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

fix(gateway): verbose tool progress no longer truncates args when tool_preview_length is 0 (#8735)

Browse source 
When tool_preview_length is 0 (default for platforms without a tier
default, like Session), verbose mode was truncating args JSON to 200
characters.  Since the user explicitly opted into verbose mode, they
expect full tool call detail — the 200-char cap defeated the purpose.

Now: tool_preview_length=0 means no truncation in verbose mode.
Positive values still cap as before.  Platform message-length limits
handle overflow naturally.
This commit is contained in:
Teknium 2026-04-12 20:05:12 -07:00 • committed by GitHub
parent 3636f64540
commit a0cd2c5338
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 68 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

8
gateway/run.py
View file

@ -7411,9 +7411,11 @@ class GatewayRunner:
_pl = get_tool_preview_max_len()
import json as _json
args_str = _json.dumps(args, ensure_ascii=False, default=str)
_cap = _pl if _pl > 0 else 200
if len(args_str) > _cap:
args_str = args_str[:_cap - 3] + "..."
# When tool_preview_length is 0 (default), don't truncate
# in verbose mode — the user explicitly asked for full
# detail. Platform message-length limits handle the rest.
if _pl > 0 and len(args_str) > _pl:
args_str = args_str[:_pl - 3] + "..."
msg = f"{emoji} {tool_name}({list(args.keys())})\n{args_str}"
elif preview:
msg = f"{emoji} {tool_name}: \"{preview}\""