Fix tg read pagination

[yourconscience]

Summary

• page large tg read requests through daemon-safe batches
• add offset-id support to the Telegram read-only daemon
• document large read behavior and cover batching with a unittest

Tests

• uv run python -m py_compile tg server.py test_tg.py
• uv run python -m unittest discover mcp/telegram-readonly
• git diff --check
• go test ./cmd/dotagents -skip TestAmpSetupE2E -count=1

[gemini-code-assist]

Code Review

This pull request implements automatic batching and paging for reading Telegram messages via the tg read command. It introduces a maximum batch size of 100 messages per call, adds support for an optional offset_id parameter to fetch older messages, and updates the CLI, daemon, and MCP tool to support this pagination. It also includes unit tests for the paging logic and updates the documentation across several README and SKILL files. I have no feedback to provide as there are no review comments.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.