Merge pull request #52412 from GodsBoy/fix/verify-on-stop-messaging-surface-leak
fix(agent): gate verify-on-stop nudge off for messaging surfaces
This commit is contained in:
commit
a2b49e60b6
4 changed files with 199 additions and 13 deletions
|
|
@ -637,7 +637,15 @@ agent:
|
|||
# primaries (default 3). The OpenAI SDK does its own low-level retries
|
||||
# underneath this wrapper — this is the Hermes-level loop.
|
||||
# api_max_retries: 3
|
||||
|
||||
|
||||
# After the agent edits code without fresh passing verification, nudge it to
|
||||
# verify before finishing. The default "auto" enables it on interactive
|
||||
# coding surfaces (CLI, TUI, desktop) and programmatic callers, and disables
|
||||
# it on conversational messaging surfaces (Telegram, Discord, etc.) where the
|
||||
# verification summary would reach a human as chat noise. Set true or false to
|
||||
# force it on or off; the HERMES_VERIFY_ON_STOP env var (1/0) takes precedence.
|
||||
# verify_on_stop: auto
|
||||
|
||||
# Enable verbose logging
|
||||
verbose: false
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue