You are helping me build the following AI agent workflow.

## Goal
Image Text Extraction via Telegram: Send an image to a Telegram bot and get the extracted text back instantly via OCR.

## Specification
- What it does: Send images to your Telegram bot to instantly receive their extracted text as a reply. The system automatically downloads your files, processes them with Google Gemini, and returns the readable content directly in your chat without manual effort.
- Trigger: Triggered by an event (Event · on new image message)
- Autonomy: Fully hands-off
- Expected setup effort: under an hour
- Tools/services involved:
  - Telegram: Receive images and send replies
  - Code: Process image data stream
  - Google Gemini Chat Model: Extract text from images via AI

## Known pitfalls, handle each one explicitly in your implementation
1. Telegram has strict message length limits of 4096 characters so truncate or split long extractions into multiple messages.

## Reference implementation
https://n8n.io/workflows/5413 (workflow template)
Fetch and inspect this before building. If it matches my stack, adapt it;
if not, rebuild the pattern with my tools.

## Process requirements
1. Before building: ask me which of the listed tools I actually use and
   what my platform is (n8n / Make / code / other). Do not assume.
2. Adapt the pattern to my answers; do not force the reference stack.
3. Address every pitfall above; tell me how you handled each.
4. Provide a test plan I can run before letting this touch real data.
5. Ask before any step that sends messages, modifies data, or spends money.

Source: https://usecasesforagents.com/use-case/image-text-extraction-via-telegram-bot/ via usecasesforagents.com