mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: enable streaming by default in CLI

Browse source 
Streaming provides a better UX — tokens appear as they arrive instead
of waiting for the full response. show_reasoning remains false so
thinking blocks are not streamed to the user.
This commit is contained in:
Teknium 2026-03-21 09:49:47 -07:00
parent d70e07fc45
commit c4e787d47b
No known key found for this signature in database
2 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

4
cli-config.yaml.example
View file

@ -696,8 +696,8 @@ display:
# Stream tokens to the terminal as they arrive instead of waiting for the # Stream tokens to the terminal as they arrive instead of waiting for the
# full response. The response box opens on first token and text appears # full response. The response box opens on first token and text appears
# line-by-line. Tool calls are still captured silently. # line-by-line. Tool calls are still captured silently.
# Disabled by default — enable to try the streaming UX. # Stream tokens to the terminal in real-time. Disable to wait for full responses.
streaming: false streaming: true
# ─────────────────────────────────────────────────────────────────────────── # ───────────────────────────────────────────────────────────────────────────
# Skin / Theme # Skin / Theme

2
cli.py
View file

@ -216,7 +216,7 @@ def load_cli_config() -> Dict[str, Any]:
"compact": False, "compact": False,
"resume_display": "full", "resume_display": "full",
"show_reasoning": False, "show_reasoning": False,
"streaming": False, "streaming": True,
"skin": "default", "skin": "default",
}, },