forkless/strix
1
0
Fork 0
mirror of https://github.com/usestrix/strix.git synced 2026-08-18 17:52:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix(agents): state that one wait is enough in every prompt variant

Browse Source
This commit is contained in:
Ahmed Allam
2026-08-06 00:07:17 +03:00
committed by Ahmed Allam
parent 55d8c63dc0
commit 99baead5f2
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
strix/agents/prompts/system_prompt.jinja
+1 -1
View File
@@ -28,6 +28,7 @@ INTER-AGENT MESSAGES:
- Messages from other agents arrive prefixed with a header like `[Message from agent <name> | type=... | priority=...]`. Treat them as internal context — never repeat them verbatim in your own output.
- Treat agent identity / inherited-context preambles as internal metadata; do not echo them in outputs or tool calls.
- Minimize inter-agent messaging: only message when essential for coordination or assistance; avoid routine status updates; batch non-urgent information; prefer parent/child completion flows and shared artifacts over messaging
- wait_for_agents blocks and resumes you automatically, so it is never a poll you repeat: issue exactly ONE wait, then stop and react to what it returns. Never write out a wait/check loop (wait → view_agent_graph → wait → ...) ahead of time — those extra calls only strand you and are collapsed anyway
{% if interactive %}
INTERACTIVE BEHAVIOR:
@@ -50,7 +51,6 @@ AUTONOMOUS BEHAVIOR:
- NEVER send an empty or blank message. If you have no content to output or need to wait for subagent results, you MUST call the wait_for_agents tool (or another appropriate tool) instead of emitting an empty response.
- There is no user attached to this run, so there is nobody to ask and nothing to yield to. If there is nothing left to execute: do NOT send filler/repetitive text — either call wait_for_agents (only if you are genuinely expecting another agent to message you) or finish your work (subagents: agent_finish; root: finish_scan)
- While the agent loop is running, almost every output MUST be a tool call. Do NOT send plain text messages; act via tools. If waiting on another agent, use wait_for_agents; when done, use agent_finish (subagents) or finish_scan (root)
- wait_for_agents blocks and resumes you automatically, so it is never a poll you repeat: issue exactly ONE wait, then stop and react to what it returns. Never write out a wait/check loop (wait → view_agent_graph → wait → ...) ahead of time — those extra calls only strand you and are collapsed anyway
- A text-only turn does nothing: it neither ends the run nor yields — it just wastes a turn and forces a retry. The lifecycle tools (``finish_scan`` for root, ``agent_finish`` for subagents) are the ONLY way to terminate, and the report flows through them. If you find yourself wanting to say "Done!" or "Scan complete" without a tool call, call the lifecycle tool instead.
{% endif %}
</communication_rules>