Skip to content

fix: direct user message on STT failure + hermes-agent-setup skill#1905

Merged
teknium1 merged 3 commits intomainfrom
hermes/hermes-ba3c8fa1
Mar 18, 2026
Merged

fix: direct user message on STT failure + hermes-agent-setup skill#1905
teknium1 merged 3 commits intomainfrom
hermes/hermes-ba3c8fa1

Conversation

@teknium1
Copy link
Copy Markdown
Contributor

Summary

Two changes to improve the voice message experience:

1. Direct user message on STT failure

When a user sends a voice message and STT isn't configured, the gateway previously injected a context note into the agent's prompt like [can't listen to it right now~]. The agent often misinterpreted this, leading to confusing responses (e.g., explaining how to find the microphone button).

Now the gateway sends a direct message to the user explaining:

  • Voice was received but can't be transcribed
  • How to install faster-whisper
  • How to enable STT in config.yaml
  • Points to /skill hermes-agent-setup for full instructions

The agent still gets the context note so it knows what happened.

2. hermes-agent-setup bundled skill

New built-in skill covering:

  • STT setup (faster-whisper local, Groq, OpenAI)
  • TTS/voice reply configuration
  • Interactive tool configuration (hermes tools)
  • Dependency installation
  • Gateway commands reference
  • Troubleshooting common issues

Test plan

  • python -m pytest tests/gateway/ -n0 -q — 1194 passed (2 pre-existing whatsapp failures)
Test added 3 commits March 18, 2026 03:01
When a user sends a voice message and STT isn't configured, the gateway
now sends a clear message directly to the user explaining how to set up
voice transcription, rather than relying on the agent to relay an
injected context note (which often gets misinterpreted).

Also adds a hermes-agent-setup bundled skill covering STT/TTS setup,
tool configuration, dependency installation, and troubleshooting.
Skill now covers full CLI usage (hermes setup, hermes skills, hermes
tools, hermes config, session management, etc.), config file reference,
and expanded gateway commands.

Agent context notes for STT failure now mention the hermes-agent-setup
skill is available to help users configure Hermes features.
Only mention the hermes-agent-setup skill in STT failure notes (both
the direct user message and the agent context note) when the skill is
actually installed. Uses _find_skill() from skill_manager_tool.

Also confirmed: STT is the only user-facing failure case where the
setup skill hint helps. Vision failures are transient API issues,
runtime transcription errors indicate a configured-but-broken provider,
and platform startup warnings are server logs.
@teknium1 teknium1 merged commit c9bb0c5 into main Mar 18, 2026
1 check failed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

1 participant