Merge branch 'main' into codex/fix-codeql-alert-28

lib/crewai/src/crewai/llms/providers/azure/completion.py

@@ -4,6 +4,7 @@ import json
 import logging
 import os
 from typing import TYPE_CHECKING, Any, TypedDict
+from urllib.parse import urlparse
 
 from pydantic import BaseModel
 from typing_extensions import Self
@@ -175,11 +176,51 @@ class AzureCompletion(BaseLLM):
             prefix in model.lower() for prefix in ["gpt-", "o1-", "text-"]
         )
 
-        self.is_azure_openai_endpoint = (
-            "openai.azure.com" in self.endpoint
-            and "/openai/deployments/" in self.endpoint
+        self.is_azure_openai_endpoint = self._is_azure_openai_deployment_endpoint(
+            self.endpoint
         )
 
+    @staticmethod
+    def _parse_endpoint_url(endpoint: str):
+        parsed_endpoint = urlparse(endpoint)
+        if parsed_endpoint.hostname:
+            return parsed_endpoint
+
+        # Support endpoint values without a URL scheme.
+        return urlparse(f"https://{endpoint}")
+
+    @staticmethod
+    def _is_azure_openai_hostname(endpoint: str) -> bool:
+        parsed_endpoint = AzureCompletion._parse_endpoint_url(endpoint)
+        hostname = parsed_endpoint.hostname or ""
+        labels = [label for label in hostname.lower().split(".") if label]
+
+        return len(labels) >= 3 and labels[-3:] == ["openai", "azure", "com"]
+
+    @staticmethod
+    def _get_endpoint_path_segments(endpoint: str) -> list[str]:
+        parsed_endpoint = AzureCompletion._parse_endpoint_url(endpoint)
+        return [segment for segment in parsed_endpoint.path.split("/") if segment]
+
+    @staticmethod
+    def _is_azure_openai_deployment_endpoint(endpoint: str) -> bool:
+        if not AzureCompletion._is_azure_openai_hostname(endpoint):
+            return False
+
+        path_segments = AzureCompletion._get_endpoint_path_segments(endpoint)
+        return len(path_segments) >= 3 and path_segments[:2] == [
+            "openai",
+            "deployments",
+        ]
+
+    @staticmethod
+    def _is_azure_openai_deployments_collection(endpoint: str) -> bool:
+        if not AzureCompletion._is_azure_openai_hostname(endpoint):
+            return False
+
+        path_segments = AzureCompletion._get_endpoint_path_segments(endpoint)
+        return path_segments == ["openai", "deployments"]
+
     @staticmethod
     def _validate_and_fix_endpoint(endpoint: str, model: str) -> str:
         """Validate and fix Azure endpoint URL format.
@@ -194,10 +235,12 @@ class AzureCompletion(BaseLLM):
         Returns:
             Validated and potentially corrected endpoint URL
         """
-        if "openai.azure.com" in endpoint and "/openai/deployments/" not in endpoint:
+        if AzureCompletion._is_azure_openai_hostname(
+            endpoint
+        ) and not AzureCompletion._is_azure_openai_deployment_endpoint(endpoint):
             endpoint = endpoint.rstrip("/")
 
-            if not endpoint.endswith("/openai/deployments"):
+            if not AzureCompletion._is_azure_openai_deployments_collection(endpoint):
                 deployment_name = model.replace("azure/", "")
                 endpoint = f"{endpoint}/openai/deployments/{deployment_name}"
                 logging.info(f"Constructed Azure OpenAI endpoint URL: {endpoint}")

lib/crewai/tests/llms/azure/test_azure.py

@@ -958,6 +958,34 @@ def test_azure_endpoint_detection_flags():
         assert llm_other.is_azure_openai_endpoint == False
 
