chore(release): backport #27319, #27756, #27921, #28395, #29983, #29984, #29986, #30160, #30327 to stable/1.84.x and cut 1.84.8

.github/workflows/test-unit-proxy-db.yml

@@ -100,6 +100,7 @@ jobs:
             test-path: >-
               tests/proxy_unit_tests/test_auth_checks.py
               tests/proxy_unit_tests/test_user_api_key_auth.py
+              tests/proxy_unit_tests/test_deprecated_key_grace_period.py
             workers: 4
             dist: loadscope
             timeout: 15

litellm/llms/anthropic/chat/handler.py

@@ -557,6 +557,10 @@ def __init__(
         # Accumulate compaction blocks for multi-turn reconstruction
         self.compaction_blocks: List[Dict[str, Any]] = []
 
+        # Accumulate streamed thinking text so final usage can split reasoning
+        # tokens from regular output tokens.
+        self.reasoning_content_chunks: List[str] = []
+
         # Track server tool use inputs and results for code_interpreter_results
         self._server_tool_inputs: Dict[str, Any] = {}
         self.tool_results: List[Dict[str, Any]] = []
@@ -587,9 +591,14 @@ def check_empty_tool_call_args(self) -> bool:
         return False
 
     def _handle_usage(self, anthropic_usage_chunk: Union[dict, UsageDelta]) -> Usage:
+        reasoning_content = (
+            "".join(self.reasoning_content_chunks)
+            if self.reasoning_content_chunks
+            else None
+        )
         return AnthropicConfig().calculate_usage(
             usage_object=cast(dict, anthropic_usage_chunk),
-            reasoning_content=None,
+            reasoning_content=reasoning_content,
             speed=self.speed,
         )
 
@@ -636,10 +645,13 @@ def _content_block_delta_helper(self, chunk: dict) -> Tuple[
             "thinking" in content_block["delta"]
             or "signature" in content_block["delta"]
         ):
+            thinking_content = content_block["delta"].get("thinking")
+            if isinstance(thinking_content, str) and thinking_content:
+                self.reasoning_content_chunks.append(thinking_content)
             thinking_blocks = [
                 ChatCompletionThinkingBlock(
                     type="thinking",
-                    thinking=content_block["delta"].get("thinking") or "",
+                    thinking=thinking_content or "",
                     signature=str(content_block["delta"].get("signature") or ""),
                 )
             ]

litellm/llms/anthropic/chat/transformation.py

@@ -1856,8 +1856,16 @@ def calculate_usage(
         speed: Optional[str] = None,
     ) -> Usage:
         # NOTE: Sometimes the usage object has None set explicitly for token counts, meaning .get() & key access returns None, and we need to account for this
-        prompt_tokens = usage_object.get("input_tokens", 0) or 0
-        completion_tokens = usage_object.get("output_tokens", 0) or 0
+        raw_prompt_tokens = usage_object.get("input_tokens", 0) or 0
+        prompt_tokens: int = (
+            int(raw_prompt_tokens) if isinstance(raw_prompt_tokens, (int, float)) else 0
+        )
+        raw_completion_tokens = usage_object.get("output_tokens", 0) or 0
+        completion_tokens: int = (
+            int(raw_completion_tokens)
+            if isinstance(raw_completion_tokens, (int, float))
+            else 0
+        )
         _usage = usage_object
         cache_creation_input_tokens: int = 0
         cache_read_input_tokens: int = 0
@@ -1926,11 +1934,12 @@ def calculate_usage(
             text_tokens=raw_input_tokens,
         )
         # Always populate completion_token_details, not just when there's reasoning_content
-        reasoning_tokens = (
+        estimated_reasoning_tokens = (
             token_counter(text=reasoning_content, count_response_tokens=True)
             if reasoning_content
             else 0
         )
+        reasoning_tokens = min(estimated_reasoning_tokens, completion_tokens)
         completion_token_details = CompletionTokensDetailsWrapper(
             reasoning_tokens=reasoning_tokens if reasoning_tokens > 0 else 0,
             text_tokens=(

litellm/llms/azure/containers/transformation.py

@@ -1,9 +1,16 @@
 from typing import Optional
+from urllib.parse import parse_qs, urlparse, urlunparse
 
 from litellm.llms.azure.common_utils import BaseAzureLLM
 from litellm.llms.openai.containers.transformation import OpenAIContainerConfig
 from litellm.types.router import GenericLiteLLMParams
 
+# Endpoint-specific path suffixes that may appear in a deployment's api_base
+# (e.g. the responses endpoint URL is stored as api_base for Azure models).
+# Strip these before building the containers URL so we always start from the
+# resource root (https://resource.cognitiveservices.azure.com).
+_AZURE_ENDPOINT_PATHS = ("/openai/responses",)
+
 
 class AzureContainerConfig(OpenAIContainerConfig):
     """
@@ -27,6 +34,27 @@ def validate_environment(
             litellm_params=GenericLiteLLMParams(api_key=api_key),
         )
 
