Litellm oss staging 1

litellm/llms/anthropic/chat/transformation.py

@@ -1506,9 +1506,21 @@ def map_openai_params(  # noqa: PLR0915
                 optional_params["metadata"] = {"user_id": value}
             elif param == "thinking":
                 optional_params["thinking"] = value
-            elif param == "reasoning_effort" and isinstance(value, str):
+            elif param == "reasoning_effort":
+                # Accept both string ("low") and dict ({"effort": "low",
+                # "summary": "concise"}). The Responses->Chat parser keeps the
+                # full dict when `summary` is set (see #25359), so a dict here
+                # is the standard shape Otto/OpenAI-Responses-Bridge callers
+                # send. Coerce to the effort string before mapping — same
+                # shape-tolerance the GPT-5 path already implements in
+                # `_normalize_reasoning_effort_for_chat_completion`.
+                effort_value = value
+                if isinstance(effort_value, dict):
+                    effort_value = effort_value.get("effort")
+                if not isinstance(effort_value, str):
+                    continue
                 mapped_thinking = AnthropicConfig._map_reasoning_effort(
-                    reasoning_effort=value,
+                    reasoning_effort=effort_value,
                     model=model,
                     llm_provider=self.custom_llm_provider or "anthropic",
                 )
@@ -1519,12 +1531,12 @@ def map_openai_params(  # noqa: PLR0915
                     optional_params["thinking"] = mapped_thinking
                     if AnthropicConfig._is_adaptive_thinking_model(model):
                         mapped_effort = REASONING_EFFORT_TO_OUTPUT_CONFIG_EFFORT.get(
-                            value
+                            effort_value
                         )
                         if mapped_effort is None:
                             AnthropicConfig._raise_invalid_reasoning_effort(
                                 model=model,
-                                value=value,
+                                value=effort_value,
                                 llm_provider=self.custom_llm_provider or "anthropic",
                             )
                         optional_params["output_config"] = {"effort": mapped_effort}

litellm/model_prices_and_context_window_backup.json

@@ -27296,6 +27296,58 @@
         "supports_web_search": true,
         "tpm": 800000
     },
+    "openrouter/google/gemini-3.1-flash-lite": {
+        "cache_read_input_token_cost": 2.5e-08,
+        "cache_read_input_token_cost_per_audio_token": 5e-08,
+        "input_cost_per_audio_token": 5e-07,
+        "input_cost_per_token": 2.5e-07,
+        "litellm_provider": "openrouter",
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_images_per_prompt": 3000,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65536,
+        "max_pdf_size_mb": 30,
+        "max_tokens": 65536,
+        "max_video_length": 1,
+        "max_videos_per_prompt": 10,
+        "mode": "chat",
+        "output_cost_per_reasoning_token": 1.5e-06,
+        "output_cost_per_token": 1.5e-06,
+        "rpm": 2000,
+        "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": false,
+        "supports_code_execution": true,
+        "supports_file_search": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "tpm": 800000
+    },
     "openrouter/google/gemini-3.1-pro-preview": {
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_above_200k_tokens": 4e-07,

litellm/proxy/_lazy_openapi_snapshot.json

@@ -3171,7 +3171,7 @@
           ]
         },
         "post": {
-          "description": "Create a new agent\n\nExample Request:\n```bash\ncurl -X POST \"http://localhost:4000/agents\" \\\n    -H \"Authorization: Bearer <your_api_key>\" \\\n    -H \"Content-Type: application/json\" \\\n    -d '{\n        \"agent\": {\n            \"agent_name\": \"my-custom-agent\",\n            \"agent_card_params\": {\n                \"protocolVersion\": \"1.0\",\n                \"name\": \"Hello World Agent\",\n                \"description\": \"Just a hello world agent\",\n                \"url\": \"http://localhost:9999/\",\n                \"version\": \"1.0.0\",\n                \"defaultInputModes\": [\"text\"],\n                \"defaultOutputModes\": [\"text\"],\n                \"capabilities\": {\n                    \"streaming\": true\n                },\n                \"skills\": [\n                    {\n                        \"id\": \"hello_world\",\n                        \"name\": \"Returns hello world\",\n                        \"description\": \"just returns hello world\",\n                        \"tags\": [\"hello world\"],\n                        \"examples\": [\"hi\", \"hello world\"]\n                    }\n                ]\n            },\n            \"litellm_params\": {\n                \"make_public\": true\n            }\n        }\n    }'\n```",
+          "description": "Create a new agent\n\nExample Request:\n```bash\ncurl -X POST \"http://localhost:4000/v1/agents\" \\\n    -H \"Authorization: Bearer <your_api_key>\" \\\n    -H \"Content-Type: application/json\" \\\n    -d '{\n        \"agent_name\": \"my-custom-agent\",\n            \"agent_card_params\": {\n                \"protocolVersion\": \"1.0\",\n                \"name\": \"Hello World Agent\",\n                \"description\": \"Just a hello world agent\",\n                \"url\": \"http://localhost:9999/\",\n                \"version\": \"1.0.0\",\n                \"defaultInputModes\": [\"text\"],\n                \"defaultOutputModes\": [\"text\"],\n                \"capabilities\": {\n                    \"streaming\": true\n                },\n                \"skills\": [\n                    {\n                        \"id\": \"hello_world\",\n                        \"name\": \"Returns hello world\",\n                        \"description\": \"just returns hello world\",\n                        \"tags\": [\"hello world\"],\n                        \"examples\": [\"hi\", \"hello world\"]\n                    }\n                ]\n            },\n            \"litellm_params\": {\n                \"make_public\": true\n       }\n    }'\n```",
           "operationId": "create_agent_v1_agents_post",
           "requestBody": {
             "content": {

litellm/proxy/management_endpoints/ui_sso.py

@@ -1798,7 +1798,10 @@ async def cli_sso_callback(
 
         from fastapi.responses import HTMLResponse
 
-        verify_url = str(request.url_for("cli_sso_complete", login_id=key))
+        verify_url = get_custom_url(
+            request_base_url=str(request.base_url),
+            route=f"sso/cli/complete/{key}",
+        )
         html_content = _render_cli_sso_verification_page(
             verify_url=verify_url,
             browser_complete_token=browser_complete_token,

litellm/responses/litellm_completion_transformation/handler.py

@@ -65,8 +65,7 @@ def response_api_handler(
         litellm_completion_response: Union[
             ModelResponse, litellm.CustomStreamWrapper
         ] = litellm.completion(
-            **litellm_completion_request,
-            **kwargs,
+            **completion_args,
         )
 
         if isinstance(litellm_completion_response, ModelResponse):

litellm/responses/main.py

@@ -1115,6 +1115,7 @@ def responses(
                 stream=stream,
                 extra_headers=extra_headers,
                 extra_body=extra_body,
+                timeout=timeout if timeout is not None else request_timeout,
                 **kwargs,
             )