated output container.
• Full localization support for both English and Spanish.

The implementation follows the established architecture of the application, ensuring consistency and ease of maintenance. Verification was performed using Playwright to confirm the visibility of all new UI elements.

---

PR created automatically by Jules for task 11749821133464895838 started by @GYFX35

Summary by Sourcery

Add new domain-specific AI assistance capabilities for supply chain, logistics, data engineering, Incoterms, and digital twins, exposing them via secured APIs and integrating them into the landing page UI.

New Features:

• Introduce Vertex AI-backed assistants for supply chain consulting, logistics and transportation, data engineering and architecture, Incoterms guidance, and digital twin strategy and operations.
• Expose new POST endpoints for each assistant, secured with API key authentication and accepting user prompts for processing.
• Add dedicated landing page sections and interaction areas for each new assistant, allowing users to submit requests and view responses directly in the UI.

Enhancements:

• Extend the frontend script to handle form submission, API key prompting, and response rendering for the five new assistance flows.
• Update English and Spanish localization resources to cover the new assistant roles and UI copy.

[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.

[sourcery-ai]

Reviewer's Guide

Adds five new domain-specific AI assistance roles (Supply Chain, Logistics, Data Engineering, Incoterms, and Digital Twin) end-to-end, including Vertex AI prompt handlers, authenticated REST endpoints, landing-page service cards, interactive request/response sections, and English/Spanish localization hooks.

Class diagram for new AI assistance handlers and endpoints

classDiagram
    class GoogleAI {
        +provide_supply_chain_assistance(prompt: string) string
        +provide_logistics_assistance(prompt: string) string
        +provide_data_engineering_assistance(prompt: string) string
        +provide_incoterm_assistance(prompt: string) string
        +provide_digital_twin_assistance(prompt: string) string
    }

    class AssistanceAPI {
        +supply_chain_assistance_endpoint() JsonResponse
        +logistics_assistance_endpoint() JsonResponse
        +data_engineering_assistance_endpoint() JsonResponse
        +incoterm_assistance_endpoint() JsonResponse
        +digital_twin_assistance_endpoint() JsonResponse
    }

    class FrontendScript {
        +handleSupplyChainClick()
        +handleLogisticsClick()
        +handleDataEngineeringClick()
        +handleIncotermClick()
        +handleDigitalTwinClick()
    }

    AssistanceAPI --> GoogleAI : uses
    FrontendScript --> AssistanceAPI : calls REST endpoints
    FrontendScript --> GoogleAI : indirect via AssistanceAPI

Loading

File-Level Changes

Change	Details	Files
Introduce backend Vertex AI role handlers and expose them via authenticated Flask API endpoints for the five new assistance domains.	Add five new provider functions that construct domain-specific system prompts and call GenerativeModel('gemini-1.5-flash'), each with tailored expertise descriptions and error handling Define five new Flask POST routes under /api/v1/*/assistance, all protected with @require_api_key, that validate the presence of a 'prompt' field, delegate to the corresponding google_ai helper, and return a standardized JSON payload	google_ai.py app.py
Extend the landing page UI with new service cards and dedicated interactive assistance sections wired to the new APIs.	Add five new cards under the 'Our Services' section describing the new roles using gettext-wrapped strings for localization Create five new assistance sections, each with heading, description, textarea input, submit button, and a pre-based response container, following existing styling conventions	frontend/templates/index.html
Wire up frontend behavior for the new assistance flows, including API-key prompting, POST requests, and response rendering.	Register click handlers for each new assistance button that read the textarea value, prompt the user for an API key, and send a JSON POST to the corresponding /api/v1/*/assistance endpoint with X-API-Key header Handle non-OK responses by reading the JSON error and surfacing a friendly message, and on success display result.message in the corresponding response element	frontend/static/js/script.js
Add localization hooks for new strings in both English and Spanish catalogs.	Introduce new gettext msgids in templates for the new role names, descriptions, and assistance instructions Update .pot and .po files to include the new messages so they can be translated in English and Spanish	messages.pot translations/en/LC_MESSAGES/messages.po translations/es/LC_MESSAGES/messages.po

---

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.

[cloudflare-workers-and-pages]

Deploying ai-services with    Cloudflare Pages

Latest commit:	e59a304
Status:	✅  Deploy successful!
Preview URL:	https://0d7b1cc6.ai-services-36y.pages.dev
Branch Preview URL:	https://feat-add-supply-chain-logist.ai-services-36y.pages.dev

View logs

[cloudflare-workers-and-pages]

Deploying with    Cloudflare Workers

The latest updates on your project. Learn more about integrating Git with Workers.

Status	Name	Latest Commit	Updated (UTC)
❌ Deployment failed View logs	aiservices	e59a304	Feb 12 2026, 08:26 AM

[sourcery-ai]

Hey - I've left some high level feedback:

• The five new assistance handlers in script.js are nearly identical; consider extracting a shared helper that takes element IDs, endpoint URL, and prompt text to reduce duplication and make future changes easier.
• The new Flask endpoints call request.get_json() and then access .get('prompt') without checking for a None body; adding a guard for invalid/missing JSON would avoid a possible AttributeError on malformed requests.
• Prompting for the API key with window.prompt on each button click is a bit awkward and may encourage re-entry of secrets; consider centralizing API key input/storage in the UI (e.g., a dedicated field saved in memory) and reusing it across these assistance calls.

Prompt for AI Agents

Please address the comments from this code review:

## Overall Comments
- The five new assistance handlers in `script.js` are nearly identical; consider extracting a shared helper that takes element IDs, endpoint URL, and prompt text to reduce duplication and make future changes easier.
- The new Flask endpoints call `request.get_json()` and then access `.get('prompt')` without checking for a `None` body; adding a guard for invalid/missing JSON would avoid a possible `AttributeError` on malformed requests.
- Prompting for the API key with `window.prompt` on each button click is a bit awkward and may encourage re-entry of secrets; consider centralizing API key input/storage in the UI (e.g., a dedicated field saved in memory) and reusing it across these assistance calls.

---

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.}