+    @staticmethod
+    def _normalize_api_base(api_base: Optional[str]) -> Optional[str]:
+        """Strip endpoint-specific path suffixes from api_base to get the resource root."""
+        if not api_base:
+            return api_base
+        parsed = urlparse(api_base)
+        path = parsed.path.rstrip("/")
+        for ep in _AZURE_ENDPOINT_PATHS:
+            if path.endswith(ep):
+                return urlunparse(
+                    (parsed.scheme, parsed.netloc, path[: -len(ep)], "", "", "")
+                )
+        return api_base
+
+    @staticmethod
+    def _extract_api_version(api_base: Optional[str]) -> Optional[str]:
+        """Return the api-version query param from api_base if present."""
+        if not api_base:
+            return None
+        return parse_qs(urlparse(api_base).query).get("api-version", [None])[0]
+
     def get_complete_url(
         self,
         api_base: Optional[str],
@@ -39,10 +67,19 @@ def get_complete_url(
           {endpoint}/openai/v1/containers
         when api_version is 'v1', 'latest', or 'preview'; otherwise:
           {endpoint}/openai/containers
+
+        The deployment's api_base may be the responses endpoint URL
+        (e.g. .../openai/responses?api-version=2025-04-01-preview). We
+        prefer the api-version embedded there over the deployment's
+        api_version field, which may point to an older chat API version.
         """
+        effective_params = dict(litellm_params)
+        api_version_from_base = self._extract_api_version(api_base)
+        if api_version_from_base:
+            effective_params["api_version"] = api_version_from_base
         return BaseAzureLLM._get_base_azure_url(
-            api_base=api_base,
-            litellm_params=litellm_params,
+            api_base=self._normalize_api_base(api_base),
+            litellm_params=effective_params,
             route="/openai/containers",
             default_api_version="v1",
         )

litellm/llms/custom_httpx/container_handler.py

@@ -257,26 +257,31 @@ def _sync_handle(
         returns_binary = endpoint_config.get("returns_binary", False)
         is_multipart = endpoint_config.get("is_multipart", False)
 
+        # An empty dict passed as `params` to httpx strips any existing query
+        # string from the URL (e.g. ?api-version=...).  Use None instead so
+        # httpx leaves the URL's own query string intact.
+        effective_params = query_params or None
+
         try:
             if method == "GET":
                 response = http_client.get(
-                    url=url, headers=headers, params=query_params
+                    url=url, headers=headers, params=effective_params
                 )
             elif method == "DELETE":
                 response = http_client.delete(
-                    url=url, headers=headers, params=query_params
+                    url=url, headers=headers, params=effective_params
                 )
             elif method == "POST":
                 if is_multipart and "file" in kwargs:
                     files, headers = _prepare_multipart_file_upload(
                         kwargs["file"], headers
                     )
                     response = http_client.post(
-                        url=url, headers=headers, params=query_params, files=files
+                        url=url, headers=headers, params=effective_params, files=files
                     )
                 else:
                     response = http_client.post(
-                        url=url, headers=headers, params=query_params
+                        url=url, headers=headers, params=effective_params
                     )
             else:
                 raise ValueError(f"Unsupported HTTP method: {method}")
@@ -376,26 +381,31 @@ async def _async_handle(
         returns_binary = endpoint_config.get("returns_binary", False)
         is_multipart = endpoint_config.get("is_multipart", False)
 
+        # An empty dict passed as `params` to httpx strips any existing query
+        # string from the URL (e.g. ?api-version=...).  Use None instead so
+        # httpx leaves the URL's own query string intact.
+        effective_params = query_params or None
+
         try:
             if method == "GET":
                 response = await http_client.get(
-                    url=url, headers=headers, params=query_params
+                    url=url, headers=headers, params=effective_params
                 )
             elif method == "DELETE":
                 response = await http_client.delete(
-                    url=url, headers=headers, params=query_params
+                    url=url, headers=headers, params=effective_params
                 )
             elif method == "POST":
                 if is_multipart and "file" in kwargs:
                     files, headers = _prepare_multipart_file_upload(
                         kwargs["file"], headers
                     )
                     response = await http_client.post(
-                        url=url, headers=headers, params=query_params, files=files
+                        url=url, headers=headers, params=effective_params, files=files
                     )
                 else:
                     response = await http_client.post(
-                        url=url, headers=headers, params=query_params
+                        url=url, headers=headers, params=effective_params
                     )
             else:
                 raise ValueError(f"Unsupported HTTP method: {method}")

litellm/llms/custom_httpx/llm_http_handler.py

@@ -7816,7 +7816,7 @@ def container_list_handler(
             response = sync_httpx_client.get(
                 url=url,
                 headers=headers,
-                params=params,
+                params=params or None,
             )
 
             return container_provider_config.transform_container_list_response(
@@ -7893,7 +7893,7 @@ async def async_container_list_handler(
             response = await async_httpx_client.get(
                 url=url,
                 headers=headers,
-                params=params,
+                params=params or None,
             )
 
             return container_provider_config.transform_container_list_response(
@@ -7983,7 +7983,7 @@ def container_retrieve_handler(
             response = sync_httpx_client.get(
                 url=url,
                 headers=headers,
-                params=params,
+                params=params or None,
             )
 