 
+def test_azure_endpoint_detection_ignores_spoofed_urls():
+    """
+    Test that endpoint detection does not trust spoofed host/path substrings
+    """
+    with patch.dict(os.environ, {
+        "AZURE_API_KEY": "test-key",
+        "AZURE_ENDPOINT": (
+            "https://evil.example.com/?redirect="
+            "https://test.openai.azure.com/openai/deployments/gpt-4"
+        ),
+    }):
+        llm_query_spoof = LLM(model="azure/gpt-4")
+        assert llm_query_spoof.is_azure_openai_endpoint == False
+        assert "model" in llm_query_spoof._prepare_completion_params(
+            messages=[{"role": "user", "content": "test"}]
+        )
+
+    with patch.dict(os.environ, {
+        "AZURE_API_KEY": "test-key",
+        "AZURE_ENDPOINT": "https://test.openai.azure.com.evil/openai/deployments/gpt-4",
+    }):
+        llm_host_spoof = LLM(model="azure/gpt-4")
+        assert llm_host_spoof.is_azure_openai_endpoint == False
+        assert "model" in llm_host_spoof._prepare_completion_params(
+            messages=[{"role": "user", "content": "test"}]
+        )
+
+
 def test_azure_improved_error_messages():
     """
     Test that improved error messages are provided for common HTTP errors

pyproject.toml

@@ -10,7 +10,7 @@ authors = [
 dev = [
     "ruff==0.14.7",
     "mypy==1.19.0",
-    "pre-commit==4.5.1",
+    "pre-commit==4.5.0",
     "bandit==1.9.2",
     "pytest==8.4.2",
     "pytest-asyncio==1.3.0",

uv.lock

@@ -41,7 +41,7 @@ dev = [
     { name = "bandit", specifier = "==1.9.2" },
     { name = "boto3-stubs", extras = ["bedrock-runtime"], specifier = "==1.40.54" },
     { name = "mypy", specifier = "==1.19.0" },
-    { name = "pre-commit", specifier = "==4.5.1" },
+    { name = "pre-commit", specifier = "==4.5.0" },
     { name = "pytest", specifier = "==8.4.2" },
     { name = "pytest-asyncio", specifier = "==1.3.0" },
     { name = "pytest-randomly", specifier = "==4.0.1" },
@@ -5346,7 +5346,7 @@ wheels = [
 
 [[package]]
 name = "pre-commit"
-version = "4.5.1"
+version = "4.5.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "cfgv" },
@@ -5355,9 +5355,9 @@ dependencies = [
     { name = "pyyaml" },
     { name = "virtualenv" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/40/f1/6d86a29246dfd2e9b6237f0b5823717f60cad94d47ddc26afa916d21f525/pre_commit-4.5.1.tar.gz", hash = "sha256:eb545fcff725875197837263e977ea257a402056661f09dae08e4b149b030a61", size = 198232, upload-time = "2025-12-16T21:14:33.552Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/f4/9b/6a4ffb4ed980519da959e1cf3122fc6cb41211daa58dbae1c73c0e519a37/pre_commit-4.5.0.tar.gz", hash = "sha256:dc5a065e932b19fc1d4c653c6939068fe54325af8e741e74e88db4d28a4dd66b", size = 198428, upload-time = "2025-11-22T21:02:42.304Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/5d/19/fd3ef348460c80af7bb4669ea7926651d1f95c23ff2df18b9d24bab4f3fa/pre_commit-4.5.1-py2.py3-none-any.whl", hash = "sha256:3b3afd891e97337708c1674210f8eba659b52a38ea5f822ff142d10786221f77", size = 226437, upload-time = "2025-12-16T21:14:32.409Z" },
+    { url = "https://files.pythonhosted.org/packages/5d/c4/b2d28e9d2edf4f1713eb3c29307f1a63f3d67cf09bdda29715a36a68921a/pre_commit-4.5.0-py2.py3-none-any.whl", hash = "sha256:25e2ce09595174d9c97860a95609f9f852c0614ba602de3561e267547f2335e1", size = 226429, upload-time = "2025-11-22T21:02:40.836Z" },
 ]
 
 [[package]]