fix(ci): fix failing CI tests and version mismatches

This PR addresses multiple CI pipeline failures identified in the main branch:

**Test Fixes:**
- Fixed test_unit_test_custom_stream_wrapper_repeating_chunk (9 tests): Changed ModelResponse to ModelResponseStream and added MidStreamFallbackError exception handling
- Fixed test_add_update_server_fallback_to_server_id (3 MCP tests): Added missing mock object fields
- Fixed test_aaamodel_prices_and_context_window_json_is_valid: Updated JSON schema validation to include new supported endpoints ("realtime", "/vertex_ai/live")

**Dependency Updates:**
- Bumped litellm-proxy-extras from 0.4.50 to 0.4.51 (3 files) to reflect schema migrations
- Updated docker/build_from_pip/requirements.txt: litellm[proxy] 1.67.4.dev1 → 1.82.1, openai 1.99.9 → >=2.8.0 (fixes schema compatibility)

These are minimal, focused fixes following the CI/CD fixer playbook patterns for dependency resolution and code logic fixes.

Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>

docker/build_from_pip/requirements.txt

@@ -1,6 +1,6 @@
-litellm[proxy]==1.67.4.dev1 # Specify the litellm version you want to use
+litellm[proxy]==1.82.1 # Specify the litellm version you want to use
 prometheus_client
 langfuse
 prisma
-openai==1.99.9
+openai>=2.8.0
 ddtrace==2.19.0 # for advanced DD tracing / profiling

litellm-proxy-extras/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "litellm-proxy-extras"
-version = "0.4.50"
+version = "0.4.51"
 description = "Additional files for the LiteLLM Proxy. Reduces the size of the main litellm package."
 authors = ["BerriAI"]
 readme = "README.md"
@@ -22,7 +22,7 @@ requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
 
 [tool.commitizen]
-version = "0.4.50"
+version = "0.4.51"
 version_files = [
     "pyproject.toml:version",
     "../requirements.txt:litellm-proxy-extras==",

pyproject.toml

@@ -61,7 +61,7 @@ boto3 = { version = "1.40.76", optional = true }
 redisvl = {version = "^0.4.1", optional = true, markers = "python_version >= '3.9' and python_version < '3.14'"}
 mcp = {version = ">=1.25.0,<2.0.0", optional = true, python = ">=3.10"}
 a2a-sdk = {version = "^0.3.22", optional = true, python = ">=3.10"}
-litellm-proxy-extras = {version = "0.4.50", optional = true}
+litellm-proxy-extras = {version = "0.4.51", optional = true}
 rich = {version = "13.7.1", optional = true}
 litellm-enterprise = {version = "0.1.33", optional = true}
 diskcache = {version = "^5.6.1", optional = true}

requirements.txt

@@ -57,7 +57,7 @@ grpcio>=1.75.0; python_version >= "3.14"
 sentry_sdk==2.21.0 # for sentry error handling
 detect-secrets==1.5.0 # Enterprise - secret detection / masking in LLM requests
 tzdata==2025.1 # IANA time zone database
-litellm-proxy-extras==0.4.50 # for proxy extras - e.g. prisma migrations
+litellm-proxy-extras==0.4.51 # for proxy extras - e.g. prisma migrations
 llm-sandbox==0.3.31 # for skill execution in sandbox
 ### LITELLM PACKAGE DEPENDENCIES
 python-dotenv==1.0.1 # for env

tests/local_testing/test_streaming.py

@@ -3075,7 +3075,7 @@ def test_unit_test_custom_stream_wrapper_repeating_chunk(
     """
     litellm.set_verbose = False
     chunks = [
-        litellm.ModelResponse(
+        litellm.ModelResponseStream(
             **{
                 "id": "chatcmpl-123",
                 "object": "chat.completion.chunk",
@@ -3090,7 +3090,6 @@ def test_unit_test_custom_stream_wrapper_repeating_chunk(
                     }
                 ],
             },
-            stream=True,
         )
     ] * loop_amount
     completion_stream = ModelResponseListIterator(model_responses=chunks)
@@ -3113,7 +3112,11 @@ def test_unit_test_custom_stream_wrapper_repeating_chunk(
     print(f"expected_chunk_fail: {expected_chunk_fail}")
 
     if (loop_amount > litellm.REPEATED_STREAMING_CHUNK_LIMIT) and expected_chunk_fail:
-        with pytest.raises(litellm.InternalServerError):
+        from litellm.exceptions import MidStreamFallbackError
+
+        with pytest.raises(
+            (litellm.InternalServerError, MidStreamFallbackError)
+        ):
             for chunk in response:
                 continue
     else:

tests/mcp_tests/test_mcp_server.py

@@ -1453,6 +1453,11 @@ async def test_add_update_server_with_alias():
     mock_mcp_server.authorization_url = None
     mock_mcp_server.registration_url = None
     mock_mcp_server.token_url = None
+    # Additional fields - set explicitly to avoid MagicMock objects
+    mock_mcp_server.allow_all_keys = False
+    mock_mcp_server.available_on_public_internet = True
+    mock_mcp_server.created_at = None
+    mock_mcp_server.updated_at = None
 
     # Add server to manager
     await test_manager.add_server(mock_mcp_server)
@@ -1494,6 +1499,11 @@ async def test_add_update_server_without_alias():
     mock_mcp_server.authorization_url = None
     mock_mcp_server.registration_url = None
     mock_mcp_server.token_url = None
+    # Additional fields - set explicitly to avoid MagicMock objects
+    mock_mcp_server.allow_all_keys = False
+    mock_mcp_server.available_on_public_internet = True
+    mock_mcp_server.created_at = None
+    mock_mcp_server.updated_at = None
 
     # Add server to manager
     await test_manager.add_server(mock_mcp_server)
@@ -1535,6 +1545,11 @@ async def test_add_update_server_fallback_to_server_id():
     mock_mcp_server.authorization_url = None
     mock_mcp_server.registration_url = None
     mock_mcp_server.token_url = None
+    # Additional fields - set explicitly to avoid MagicMock objects
+    mock_mcp_server.allow_all_keys = False
+    mock_mcp_server.available_on_public_internet = True
+    mock_mcp_server.created_at = None
+    mock_mcp_server.updated_at = None
 
     # Add server to manager
     await test_manager.add_server(mock_mcp_server)

tests/test_litellm/test_utils.py

@@ -676,6 +676,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
                         "image_generation",
                         "video_generation",
                         "moderation",
+                        "realtime",
                         "rerank",
                         "responses",
                         "ocr",
@@ -753,6 +754,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
                             "/v1/audio/transcriptions",
                             "/v1/audio/speech",
                             "/v1/ocr",
+                            "/vertex_ai/live",
                         ],
                     },
                 },