             return container_provider_config.transform_container_retrieve_response(
@@ -8060,7 +8060,7 @@ async def async_container_retrieve_handler(
             response = await async_httpx_client.get(
                 url=url,
                 headers=headers,
-                params=params,
+                params=params or None,
             )
 
             return container_provider_config.transform_container_retrieve_response(
@@ -8150,7 +8150,7 @@ def container_delete_handler(
             response = sync_httpx_client.delete(
                 url=url,
                 headers=headers,
-                params=params,
+                params=params or None,
             )
 
             return container_provider_config.transform_container_delete_response(
@@ -8227,7 +8227,7 @@ async def async_container_delete_handler(
             response = await async_httpx_client.delete(
                 url=url,
                 headers=headers,
-                params=params,
+                params=params or None,
             )
 
             return container_provider_config.transform_container_delete_response(
@@ -8323,7 +8323,7 @@ def container_file_list_handler(
             response = sync_httpx_client.get(
                 url=url,
                 headers=headers,
-                params=params,
+                params=params or None,
             )
 
             return container_provider_config.transform_container_file_list_response(
@@ -8402,7 +8402,7 @@ async def async_container_file_list_handler(
             response = await async_httpx_client.get(
                 url=url,
                 headers=headers,
-                params=params,
+                params=params or None,
             )
 
             return container_provider_config.transform_container_file_list_response(
@@ -8490,7 +8490,7 @@ def container_file_content_handler(
             response = sync_httpx_client.get(
                 url=url,
                 headers=headers,
-                params=params,
+                params=params or None,
             )
 
             return container_provider_config.transform_container_file_content_response(
@@ -8566,7 +8566,7 @@ async def async_container_file_content_handler(
             response = await async_httpx_client.get(
                 url=url,
                 headers=headers,
-                params=params,
+                params=params or None,
             )
 
             return container_provider_config.transform_container_file_content_response(

litellm/proxy/_types.py

@@ -2327,6 +2327,41 @@ class ConfigGeneralSettings(LiteLLMPydanticObjectBase):
     database_connection_timeout: Optional[float] = Field(
         60, description="default timeout for a connection to the database"
     )
+    database_connect_timeout: Optional[float] = Field(
+        None,
+        description=(
+            "Prisma `connect_timeout` URL param (seconds). Bounds how long the "
+            "engine waits to establish a new connection before failing. Defaults "
+            "to Prisma's built-in value when unset."
+        ),
+    )
+    database_socket_timeout: Optional[float] = Field(
+        None,
+        description=(
+            "Prisma `socket_timeout` URL param (seconds). When set, an idle/slow "
+            "connection that has not produced data within this window is closed. "
+            "This is the main knob for capping idle DB connections from LiteLLM."
+        ),
+    )
+    database_extra_connection_params: Optional[Dict[str, Any]] = Field(
+        None,
+        description=(
+            "Escape hatch: extra key/value pairs appended verbatim to the Prisma "
+            "DATABASE_URL / DIRECT_URL query string (e.g. `sslmode`, `pgbouncer`, "
+            "`statement_cache_size`). Keys here override any default LiteLLM sets."
+        ),
+    )
+    database_disable_prepared_statements: Optional[bool] = Field(
+        None,
+        description=(
+            "Disable server-side prepared statements by setting Prisma's "
+            "`pgbouncer=true` URL param. Use this for pgbouncer transaction-pooling "
+            "deployments, or to prevent the 'cached plan must not change result "
+            "type' error that pooled connections hit during rolling schema "
+            "migrations. An explicit `pgbouncer` in `database_extra_connection_params` "
+            "takes precedence."
+        ),
+    )
     database_type: Optional[Literal["dynamo_db"]] = Field(
         None, description="to use dynamodb instead of postgres db"
     )

litellm/proxy/auth/auth_exception_handler.py

@@ -134,6 +134,16 @@ async def _handle_authentication_error(
                 )
             elif isinstance(e, ProxyException):
                 raise e
+            if PrismaDBExceptionHandler.is_database_service_unavailable_error(e):
+                raise ProxyException(
+                    message=(
+                        "Service Unavailable, the authentication database is "
+                        "temporarily unreachable. Please retry shortly."
+                    ),
+                    type=ProxyErrorTypes.no_db_connection,
+                    param="None",
+                    code=status.HTTP_503_SERVICE_UNAVAILABLE,
+                )
             raise ProxyException(
                 message="Authentication Error, " + str(e),
                 type=ProxyErrorTypes.auth_error,

litellm/proxy/container_endpoints/endpoints.py

@@ -328,7 +328,7 @@ async def retrieve_container(
         custom_llm_provider=custom_llm_provider,
     )
     data.update(
-        get_container_forwarding_params(
+        await get_container_forwarding_params(
             container_id,
             original_container_id,
             custom_llm_provider,
@@ -433,7 +433,7 @@ async def delete_container(
         custom_llm_provider=custom_llm_provider,
     )
     data.update(
-        get_container_forwarding_params(
+        await get_container_forwarding_params(
             container_id,
             original_container_id,
             custom_llm_provider,