Merge remote-tracking branch 'origin/litellm_bedrock_sanitize_tool_use_id' into litellm_bedrock_sanitize_tool_use_id

litellm/litellm_core_utils/prompt_templates/factory.py

@@ -1500,32 +1500,29 @@ def convert_to_gemini_tool_call_result(
     return _part
 
 
-def _sanitize_anthropic_tool_use_id(tool_use_id: str) -> str:
-    """
-    Sanitize tool_use_id to match Anthropic's required pattern: ^[a-zA-Z0-9_-]+$
-
-    Anthropic requires tool_use_id to only contain alphanumeric characters, underscores, and hyphens.
-    This function replaces any invalid characters with underscores.
-    """
-    # Replace any character that's not alphanumeric, underscore, or hyphen with underscore
-    sanitized = re.sub(r"[^a-zA-Z0-9_-]", "_", tool_use_id)
-    # Ensure it's not empty (fallback to a default if needed)
-    if not sanitized:
-        sanitized = "tool_use_id"
-    return sanitized
-
-
+_TOOL_USE_ID_FALLBACK: Final = "tool_use_id"
+_ANTHROPIC_TOOL_USE_ID_INVALID_CHARS: Final = re.compile(r"[^a-zA-Z0-9_-]")
+_BEDROCK_TOOL_USE_ID_INVALID_CHARS: Final = re.compile(r"[^a-zA-Z0-9_.:-]")
 _BEDROCK_TOOL_USE_ID_MAX_LEN: Final = 64
 _BEDROCK_TOOL_USE_ID_HASH_LEN: Final = 8
 
 
+def _replace_invalid_tool_use_id_chars(tool_use_id: str, invalid_chars: re.Pattern[str]) -> str:
+    return invalid_chars.sub("_", tool_use_id) or _TOOL_USE_ID_FALLBACK
+
+
+def _sanitize_anthropic_tool_use_id(tool_use_id: str) -> str:
+    """Anthropic requires tool_use_id to match ^[a-zA-Z0-9_-]+$."""
+    return _replace_invalid_tool_use_id_chars(tool_use_id, _ANTHROPIC_TOOL_USE_ID_INVALID_CHARS)
+
+
 def _sanitize_bedrock_tool_use_id(tool_use_id: str) -> str:
     """
     Bedrock Converse requires toolUseId to match [a-zA-Z0-9_.:-]+ and be at most 64 chars.
     Ids that need rewriting get a short hash of the original appended so two ids that only
     differ in a replaced char or past the cut still map to distinct values.
     """
-    sanitized: Final = re.sub(r"[^a-zA-Z0-9_.:-]", "_", tool_use_id) or "tool_use_id"
+    sanitized: Final = _replace_invalid_tool_use_id_chars(tool_use_id, _BEDROCK_TOOL_USE_ID_INVALID_CHARS)
     if sanitized == tool_use_id and len(sanitized) <= _BEDROCK_TOOL_USE_ID_MAX_LEN:
         return sanitized
     digest: Final = hashlib.sha256(tool_use_id.encode()).hexdigest()[:_BEDROCK_TOOL_USE_ID_HASH_LEN]

tests/test_litellm/litellm_core_utils/prompt_templates/test_litellm_core_utils_prompt_templates_factory.py

@@ -20,6 +20,7 @@ from litellm.litellm_core_utils.prompt_templates.factory import (
     _convert_to_bedrock_tool_call_invoke,
     _convert_to_bedrock_tool_call_result,
     anthropic_messages_pt,
+    convert_to_anthropic_tool_result,
     convert_to_gemini_tool_call_result,
     make_valid_bedrock_tool_name,
     ollama_pt,
@@ -2219,6 +2220,7 @@ _BEDROCK_TOOL_USE_ID_RE = re.compile(r"^[a-zA-Z0-9_.:-]{1,64}$")
         "call|with|pipes",
         "call_" + "y" * 60 + "|end",
         "call:ok.dots-and_under",
+        "",
     ],
 )
 def test_bedrock_tool_use_id_is_sanitized_consistently_for_invoke_and_result(tool_call_id):
@@ -2291,6 +2293,21 @@ def test_bedrock_tool_call_invoke_concatenated_json_long_id_stays_within_limit()
     assert all(_BEDROCK_TOOL_USE_ID_RE.match(i) for i in ids)
 
 
+@pytest.mark.parametrize(
+    ("tool_call_id", "expected"),
+    [
+        ("call|with|pipes", "call_with_pipes"),
+        ("call:ok.dots", "call_ok_dots"),
+        ("call_" + "x" * 100, "call_" + "x" * 100),
+        ("toolu_01AbC-xyz", "toolu_01AbC-xyz"),
+        ("", "tool_use_id"),
+    ],
+)
+def test_anthropic_tool_use_id_keeps_pattern_only_rewrite_with_no_cap_or_hash(tool_call_id, expected):
+    result = convert_to_anthropic_tool_result({"role": "tool", "tool_call_id": tool_call_id, "content": "ok"})
+    assert result["tool_use_id"] == expected
+
+
 def test_bedrock_tool_call_invoke_concatenated_json():
     """
     Tool call whose arguments contain multiple concatenated JSON objects