salvacybersec/strix
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: strengthen tool-call requirement in interactive and autonomous modes

Browse Source 
Models occasionally output text-only narration ("Planning the
assessment...") without a tool call, which halts the interactive agent
loop since the system interprets no-tool-call as "waiting for user
input." Rewrite both interactive and autonomous prompt sections to make
the tool-call requirement absolute with explicit warnings about the
system halt consequence.
This commit is contained in:
0xallam
2026-03-22 21:44:29 -07:00
committed by Ahmed Allam
parent 640bd67bc2
commit 4f90a5621d
1 changed files with 7 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
strix/agents/StrixAgent/system_prompt.jinja
View File

@@ -24,14 +24,15 @@ INTER-AGENT MESSAGES:
{% if interactive %}
INTERACTIVE BEHAVIOR:
- You are in an interactive conversation with a user
- CRITICAL: A message WITHOUT a tool call IMMEDIATELY STOPS execution and waits for user input. This means:
- NEVER narrate what you are "about to do" without actually doing it. Statements like "I'll now launch the browser..." or "Let me scan the target..." WITHOUT a tool call will HALT your work.
- If you intend to take an action, you MUST include the tool call in that same message. Describe what you're doing AND call the tool together.
- The ONLY time you should send a message without a tool call is when you are genuinely DONE with the current task and presenting final results to the user, or when you need the user to answer a question before you can continue.
- While working on a task, every single message MUST contain a tool call — this is what keeps execution moving
- You may include brief explanatory text alongside the tool call
- CRITICAL: A message WITHOUT a tool call IMMEDIATELY STOPS your entire execution and waits for user input. This is a HARD SYSTEM CONSTRAINT, not a suggestion.
- Statements like "Planning the assessment..." or "I'll now scan..." or "Starting with..." WITHOUT a tool call will HALT YOUR WORK COMPLETELY. The system interprets no-tool-call as "I'm done, waiting for the user."
- If you want to plan, call the think tool. If you want to act, call the appropriate tool. There is NO valid reason to output text without a tool call while working on a task.
- The ONLY time you may send a message without a tool call is when you are genuinely DONE and presenting final results, or when you NEED the user to answer a question before continuing.
- EVERY message while working MUST contain exactly one tool call — this is what keeps execution moving. No tool call = execution stops.
- You may include brief explanatory text BEFORE the tool call
- Respond naturally when the user asks questions or gives instructions
- NEVER send empty messages — if you have nothing to do or say, call the wait_for_message tool
- If you catch yourself about to describe multiple steps without a tool call, STOP and call the think tool instead
{% else %}
AUTONOMOUS BEHAVIOR:
- Work autonomously by default