Issue Station
Sign In
Tools hereToolbox

claude-code - 💡(How to fix) Fix Telegram Channels plugin drops messages when LLM is busy [2 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
anthropics/claude-code#45521•Fetched 2026-04-09 08:03:28
View on GitHub
Comments
2
Participants
2
Timeline
5
Reactions
0
Author
dyjhhhdyjhhh
Participants
dyjhhhdyjhhhgithub-actions[bot]github-actions[bot]
Timeline (top)
labeled ×3commented ×2

When using the Telegram Channels plugin, incoming messages are silently dropped if the LLM is currently processing another message. The user receives "LLM request rejected: You're out of extra usage" on Telegram, which is misleading — the actual issue is that the session is busy, not that the subscription quota is exhausted.

Error Message

  1. The second message is dropped with "LLM request rejected" error shown to the Telegram user
  • The misleading error message causes confusion about subscription status

Root Cause

When using the Telegram Channels plugin, incoming messages are silently dropped if the LLM is currently processing another message. The user receives "LLM request rejected: You're out of extra usage" on Telegram, which is misleading — the actual issue is that the session is busy, not that the subscription quota is exhausted.

RAW_BUFFERClick to expand / collapse

Description

When using the Telegram Channels plugin, incoming messages are silently dropped if the LLM is currently processing another message. The user receives "LLM request rejected: You're out of extra usage" on Telegram, which is misleading — the actual issue is that the session is busy, not that the subscription quota is exhausted.

Steps to reproduce

  1. Set up Telegram Channels plugin with a bot
  2. Send a message → bot starts processing/responding
  3. While the bot is generating a response, send another message
  4. The second message is dropped with "LLM request rejected" error shown to the Telegram user

Also reproduced:

  • Sending messages in quick succession (< 2 seconds apart)
  • Sending a message right after the bot finishes replying (internal processing not yet complete)

Expected behavior

  • Incoming messages should be queued when the LLM is busy
  • Queued messages should be processed after the current response completes
  • Messages should never be silently dropped

Actual behavior

  • Messages sent while LLM is busy are rejected immediately
  • The Telegram user sees "LLM request rejected: You're out of extra usage. Add more at claude.ai/settings/usage and keep going." which is misleading (subscription is Max/unlimited)
  • No retry or queue mechanism exists
  • Messages are permanently lost

Impact

For users running Claude Code as an always-on Telegram assistant, this means:

  • Rapid messages are lost
  • Users must wait and guess when the bot is "ready" before sending
  • The misleading error message causes confusion about subscription status
  • No indication to the user that their message was dropped vs. being processed

Suggested fix

Add a message queue in the Channels plugin that buffers incoming messages when the LLM is busy, and processes them sequentially once the current response completes.

Environment

  • Claude Code version: latest
  • OS: macOS (Darwin 25.2.0)
  • Subscription: Max (unlimited)
  • Plugin: Telegram Channels (plugin:telegram:telegram)

extent analysis

TL;DR

Implement a message queue in the Telegram Channels plugin to buffer incoming messages when the LLM is busy, ensuring sequential processing and preventing silent drops.

Guidance

  • Identify the current LLM processing state to determine when to buffer incoming messages.
  • Develop a queue mechanism to store incoming messages when the LLM is busy, ensuring messages are not lost.
  • Implement a retry or sequential processing mechanism to handle queued messages once the LLM is available.
  • Update the error handling to provide accurate feedback to users when messages are queued or cannot be processed immediately.

Example

A basic message queue implementation could utilize a data structure like a FIFO (First-In-First-Out) queue to store incoming messages. When the LLM is busy, incoming messages are added to the queue, and when the LLM is available, messages are dequeued and processed sequentially.

Notes

The suggested fix assumes that the LLM processing state can be accurately determined and that the queue mechanism can be efficiently implemented within the existing plugin architecture.

Recommendation

Apply a workaround by implementing a message queue in the Telegram Channels plugin, as this addresses the root cause of the issue (silent message drops due to busy LLM) and provides a more robust solution for handling incoming messages.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

FAQ

Expected behavior

  • Incoming messages should be queued when the LLM is busy
  • Queued messages should be processed after the current response completes
  • Messages should never be silently dropped
#api#pipeline error#runtime error#dependency conflict#environment setup

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING