Code-Inc/intelligence-terminal
2
0
Fork 0
Code Issues 11 Pull Requests Actions Packages Projects Releases Wiki Activity

Add secure conversational AI chat to Telegram bot #56

New Issue
Closed
opened 2026-07-05 18:31:58 +00:00 by MrSphay · 1 comment
MrSphay commented 2026-07-05 18:31:58 +00:00
Owner
Copy Link

Goal

Turn the Telegram command bot into a secure conversational AI assistant backed by the configured LLM and current Intelligence Terminal data.

Scope

  • Respond to normal text messages from the configured TELEGRAM_CHAT_ID.
  • Add /ask and /reset commands.
  • Maintain bounded in-memory conversation history.
  • Ground answers in a compact current intelligence snapshot while treating feed text as untrusted evidence.
  • Show Telegram typing activity during slow local inference.
  • Send AI responses as plain text to avoid Markdown parsing failures.
  • Keep commands, alerts, and strict chat allowlisting intact.
  • Add environment controls, tests, and operator documentation.

Acceptance criteria

  • Unauthorized chat IDs remain ignored.
  • Direct messages and /ask invoke the configured LLM.
  • /reset clears conversation state.
  • History and user input are bounded.
  • Missing/misconfigured LLM returns a transparent message without crashing polling.
  • Gitea runner tests and Docker build pass.
  • Live Dockge test receives an AI response through Telegram.
## Goal Turn the Telegram command bot into a secure conversational AI assistant backed by the configured LLM and current Intelligence Terminal data. ## Scope - Respond to normal text messages from the configured `TELEGRAM_CHAT_ID`. - Add `/ask` and `/reset` commands. - Maintain bounded in-memory conversation history. - Ground answers in a compact current intelligence snapshot while treating feed text as untrusted evidence. - Show Telegram typing activity during slow local inference. - Send AI responses as plain text to avoid Markdown parsing failures. - Keep commands, alerts, and strict chat allowlisting intact. - Add environment controls, tests, and operator documentation. ## Acceptance criteria - Unauthorized chat IDs remain ignored. - Direct messages and `/ask` invoke the configured LLM. - `/reset` clears conversation state. - History and user input are bounded. - Missing/misconfigured LLM returns a transparent message without crashing polling. - Gitea runner tests and Docker build pass. - Live Dockge test receives an AI response through Telegram.
MrSphay added the research label 2026-07-05 18:31:59 +00:00
MrSphay commented 2026-07-05 18:39:47 +00:00
Author
Owner
Copy Link

Implementation is in PR #57: #57. Waiting for runner verification before merge.

Implementation is in PR #57: https://git.wilkensxl.de/Code-Inc/intelligence-terminal/pulls/57. Waiting for runner verification before merge.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
design-revert
Reverts visual/design changes
 enhancement
New feature or product improvement
 frontend-redesign
Frontend redesign and app-shell/UI work
 marketing-finalization
Product presentation, README, packaging metadata, and customer-facing communication.
 product
User-facing product capability or workflow
 research
Research-originated product idea ready for implementation design
No Label research
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
MrSphay Toxic
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Code-Inc/intelligence-terminal#56
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?