* fix(goal): increase goal evaluate timeout from 5s to 120s
5s timeout from #1580 is too aggressive for users with remote/slow LLM
services. Goal judge calls silently fail causing goal continuation to
never enqueue, leaving the goal stuck at 1 turn.
Align with auxiliary.goal_judge.timeout default (120s) in config.yaml.
* docs: note goal evaluate timeout change
---------
Co-authored-by: WenhuaXia <wenhua_xia@163.com>
Add one Markdown fragment per PR when a change touches the Chat session chain,
Agent Bridge, compression, or Group Chat runtime paths documented in
docs/cli-chat-sessions.md.
Do not append new rows to docs/cli-chat-sessions.md. Keeping one fragment per
PR avoids merge conflicts when multiple branches change the chat chain at the
same time.
Use this shape:
---
date: YYYY-MM-DD
pr: 1234
feature: Short feature name
impact: One-sentence behavior impact
---
Optional extra notes.
If the PR number is not known yet, use pr: pending while the branch is local,
then update that same fragment after the PR is opened.
ekko
fa92b4157e