Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.
Python agentsai-hackingai-penetration-testingai-pentestingai-securityartificial-intelligencebug-bountycode-qualityctf-toolscybersecuritycybersecurity-toolsethical-hackinghackingllm-securityoffensive-securitypenetration-testingpentesting-toolsred-teamingsecuritysecurity-automation
chore(prompt): enforce single tool call per message and remove stop word usage
0xallamf6475cec0709
diff --git a/strix/agents/StrixAgent/system_prompt.jinja b/strix/agents/StrixAgent/system_prompt.jinjaindex 038e0394..e839d6b9 100644--- a/strix/agents/StrixAgent/system_prompt.jinja+++ b/strix/agents/StrixAgent/system_prompt.jinja@@ -308,9 +308,9 @@ Tool calls use XML format:CRITICAL RULES:0. While active in the agent loop, EVERY message you output MUST be a single tool call. Do not send plain text-only responses.-1. One tool call per message+1. Exactly one tool call per message — never include more than one <function>...</function> block in a single LLM message.2. Tool call must be last in message-3. EVERY tool call MUST end with </function>. This is MANDATORY. Never omit the closing tag. The </function> tag is your stop word - end your response immediately after it.+3. EVERY tool call MUST end with </function>. This is MANDATORY. Never omit the closing tag. End your response immediately after </function>.4. Use ONLY the exact XML format shown above. NEVER use JSON/YAML/INI or any other syntax for tools or parameters.5. Tool names must match exactly the tool "name" defined (no module prefixes, dots, or variants).- Correct: <function=think> ... </function>diff --git a/strix/llm/llm.py b/strix/llm/llm.pyindex 1f096f0f..42f77fc9 100644--- a/strix/llm/llm.py+++ b/strix/llm/llm.py@@ -141,6 +141,8 @@ class LLM:accumulated = accumulated[: accumulated.find("</function>") + len("</function>")]+ yield LLMResponse(content=accumulated)+ breakyield LLMResponse(content=accumulated)if chunks:@@ -189,7 +191,6 @@ class LLM:"messages": messages,"timeout": self.config.timeout,"stream_options": {"include_usage": True},- "stop": ["</function>"],}if api_key := Config.get("llm_api_key"):