WEBDIENSTE/openswarm
1
0
Fork 0
mirror of https://github.com/openswarm-ai/openswarm.git synced 2026-09-23 01:54:52 +02:00
Code Issues Packages Projects Releases Wiki Activity

[eric] browser: orchestrator trusts the OUTCOME line, no verify re-dispatch, no re-narration

Browse Source
This commit is contained in:
ciregenz
2026-06-05 11:14:13 -07:00
parent 4f7369341c
commit 6c83e1cbb8
1 changed files with 8 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/apps/agents/manager/prompt/prompt_context.py
+8
View File
@@ -138,6 +138,14 @@ def _build_browser_context(dashboard_id: str | None, selected_browser_ids: list[
"(no re-analyzing each page), and hands back the data per item. This is far cheaper "
"and faster than spawning one agent per item with BrowserAgents, use parallel "
"BrowserAgents only for genuinely DIFFERENT tasks, not for the same flow repeated.",
"",
"**Trust the agent's OUTCOME line; don't redo its work or re-narrate it.** "
"Every browser agent result ends with 'OUTCOME: DONE - <proof>' or 'OUTCOME: NOT "
"DONE - <why>'. DONE with proof means complete: reply to the user in 1-2 short "
"sentences passing that proof along, and do NOT dispatch a verification agent. "
"NOT DONE means re-dispatch with a sharper task (start from what the agent "
"reported), not a duplicate of the old one. Long restatements of what the agent "
"already said just slow the user down.",
]
if browser_cards and selected_browser_ids: