peter/devclaw-gitea
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: show planning and steering in the same group chat demo

Browse Source 
Manual interaction example now shows creating issues, sequencing work,
and parking tasks in Planning — all in the same conversation where
autonomous execution happens.

https://claude.ai/code/session_01R3rGevPY748gP4uK2ggYag
This commit is contained in:
Claude
2026-02-11 02:12:50 +00:00
parent 089664a675
commit 40215f5c28
1 changed files with 10 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
README2.md
View File

@@ -38,17 +38,24 @@ Agent: "⚡ Sending DEV (medior) for #19: Add rate limiting to /api/search"
Three issues shipped, one sent back for a fix (and auto-retried), another project's migration completed — all while you slept. The heartbeat scanned the queues, dispatched workers, chained DEV into QA, and chained QA failures back to DEV. No human in the loop.
You can also drive it manually:
You can also plan and steer in the same chat — the orchestrator is right there:
```
You: "Check the queue"
Agent: "2 issues in To Do. DEV is idle. QA is idle."
You: "Pick up #44 for DEV"
You: "We need to refactor the profile page before we add settings.
Create an issue for that, mark it as To Do, and pick it up."
Agent: creates #44 "Refactor user profile page" with label "To Do"
Agent: "⚡ Sending DEV (medior) for #44: Refactor user profile page"
You: "Also create an issue for adding the settings page.
Keep it in Planning until #44 is done."
Agent: creates #45 "Add settings page" with label "Planning"
Agent: "Parked in Planning. I'll move it to To Do once #44 ships."
```
Same agent, as many groups as you want, fully isolated teams per project.
Same group chat for planning, prioritizing, and execution. Same agent, as many groups as you want, fully isolated teams per project.
---