Open-source release for Alpha version

strix/llm/utils.py

@@ -0,0 +1,84 @@
+import re
+from typing import Any
+
+
+def _truncate_to_first_function(content: str) -> str:
+    if not content:
+        return content
+
+    function_starts = [match.start() for match in re.finditer(r"<function=", content)]
+
+    if len(function_starts) >= 2:
+        second_function_start = function_starts[1]
+
+        return content[:second_function_start].rstrip()
+
+    return content
+
+
+def parse_tool_invocations(content: str) -> list[dict[str, Any]] | None:
+    content = _fix_stopword(content)
+
+    tool_invocations: list[dict[str, Any]] = []
+
+    fn_regex_pattern = r"<function=([^>]+)>\n?(.*?)</function>"
+    fn_param_regex_pattern = r"<parameter=([^>]+)>(.*?)</parameter>"
+
+    fn_matches = re.finditer(fn_regex_pattern, content, re.DOTALL)
+
+    for fn_match in fn_matches:
+        fn_name = fn_match.group(1)
+        fn_body = fn_match.group(2)
+
+        param_matches = re.finditer(fn_param_regex_pattern, fn_body, re.DOTALL)
+
+        args = {}
+        for param_match in param_matches:
+            param_name = param_match.group(1)
+            param_value = param_match.group(2).strip()
+            args[param_name] = param_value
+
+        tool_invocations.append({"toolName": fn_name, "args": args})
+
+    return tool_invocations if tool_invocations else None
+
+
+def _fix_stopword(content: str) -> str:
+    if "<function=" in content and content.count("<function=") == 1:
+        if content.endswith("</"):
+            content = content.rstrip() + "function>"
+        elif not content.rstrip().endswith("</function>"):
+            content = content + "\n</function>"
+    return content
+
+
+def format_tool_call(tool_name: str, args: dict[str, Any]) -> str:
+    xml_parts = [f"<function={tool_name}>"]
+
+    for key, value in args.items():
+        xml_parts.append(f"<parameter={key}>{value}</parameter>")
+
+    xml_parts.append("</function>")
+
+    return "\n".join(xml_parts)
+
+
+def clean_content(content: str) -> str:
+    if not content:
+        return ""
+
+    content = _fix_stopword(content)
+
+    tool_pattern = r"<function=[^>]+>.*?</function>"
+    cleaned = re.sub(tool_pattern, "", content, flags=re.DOTALL)
+
+    hidden_xml_patterns = [
+        r"<inter_agent_message>.*?</inter_agent_message>",
+        r"<agent_completion_report>.*?</agent_completion_report>",
+    ]
+    for pattern in hidden_xml_patterns:
+        cleaned = re.sub(pattern, "", cleaned, flags=re.DOTALL | re.IGNORECASE)
+
+    cleaned = re.sub(r"\n\s*\n", "\n\n", cleaned)
+
+    return cleaned.strip()