TypingMindTypingMindThe best frontend for AI
Messaging Gateway Troubleshooting logo

Messaging Gateway Troubleshooting

Community
AtlasOmnia
messaging-gateway-troubleshooting

messaging-gateway-troubleshooting — Troubleshoot Hermes messaging gateway platform adapters, webhooks, authorization, delivery, and loop-prevention behavior.

Overview

PublisherAtlasOmnia
Repositorydonna-starter
Skill namemessaging-gateway-troubleshooting
Stars
131
Forks
9
Bundled files
3
LicenseMIT
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by AtlasOmnia on GitHub. Read the source before you install it.

Installation

Install the Messaging Gateway Troubleshooting AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/AtlasOmnia/donna-starter/tree/main/skills/hermes/messaging-gateway-troubleshooting
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/AtlasOmnia/donna-starter.git /tmp/donna-starter
mkdir -p .claude/skills
cp -r /tmp/donna-starter/skills/hermes/messaging-gateway-troubleshooting .claude/skills/messaging-gateway-troubleshooting
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Messaging Gateway Troubleshooting in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Messaging Gateway Troubleshooting on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Messaging Gateway Troubleshooting is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Messaging Gateway Troubleshooting

Use this when Hermes messaging platforms are installed/configured but messages do not arrive, are ignored, do not reply, or appear to risk reply loops.

Operating principles

  1. Verify the live path end to end before assuming config is wrong:
  • Gateway service is running.
  • Platform server/client is running.
  • Local webhook/listener is bound.
  • Health endpoint responds if available.
  • Platform has the webhook registered.
  • Gateway logs show the adapter connected.
  1. Separate transport, authorization, and adapter filtering:
  • Transport failure: no webhook hit / listener closed.
  • Authorization failure: sender not allowed or pairing pending.
  • Adapter filtering: message acknowledged but intentionally skipped, e.g. group mention gating, tapback filtering, or self-message loop guard.
  1. For user-visible claims, verify with real command output: hermes status, listener checks, webhook health, and gateway logs.
  2. When changing Hermes gateway config or adapter code, restart the gateway and verify the adapter reconnects.
  3. For gateway slash-command failures, inspect session-origin scope separately from transport health:
  • Compare source, user_id, chat_id, thread_id, and origin_json in the live session database.
  • Trace both the listing path and the action path; a session browser is still broken if it lists a target that /resume rejects.
  • In forum/threaded platforms, distinguish same-parent-chat ownership from exact-thread isolation rather than weakening origin checks globally.

Telegram forum session browsing

  • A fresh Telegram forum topic can have no prior exact-thread sessions even when the same owner has many titled sessions in sibling topics of the same parent chat.
  • Do not diagnose this from session history alone. Correlate gateway send logs, live DB origin columns, and the gateway routing origin.
  • Cross-topic browsing must be Telegram-specific, same-parent-chat, and same-owner; thread_sessions_per_user=false permits sharing within one thread, not across sibling threads.
  • Keep /sessions visibility and /resume authorization aligned, including persisted-only rows.
  • See references/telegram-forum-session-scope.md for the reproduction, authorization contract, TDD matrix, and safe activation procedure.

BlueBubbles / iMessage notes

  • BlueBubbles may mark messages from the Mac's own Apple ID/iMessage identity as isFromMe=true.
  • A blanket isFromMe skip prevents reply loops but also prevents the owner from texting Hermes from that same iMessage identity.
  • The safer loop guard is outbound-ID based: remember Hermes-sent tempGuid and returned guid/messageGuid, then ignore only inbound webhook echoes whose IDs match that cache.
  • On macOS, do not assume localhost reaches an IPv4-only Hermes webhook. BlueBubbles/Electron/Node may resolve localhost to IPv6 ::1, causing connect ECONNREFUSED ::1:<port> while curl http://127.0.0.1:<port>/health still works. Register local BlueBubbles webhooks as http://127.0.0.1:<port>/... unless Hermes is listening on IPv6 too.
  • See references/bluebubbles-self-imessage-loop-guard.md for the concrete fix pattern, localhost/IPv6 pitfall, stale-webhook cleanup, and verification loop.
  • See references/memory-context-injection-probes.md for probe handling when recalled-memory wrappers, formatting-failure echoes, or outbound test messages appear in a live platform chat.

Verification checklist

  • hermes status shows the platform configured.
  • Gateway process/service is running under the expected profile/home.
  • Listener exists for the adapter webhook port/path.
  • Webhook health returns success if implemented.
  • Platform-side webhook registration points at the active Hermes listener.
  • Logs show adapter connected and webhook registered.
  • A test message reaches the adapter or produces a pairing/authorization signal.

Pitfalls

  • Do not confuse “gateway open” with “message authorized.” A listener can be healthy while the sender is ignored by allowlist/pairing logic.
  • If Telegram is fast for text but a photo/image turn appears to run forever, inspect agent.log for repeated API calls ending in TypeError: expected string or bytes-like object, got 'list' from _interim_assistant_visible_text → strip_think_blocks. This was a multimodal block-list regression introduced by Codex interim-commentary handling; a current upstream release fixes the loop. Stop the affected turn, update Hermes through the normal update-safe procedure, reapply local patches, restart the gateway, and verify with a real photo+caption message. Transport latency and gateway health can look completely normal while this retry loop burns up to the agent iteration cap.
  • Do not persist negative claims like “BlueBubbles ignores self messages” as a permanent tool limitation. The durable lesson is the loop-guard design.
  • Do not edit protected bundled skills; place Hermes-gateway-specific operational learnings here when bundled skills cannot be patched.

Public support files

  • references/bluebubbles-self-imessage-loop-guard.md
  • references/memory-context-injection-probes.md
  • references/telegram-forum-session-scope.md

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Messaging Gateway Troubleshooting AI skill do?

messaging-gateway-troubleshooting — Troubleshoot Hermes messaging gateway platform adapters, webhooks, authorization, delivery, and loop-prevention behavior.

Why use Messaging Gateway Troubleshooting on TypingMind?

Because you install it once and use it with any model. Messaging Gateway Troubleshooting is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Messaging Gateway Troubleshooting in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/AtlasOmnia/donna-starter/tree/main/skills/hermes/messaging-gateway-troubleshooting. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Messaging Gateway Troubleshooting?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Messaging Gateway Troubleshooting?

As many as you like. As long as a model supports skills, you can use Messaging Gateway Troubleshooting with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Messaging Gateway Troubleshooting AI skill free?

Yes. It is published on GitHub by AtlasOmnia under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
addyosmani logo

Spec Driven Development

addyosmani
CommunityPopular

Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when drafting a PRD or requirements document with objectives and…

10.1K
95.8K
Instructions
View
paperclipai logo

Release Announcement

paperclipai
OrganizationPopular

Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.

16.2K
95.4K
Instructions
View
thedotmack logo

Mode Creator

thedotmack
CommunityPopular

Interactively create, install, activate, and verify custom claude-mem modes, including domain-specific observation types, concept tags, optional Telegram alerts, bot setup, worker restart, and…

8.3K
94.1K
5 files
View
thedotmack logo

Version Bump

thedotmack
CommunityPopular

Automated semantic versioning and release workflow for Claude Code plugins. Handles version increments across package.json, marketplace.json, plugin.json manifests, build verification, git tagging,…

8.3K
94.1K
1 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