openclaw-code-agent 4.3.6 → 4.3.8

package/README.md

@@ -177,7 +177,7 @@ New sessions use delegated worktree follow-through unless configured otherwise.
 
 Ask OpenClaw for worktree status before cleaning resolved sandboxes.
 
-Merge and PR outcomes use a two-step completion contract: the plugin delivers the canonical outcome status, then wakes the orchestrator with the original route/thread metadata and `completionWakeSummaryRequired=true`. The orchestrator should read the full output, avoid repeating the status line, and send one short factual summary to the session origin route.
+Merge, PR, ordinary terminal, and no-change worktree outcomes use a two-step completion contract: the plugin delivers the canonical terse status, then wakes the orchestrator with the original route/thread metadata and `completionWakeSummaryRequired=true`. The orchestrator must read the full output, treat any final summary inside `agent_output` as source material rather than visible delivery, avoid repeating the status line, and send at most one short factual summary to the session origin route for the terminal/worktree outcome.
 
 ### Goal Tasks
 
@@ -189,6 +189,7 @@ Ask in normal chat:
 Start a verifier goal in /repo: fix the failing auth flow and keep running pnpm test until it passes.
 Start a Ralph-style goal for /repo: ship the draft workflow, and consider it complete when the output says DONE.
 Show goal status.
+Change the auth goal to also update the smoke tests.
 Stop the auth goal.
 ```
 
@@ -214,9 +215,10 @@ Most users interact in chat. The tool surface is for OpenClaw agents and advance
 | `agent_worktree_cleanup` | Clean safe worktrees or dismiss one pending decision |
 | `goal_launch` | Start an explicit verifier or Ralph-style goal loop |
 | `goal_status` | Show one goal task or list all goal tasks |
+| `goal_edit` | Change the goal text for an active goal task |
 | `goal_stop` | Stop a running goal task |
 
-Chat commands mirror the common workflows when you want explicit commands instead of natural-language chat, but most human use should start with plain requests like the examples above. Available commands are `/agent`, `/agent_sessions`, `/agent_output`, `/agent_respond`, `/agent_kill`, `/agent_stats`, `/goal`, `/goal_status`, and `/goal_stop`.
+Chat commands mirror the common workflows when you want explicit commands instead of natural-language chat, but most human use should start with plain requests like the examples above. Available commands are `/agent`, `/agent_sessions`, `/agent_output`, `/agent_respond`, `/agent_kill`, `/agent_stats`, `/goal`, `/goal_status`, `/goal_edit`, and `/goal_stop`.
 
 ## Docs