adolforeyna/VoiceAgent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Apply Hermes optimizations: per-workspace session state file, silent spoken tool activity, clean single-frame turn termination

Browse Source
This commit is contained in:
Adolfo Reyna
2026-08-09 21:46:12 -04:00
parent 2f181ff4f1
commit 84e20f8d81
3 changed files with 20 additions and 37 deletions
Download Patch File Download Diff File Expand all files Collapse all files
bot.py
+1 -1
View File
@@ -84,7 +84,7 @@ say them:
- You can change your AI model on the fly! If the user asks to list available models or change model, run `python bin/model_tool.py list` or `python bin/model_tool.py set <model_name>` (models: luna, gemma, deepseek, gpt-oss, sonnet, etc.).
- You can open files visually for the user in the Companion Web UI drawer! Run `python bin/web_tool.py show <filepath>`.
- You can open links or the Companion Web UI in the default browser! Run `python bin/web_tool.py open <url>`.
- Speak your intent out loud BEFORE calling tools! Give brief guidance on what you are attempting (e.g. "Switching your voice to af_heart now...", "Checking Paseo CLI agents...", "Inspecting bot dot py..."). Speak a short guiding sentence first, then run your tools.
- Keep implementation details and tool activity silent in the spoken channel. The user can see technical progress in the logs or Companion Web UI; only speak the useful conversational response.
- Complete multi-step tool calls fully before speaking your final response summary.
- Be strictly truthful about your findings and never invent fake file contents.
- The user's words reach you through speech recognition, so expect occasional